{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/graph-attention-networks","title":"Graph Attention Networks","arxiv_id":"1710.10903","date":"2017-10-30","proceeding":"ICLR 2018 1","authors":["Petar Veličković","Guillem Cucurull","Arantxa Casanova","Adriana Romero","Pietro Liò","Yoshua Bengio"],"abstract":"We present graph attention networks (GATs), novel neural network\narchitectures that operate on graph-structured data, leveraging masked\nself-attentional layers to address the shortcomings of prior methods based on\ngraph convolutions or their approximations. By stacking layers in which nodes\nare able to attend over their neighborhoods' features, we enable (implicitly)\nspecifying different weights to different nodes in a neighborhood, without\nrequiring any kind of costly matrix operation (such as inversion) or depending\non knowing the graph structure upfront. In this way, we address several key\nchallenges of spectral-based graph neural networks simultaneously, and make our\nmodel readily applicable to inductive as well as transductive problems. Our GAT\nmodels have achieved or matched state-of-the-art results across four\nestablished transductive and inductive graph benchmarks: the Cora, Citeseer and\nPubmed citation network datasets, as well as a protein-protein interaction\ndataset (wherein test graphs remain unseen during training).","url_abs":"http://arxiv.org/abs/1710.10903v3","url_pdf":"http://arxiv.org/pdf/1710.10903v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/PetarV-/GAT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/404nofound/gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/4pygmalion/GAT_tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Anak2016/GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/AngusMonroe/GAT-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Anou9531/GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Aveek-Saha/Graph-Attention-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/BIG-S2/keras-gnm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/ChengSashankh/trying-GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/ChengyuSun/gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/ColdenChan/GAT_D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Diego999/pyGAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/GraphSAINT/GraphSAINT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/HazyResearch/hgcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/HeapHop30/graph-attention-nets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/IllinoisGraphBenchmark/IGB-Datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Kaimaoge/IGNNK","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Kristof-Neys/GAT_Neo4j_DGL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/MehmetBarutcu/Streaming-Algorithm-for-Monotone-k-Submodular-Maximization-with-Cardinality-Constraints","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Messham87/COVID_GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Negus25/GAT-Mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/PumpkinYing/GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/TyngJiunKuo/deep-learning-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/WantingZhao/my_GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Yindong-Zhang/myGAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/YunseobShin/wiki_GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/abhilash1910/GraphAttentionNetworks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/akash18tripathi/MAGNET-Multi-Label-Text-Classi-cation-using-Attention-based-Graph-Neural-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/alexOarga/haiku-geometric","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/anish-lu-yihe/SVRT-by-GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/arangoml/fastgraphml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/basiralab/RG-Select","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/basiralab/Reproducible-Generative-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/blueberryc/pyGAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/bowu/GraphSearch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/calciver/Graph-Attention-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/danielegrattarola/keras-gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/davidpicard/homm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/dmeoli/neuro-sat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/ds4dm/sGat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/ds4dm/sparse-gcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/dzb1998/pyGAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/fanzhenliu/dagad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/fongyk/graph-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/galkampel/HyperNetworks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/gayanku/FDGATII","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/gcucurull/jax-gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/giuseppefutia/link-prediction-code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/gmum/umwpl2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/gordicaleksa/pytorch-GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/handasontam/GAT-with-edgewise-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/isotlaboratory/ml4vrp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/joaopedromattos/gnee","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/liu6zijian/simplified-gcn-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/marble0117/GNN_models_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/marble0117/GNN_models_pytorch_geometric","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/marblet/GNN_models_pytorch_geometric","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/marblet/gat-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/meliketoy/graph-cnn.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/mitya8128/experiments_notes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/mlzxzhou/keras-gnm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/nnaakkaaii/g2-MLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/noahtren/Graph-Attention-Networks-TensorFlow-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/pengsl-lab/mssl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/pengsl-lab/mssl2drug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/qema/orca-py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/shenweichen/GraphNeuralNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/shi27feng/transformers.satisfy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/snowkylin/gnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/snownus/COOP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/subercui/pyGConvAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/taishan1994/pytorch_gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/tatp22/pytorch-fast-GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/tlmakinen/GAT-noise","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/vailatuts/SSFG-regularization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/wan2000/mc-mot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/weiyangfb/PyTorchSparseGAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/whut2962575697/gat_sementic_segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/ydzhang-stormstout/HAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/yururyuru00/GAT_pyG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/zhangbo2008/GAT_network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/zhanglab-aim/cancer-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-2.0"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/zhao-tong/GNNs-easy-to-use","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/zxhhh97/ABot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/Mind23-2/MindCode-4/tree/main/gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/MindSpore-scientific-2/code-4/tree/main/GR-HSTU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/ak24watch/Graph-Deeplearning-GAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/tensorflow/gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/lukecavabarrett/pna","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"graph-attention-networks","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/gnn/gat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"heterogeneous-node-classification","task_name":"Heterogeneous Node Classification"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-classification-on-non-homophilic","task_name":"Node Classification on Non-Homophilic (Heterophilic) Graphs"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"}],"methods":[{"method_slug":"gat","method_name":"GAT"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gat","name":"GAT","full_name":"Graph Attention Network"}],"results":[{"leaderboard":"/sota/document-classification-on-cora","task":"Document Classification","dataset":"Cora","model":"GAT","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-cifar10-100k","task":"Graph Classification","dataset":"CIFAR10 100k","model":"GAT","rank_in_archive_order":18,"of":20,"metrics":{"Accuracy (%)":"65.48"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"GAT","rank_in_archive_order":50,"of":53,"metrics":{"Accuracy":"73.109±3.413"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"GAT","rank_in_archive_order":3,"of":54,"metrics":{"Accuracy":"78.611±1.556"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"GAT","rank_in_archive_order":3,"of":51,"metrics":{"Accuracy":"84.250±2.062"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"GAT","rank_in_archive_order":14,"of":69,"metrics":{"Accuracy":"85.109±1.107"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci109","task":"Graph Classification","dataset":"NCI109","model":"GAT","rank_in_archive_order":16,"of":38,"metrics":{"Accuracy":"82.560±0.601"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"GAT","rank_in_archive_order":39,"of":103,"metrics":{"Accuracy":"76.786±1.670"},"uses_additional_data":false},{"leaderboard":"/sota/graph-property-prediction-on-ogbg-code2","task":"Graph Property Prediction","dataset":"ogbg-code2","model":"GAT","rank_in_archive_order":16,"of":21,"metrics":{"Ext. data":"No","Number of params":"11030210","Test F1 score":"0.1569 ± 0.0010","Validation F1 score":"0.1442 ± 0.0017"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-esr2","task":"Graph Regression","dataset":"ESR2","model":"GAT","rank_in_archive_order":5,"of":9,"metrics":{"R2":"0.666±0.000","RMSE":"0.510±0.666"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-f2","task":"Graph Regression","dataset":"F2","model":"GAT","rank_in_archive_order":4,"of":9,"metrics":{"R2":"0.886±0.000","RMSE":"0.343±0.886"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-kit","task":"Graph Regression","dataset":"KIT","model":"GAT","rank_in_archive_order":4,"of":9,"metrics":{"R2":"0.833±0.000","RMSE":"0.443±0.833"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-lipophilicity-1","task":"Graph Regression","dataset":"Lipophilicity","model":"GAT","rank_in_archive_order":1,"of":1,"metrics":{"RMSE":"0.95"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-lipophilicity","task":"Graph Regression","dataset":"Lipophilicity","model":"GAT","rank_in_archive_order":3,"of":23,"metrics":{"R2":"0.820±0.014","RMSE":"0.536±0.020"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-parp1","task":"Graph Regression","dataset":"PARP1","model":"GAT","rank_in_archive_order":4,"of":9,"metrics":{"R2":"0.921±0.000","RMSE":"0.353±0.921"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-pgr","task":"Graph Regression","dataset":"PGR","model":"GAT","rank_in_archive_order":6,"of":9,"metrics":{"R2":"0.681±0.000","RMSE":"0.546±0.681"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-100k","task":"Graph Regression","dataset":"ZINC 100k","model":"GAT","rank_in_archive_order":8,"of":8,"metrics":{"MAE":"0.463"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-full","task":"Graph Regression","dataset":"ZINC-full","model":"GAT","rank_in_archive_order":16,"of":19,"metrics":{"Test MAE":"0.078±0.006"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-acm","task":"Heterogeneous Node Classification","dataset":"ACM (Heterogeneous Node Classification)","model":"GAT","rank_in_archive_order":11,"of":11,"metrics":{"Macro-F1":"92.26","Micro-F1":"92.19"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-2","task":"Heterogeneous Node Classification","dataset":"DBLP (Heterogeneous Node Classification)","model":"GAT","rank_in_archive_order":11,"of":11,"metrics":{"Macro-F1":"93.83","Micro-F1":"93.39"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-freebase","task":"Heterogeneous Node Classification","dataset":"Freebase (Heterogeneous Node Classification)","model":"GAT","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"65.26","Macro-F1":"40.74"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-imdb","task":"Heterogeneous Node Classification","dataset":"IMDB (Heterogeneous Node Classification)","model":"GAT","rank_in_archive_order":11,"of":11,"metrics":{"Macro-F1":"58.94","Micro-F1":"64.86"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-esol","task":"Molecular Property Prediction","dataset":"ESOL","model":"GAT","rank_in_archive_order":6,"of":20,"metrics":{"R2":"0.930±0.007","RMSE":"0.540±0.027"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-freesolv","task":"Molecular Property Prediction","dataset":"FreeSolv","model":"GAT","rank_in_archive_order":5,"of":22,"metrics":{"R2":"0.959±0.011","RMSE":"0.791±0.101"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-brazil-air-traffic","task":"Node Classification","dataset":"Brazil Air-Traffic","model":"GAT (Velickovic et al., 2018)","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"0.382"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20","task":"Node Classification","dataset":"Chameleon (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":21,"of":38,"metrics":{"1:1 Accuracy":"63.9 ± 0.46"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-05","task":"Node Classification","dataset":"CiteSeer (0.5%)","model":"GAT","rank_in_archive_order":13,"of":14,"metrics":{"Accuracy":"38.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-1","task":"Node Classification","dataset":"CiteSeer (1%)","model":"GAT","rank_in_archive_order":14,"of":14,"metrics":{"Accuracy":"46.5%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-60-20-20","task":"Node Classification","dataset":"CiteSeer (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":32,"of":33,"metrics":{"1:1 Accuracy":"67.20 ± 0.46"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-with-public","task":"Node Classification","dataset":"CiteSeer with Public Split: fixed 20 nodes per class","model":"GAT","rank_in_archive_order":27,"of":40,"metrics":{"Accuracy":"72.5 ± 0.7%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"GAT","rank_in_archive_order":42,"of":71,"metrics":{"Accuracy":"72.5 ± 0.7%","Training Split":"fixed 20 per node","Validation":"YES"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"GAT","rank_in_archive_order":44,"of":73,"metrics":{"Accuracy":"83.0% ± 0.7%","Training Split":"fixed 20 per node","Validation":"YES"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-05","task":"Node Classification","dataset":"Cora (0.5%)","model":"GAT","rank_in_archive_order":13,"of":15,"metrics":{"Accuracy":"41.4%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-1","task":"Node Classification","dataset":"Cora (1%)","model":"GAT","rank_in_archive_order":14,"of":15,"metrics":{"Accuracy":"48.6%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-3","task":"Node Classification","dataset":"Cora (3%)","model":"GAT","rank_in_archive_order":15,"of":15,"metrics":{"Accuracy":"56.8%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-60-20-20-random","task":"Node Classification","dataset":"Cora (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":31,"of":33,"metrics":{"1:1 Accuracy":"76.70 ± 0.42"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-with-public-split","task":"Node Classification","dataset":"Cora with Public Split: fixed 20 nodes per class","model":"GAT","rank_in_archive_order":23,"of":36,"metrics":{"Accuracy":"83.0 ± 0.7%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell-60-20-20","task":"Node Classification","dataset":"Cornell (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":26,"of":36,"metrics":{"1:1 Accuracy":"76.00 ± 1.01"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-europe-air-traffic","task":"Node Classification","dataset":"Europe Air-Traffic","model":"GAT (Velickovic et al., 2018)","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"42.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-film-60-20-20-random","task":"Node Classification","dataset":"Film (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":28,"of":37,"metrics":{"1:1 Accuracy":"35.98 ± 0.23"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-flickr","task":"Node Classification","dataset":"Flickr","model":"GAT (Velickovic et al., 2018)","rank_in_archive_order":8,"of":8,"metrics":{"Accuracy":"0.359"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pattern-100k","task":"Node Classification","dataset":"PATTERN 100k","model":"GAT","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy (%)":"75.824"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ppi","task":"Node Classification","dataset":"PPI","model":"GAT","rank_in_archive_order":16,"of":24,"metrics":{"F1":"97.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-penn94","task":"Node Classification","dataset":"Penn94","model":"GAT","rank_in_archive_order":19,"of":32,"metrics":{"Accuracy":"81.53 ± 0.55"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-003","task":"Node Classification","dataset":"PubMed (0.03%)","model":"GAT","rank_in_archive_order":12,"of":14,"metrics":{"Accuracy":"50.9%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-005","task":"Node Classification","dataset":"PubMed (0.05%)","model":"GAT","rank_in_archive_order":13,"of":14,"metrics":{"Accuracy":"50.4%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-01","task":"Node Classification","dataset":"PubMed (0.1%)","model":"GAT","rank_in_archive_order":13,"of":14,"metrics":{"Accuracy":"59.6%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-60-20-20-random","task":"Node Classification","dataset":"PubMed (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":37,"of":37,"metrics":{"1:1 Accuracy":"83.28 ± 0.12"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-with-public","task":"Node Classification","dataset":"PubMed with Public Split: fixed 20 nodes per class","model":"GAT","rank_in_archive_order":23,"of":37,"metrics":{"Accuracy":"79.0%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"GAT","rank_in_archive_order":53,"of":70,"metrics":{"Accuracy":"79.0 ± 0.3%","F1-Score":"79.0","Training Split":"fixed 20 per node","Validation":"YES"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20","task":"Node Classification","dataset":"Squirrel (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":24,"of":37,"metrics":{"1:1 Accuracy":"42.72 ± 0.33"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas-60-20-20-random","task":"Node Classification","dataset":"Texas (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":32,"of":36,"metrics":{"1:1 Accuracy":"78.87 ± 0.86"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-usa-air-traffic","task":"Node Classification","dataset":"USA Air-Traffic","model":"GAT (Velickovic et al., 2018)","rank_in_archive_order":4,"of":7,"metrics":{"Accuracy":"58.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wiki-vote","task":"Node Classification","dataset":"Wiki-Vote","model":"GAT (Velickovic et al., 2018)","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"59.4"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin-60-20-20","task":"Node Classification","dataset":"Wisconsin (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":29,"of":35,"metrics":{"1:1 Accuracy":"71.01 ± 4.66"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-genius","task":"Node Classification","dataset":"genius","model":"GAT","rank_in_archive_order":25,"of":26,"metrics":{"Accuracy":"55.80 ± 0.87"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-4","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Chameleon(60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":18,"of":32,"metrics":{"1:1 Accuracy":"63.9 ± 0.46"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Cornell (60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":26,"of":33,"metrics":{"1:1 Accuracy":"76.00 ± 1.01"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-6","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Deezer-Europe","model":"GAT","rank_in_archive_order":22,"of":28,"metrics":{"1:1 Accuracy":"61.09±0.77"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-13","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Penn94","model":"GAT","rank_in_archive_order":14,"of":28,"metrics":{"1:1 Accuracy":"81.53 ± 0.55"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-16","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Pubmed","model":"GAT","rank_in_archive_order":1,"of":1,"metrics":{"F1-Score":"59.89 ± 4.12","NMI":"55.80 ± 0.87"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-2","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Texas(60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":29,"of":32,"metrics":{"1:1 Accuracy":"78.87 ± 0.86"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-1","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"Wisconsin(60%/20%/20% random splits)","model":"GAT","rank_in_archive_order":26,"of":32,"metrics":{"1:1 Accuracy":"71.01 ± 4.66"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GAT+label reuse+self KD","rank_in_archive_order":25,"of":86,"metrics":{"Ext. data":"No","Number of params":"1441580","Test Accuracy":"0.7416 ± 0.0008","Validation Accuracy":"0.7514 ± 0.0004"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GAT+label+reuse+topo loss","rank_in_archive_order":30,"of":86,"metrics":{"Ext. data":"No","Number of params":"1441580","Test Accuracy":"0.7399 ± 0.0012","Validation Accuracy":"0.7513 ± 0.0009"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"GAT with NeighborSampling","rank_in_archive_order":48,"of":64,"metrics":{"Ext. data":"No","Number of params":"751574","Test Accuracy":"0.7945 ± 0.0059","Validation Accuracy":"Please tell us"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"GAT + labels + node2vec","rank_in_archive_order":8,"of":26,"metrics":{"Ext. data":"No","Number of params":"6360470","Test ROC-AUC":"0.8711 ± 0.0007","Validation ROC-AUC":"0.9217 ± 0.0011"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-j-hmbd","task":"Skeleton Based Action Recognition","dataset":"J-HMBD Early Action","model":"GAT","rank_in_archive_order":2,"of":2,"metrics":{"10%":"58.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.10903","atlas_url":"https://app.syntology.ai/?focus=1710.10903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10903"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10903"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10903"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.10903\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1710.10903"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1710.10903\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1710.10903"},"call":"get_concepts_for_paper(arxiv_id=\"1710.10903\")"}],"by_repo":[{"repo":"PetarV-/GAT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2006.11468"],"harvested_for_calls":[{"arxiv_id":"2006.11468","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.11468"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.11468\")"}]},{"repo":"404nofound/gat","kind":"listed","samples":6,"ran":5,"instrument":0,"unverified":1},{"repo":"4pygmalion/GAT_tensorflow","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"Anak2016/GAT","kind":"listed","samples":4,"ran":3,"instrument":2,"unverified":1},{"repo":"AngusMonroe/GAT-pytorch","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"Anou9531/GAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Aveek-Saha/Graph-Attention-Net","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"BIG-S2/keras-gnm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ChengSashankh/trying-GAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ChengyuSun/gat","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"ColdenChan/GAT_D","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"Diego999/pyGAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2109.14285"],"harvested_for_calls":[{"arxiv_id":"2109.14285","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.14285"},"call":"get_harvested_code_for_paper(arxiv_id=\"2109.14285\")"}]},{"repo":"GraphSAINT/GraphSAINT","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"HazyResearch/hgcn","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"HeapHop30/graph-attention-nets","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"IllinoisGraphBenchmark/IGB-Datasets","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Kaimaoge/IGNNK","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"Kristof-Neys/GAT_Neo4j_DGL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MehmetBarutcu/Streaming-Algorithm-for-Monotone-k-Submodular-Maximization-with-Cardinality-Constraints","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Messham87/COVID_GAT","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"Negus25/GAT-Mindspore","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PumpkinYing/GAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"TyngJiunKuo/deep-learning-project","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"WantingZhao/my_GAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Yindong-Zhang/myGAT","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"YunseobShin/wiki_GAT","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"abhilash1910/GraphAttentionNetworks","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"akash18tripathi/MAGNET-Multi-Label-Text-Classi-cation-using-Attention-based-Graph-Neural-Network","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"alexOarga/haiku-geometric","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.05718"],"harvested_for_calls":[{"arxiv_id":"2004.05718","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.05718"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.05718\")"}]},{"repo":"anish-lu-yihe/SVRT-by-GAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"arangoml/fastgraphml","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"basiralab/RG-Select","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"basiralab/Reproducible-Generative-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"blueberryc/pyGAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"bowu/GraphSearch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"calciver/Graph-Attention-Networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"danielegrattarola/keras-gat","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"davidpicard/homm","kind":"listed","samples":13,"ran":2,"instrument":2,"unverified":11},{"repo":"dmeoli/neuro-sat","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ds4dm/sGat","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"ds4dm/sparse-gcn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dzb1998/pyGAT","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"fanzhenliu/dagad","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"fongyk/graph-attention","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"galkampel/HyperNetworks","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"gayanku/FDGATII","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"gcucurull/jax-gat","kind":"listed","samples":4,"ran":3,"instrument":3,"unverified":1},{"repo":"giuseppefutia/link-prediction-code","kind":"listed","samples":4,"ran":3,"instrument":1,"unverified":1},{"repo":"gmum/umwpl2021","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"gordicaleksa/pytorch-GAT","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"handasontam/GAT-with-edgewise-attention","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"isotlaboratory/ml4vrp","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"joaopedromattos/gnee","kind":"listed","samples":4,"ran":2,"instrument":0,"unverified":2},{"repo":"liu6zijian/simplified-gcn-model","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"marble0117/GNN_models_pytorch","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"marble0117/GNN_models_pytorch_geometric","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"marblet/GNN_models_pytorch_geometric","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"marblet/gat-pytorch","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"meliketoy/graph-cnn.pytorch","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"mitya8128/experiments_notes","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mlzxzhou/keras-gnm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nnaakkaaii/g2-MLP","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"noahtren/Graph-Attention-Networks-TensorFlow-2","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"pengsl-lab/mssl","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"pengsl-lab/mssl2drug","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"qema/orca-py","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"shenweichen/GraphNeuralNetwork","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"shi27feng/transformers.satisfy","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"snowkylin/gnn","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"snownus/COOP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"subercui/pyGConvAT","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"taishan1994/pytorch_gat","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"tatp22/pytorch-fast-GAT","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"tlmakinen/GAT-noise","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vailatuts/SSFG-regularization","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"wan2000/mc-mot","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"weiyangfb/PyTorchSparseGAT","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"whut2962575697/gat_sementic_segmentation","kind":"listed","samples":6,"ran":4,"instrument":1,"unverified":2},{"repo":"ydzhang-stormstout/HAT","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"yururyuru00/GAT_pyG","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"zhangbo2008/GAT_network","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zhanglab-aim/cancer-net","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zhao-tong/GNNs-easy-to-use","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"zxhhh97/ABot","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"Mind23-2/MindCode-4","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-scientific-2/code-4","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ak24watch/Graph-Deeplearning-GAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dmlc/dgl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":6,"harvested_for":["1607.00653","1612.00222","1802.04364","1806.01973","2006.05582","2010.16103"],"harvested_for_calls":[{"arxiv_id":"1607.00653","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1607.00653"},"call":"get_harvested_code_for_paper(arxiv_id=\"1607.00653\")"},{"arxiv_id":"1612.00222","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1612.00222"},"call":"get_harvested_code_for_paper(arxiv_id=\"1612.00222\")"},{"arxiv_id":"1802.04364","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1802.04364"},"call":"get_harvested_code_for_paper(arxiv_id=\"1802.04364\")"},{"arxiv_id":"1806.01973","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1806.01973"},"call":"get_harvested_code_for_paper(arxiv_id=\"1806.01973\")"},{"arxiv_id":"2006.05582","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.05582"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.05582\")"},{"arxiv_id":"2010.16103","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.16103"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.16103\")"}]},{"repo":"labmlai/annotated_deep_learning_paper_implementations","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"lukecavabarrett/pna","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"mindspore-ai/models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.08084"],"harvested_for_calls":[{"arxiv_id":"2208.08084","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.08084"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.08084\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"04c39c60787f7b72","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims a novel neural network layer that leverages masked self-attentional mechanisms to operate on graph-structured data, addressing limitations of prior graph convolution methods.","centrality":"contribution","entry":"SpGraphAttentionLayer","entry_sha256":"f2e88290d89e5830","n_bricks":3,"bricks":[{"entry":"SpGraphAttentionLayer","code_sha256":"f2e88290d89e5830","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"SpecialSpmm","code_sha256":"499f87bed1d30f44","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"SpecialSpmmFunction","code_sha256":"3e9e9056af401802","role":"helper","order":2,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"0dce3d1c873ac859","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"Implements graph attention networks (GATs) using self-attentional layers to operate on graph-structured data, allowing nodes to attend over their neighborhoods.","centrality":"contribution","entry":"GATLayerImp3","entry_sha256":"21ba3ceb8353096e","n_bricks":3,"bricks":[{"entry":"GATLayerImp3","code_sha256":"21ba3ceb8353096e","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"GATLayer","code_sha256":"5d5e29ef042a08a8","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"LayerType","code_sha256":"dcd585593f9c47a5","role":"helper","order":2,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2347fc8cf4df093b","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a graph attention layer that uses masked self-attentional mechanisms to weigh node features in graph-structured data, as proposed in the Graph Attention Networks (GATs) paper.","centrality":"contribution","entry":"GraphAttention","entry_sha256":"5ef6599b549742dd","n_bricks":1,"bricks":[{"entry":"GraphAttention","code_sha256":"5ef6599b549742dd","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"299da02c12f88aba","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks (GATs), novel neural network architectures that use masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GAT","entry_sha256":"8e9b126f3a88cbdd","n_bricks":2,"bricks":[{"entry":"GAT","code_sha256":"8e9b126f3a88cbdd","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseGAttN","code_sha256":"ed5c43f164ad0b54","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2cd00679918f825e","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a Graph Attention Network (GAT) layer that uses masked self-attentional layers to operate on graph-structured data, as proposed in the paper.","centrality":"contribution","entry":"GAT","entry_sha256":"0543c5506767fe53","n_bricks":1,"bricks":[{"entry":"GAT","code_sha256":"0543c5506767fe53","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2cf1576e12e6dc90","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"Implements a Graph Attention Layer as described in the GAT paper, using masked self-attentional layers to aggregate node features based on attention coefficients.","centrality":"contribution","entry":"GATLayer","entry_sha256":"50fe8f71c8211753","n_bricks":2,"bricks":[{"entry":"GATLayer","code_sha256":"50fe8f71c8211753","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"GATHead","code_sha256":"9b65469bbd07b3db","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"37b9aa138e348924","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs), which use masked self-attentional layers to operate on graph-structured data, stacking layers where nodes attend over their neighbors.","centrality":"contribution","entry":"GAT","entry_sha256":"ef36abf2c8ed6532","n_bricks":1,"bricks":[{"entry":"GAT","code_sha256":"ef36abf2c8ed6532","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"38ae770461a6599b","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a graph attention layer that uses masked self-attentional mechanisms to weigh node features in graph-structured data, as proposed in the Graph Attention Networks (GATs) paper.","centrality":"contribution","entry":"GATLayer","entry_sha256":"084e19b084167399","n_bricks":1,"bricks":[{"entry":"GATLayer","code_sha256":"084e19b084167399","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"46f561be134d600b","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"This class implements the Graph Attention Network layer that performs weighted aggregation on neighbor features using masked self-attentional mechanisms.","centrality":"component","entry":"AttentionAggregator","entry_sha256":"a17fe9c7a3d566f4","n_bricks":1,"bricks":[{"entry":"AttentionAggregator","code_sha256":"a17fe9c7a3d566f4","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4b31d0d3f3f64b41","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements graph attention layers that leverage masked self-attentional mechanisms to operate on graph-structured data, addressing limitations of prior graph convolution-based methods.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"ef1e2b2dc826e35c","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"ef1e2b2dc826e35c","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4fb9859d6935a9f7","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"Implements a graph attention layer that leverages masked self-attentional layers to operate on graph-structured data, as proposed in the Graph Attention Networks paper.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"2b9d25ebc1ad21fe","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"2b9d25ebc1ad21fe","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5ff3cf1c8202907a","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks (GATs), novel neural network architectures that use masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GAT","entry_sha256":"14b29bb3c2e77060","n_bricks":2,"bricks":[{"entry":"GAT","code_sha256":"14b29bb3c2e77060","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"GATConv","code_sha256":"600d032886c740f2","role":"model","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"629239bdf72434d4","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks (GATs), novel neural network architectures that use masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GATNode","entry_sha256":"3b5dfe5f6487483a","n_bricks":2,"bricks":[{"entry":"GATNode","code_sha256":"3b5dfe5f6487483a","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Residual","code_sha256":"1f6d95f2dbf139ad","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"71e0da22858fec3a","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks (GATs), a novel neural network architecture that uses masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GAT","entry_sha256":"ca3843aa2d3c4206","n_bricks":1,"bricks":[{"entry":"GAT","code_sha256":"ca3843aa2d3c4206","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"744503198745d3cc","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims that Graph Attention Networks (GATs) are novel neural network architectures operating on graph-structured data using masked self-attentional layers to improve upon graph convolution-based methods.","centrality":"contribution","entry":"CustomGATLayer","entry_sha256":"69bb60470be073ba","n_bricks":2,"bricks":[{"entry":"CustomGATLayer","code_sha256":"69bb60470be073ba","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"CustomGATHeadLayer","code_sha256":"550882cf5406f142","role":"model","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7615c10688a2c1f7","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs), a neural network architecture that uses masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GAT","entry_sha256":"1d632b6bedff39f7","n_bricks":2,"bricks":[{"entry":"GAT","code_sha256":"1d632b6bedff39f7","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"GraphAttentionLayer","code_sha256":"f133a4cc58a34a5b","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7cb27231a3b4b1a7","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a graph attention layer that uses masked self-attentional layers to weigh node neighbors dynamically, forming the core of the Graph Attention Network (GAT) method.","centrality":"contribution","entry":"GraphAttention","entry_sha256":"3bd3e21f7881b3ad","n_bricks":1,"bricks":[{"entry":"GraphAttention","code_sha256":"3bd3e21f7881b3ad","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"83a249c080779876","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements the graph attention layer that uses masked self-attention to operate on graph-structured data.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"4830f24ef485057f","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"4830f24ef485057f","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"98481af5e742f0f3","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements graph attention layers that use masked self-attention mechanisms to operate on graph-structured data.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"deefaca543b8cc51","n_bricks":3,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"deefaca543b8cc51","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"BaseGraphAttentionLayer","code_sha256":"3db162112d63db34","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"GraphConvolutionLayer","code_sha256":"1dbf66eba24dbc7e","role":"helper","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"98af3f0f75e1e1ef","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks (GATs), which use masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"SpMHGAT","entry_sha256":"b5b7966d6d562760","n_bricks":2,"bricks":[{"entry":"SpMHGAT","code_sha256":"b5b7966d6d562760","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseHGAttN","code_sha256":"b63d599a318b4057","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"UNCLEAR","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9df756d0a3aa5b02","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs), a novel neural network architecture that operates on graph-structured data using masked self-attentional layers to aggregate node features.","centrality":"contribution","entry":"GAT","entry_sha256":"628b8816e46fa27f","n_bricks":4,"bricks":[{"entry":"GAT","code_sha256":"628b8816e46fa27f","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"MultiHeadLayer","code_sha256":"5a977055a872edd8","role":"model","order":1,"level":1,"status":"ran_draft_wrong"},{"entry":"GraphAttentionLayer","code_sha256":"aaafc660d13f4e16","role":"model","order":2,"level":1,"status":"ran_draft_wrong"},{"entry":"Dropout","code_sha256":"5afc838eec40772e","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9ff236658b1cb2f1","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims to implement Graph Attention Networks (GATs), which use masked self-attentional layers to operate on graph-structured data, allowing nodes to attend over their neighborhoods' features.","centrality":"contribution","entry":"GATLayer","entry_sha256":"2e1cd02fdff09cfc","n_bricks":1,"bricks":[{"entry":"GATLayer","code_sha256":"2e1cd02fdff09cfc","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"a22832cf566c81a3","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims that Graph Attention Networks (GATs) leverage masked self-attentional layers to operate on graph-structured data, enabling nodes to attend over their neighborhoods' features.","centrality":"contribution","entry":"GATLayer","entry_sha256":"52e34cb027943420","n_bricks":4,"bricks":[{"entry":"GATLayer","code_sha256":"52e34cb027943420","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"NodeApplyModule","code_sha256":"debb79dfd7fbb165","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"gat_msg","code_sha256":"6083fea83bb7098c","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"},{"entry":"gat_reduce","code_sha256":"9dc615acb2d8de00","role":"helper","order":3,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"a57858ef3cdc8bda","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements a graph attention mechanism that leverages masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GAT","entry_sha256":"fb04b1d471c6acc1","n_bricks":1,"bricks":[{"entry":"GAT","code_sha256":"fb04b1d471c6acc1","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ac217b2dbeb06b1e","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a graph attention mechanism that uses masked self-attentional layers to operate on graph-structured data, as proposed in the Graph Attention Networks (GATs) paper.","centrality":"contribution","entry":"StructuralAttentionLayer","entry_sha256":"2e935d44457aab07","n_bricks":1,"bricks":[{"entry":"StructuralAttentionLayer","code_sha256":"2e935d44457aab07","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ad6d62a394f95785","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims that Graph Attention Networks (GATs) leverage masked self-attentional layers to operate on graph-structured data, addressing shortcomings of prior graph convolution methods.","centrality":"contribution","entry":"HyperGATConv","entry_sha256":"fc520c658083198c","n_bricks":1,"bricks":[{"entry":"HyperGATConv","code_sha256":"fc520c658083198c","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ad948e5630cf2918","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements graph attention layers that use masked self-attentional mechanisms to weigh node neighbors dynamically, forming the core of Graph Attention Networks (GATs).","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"2b7d556bf1ddeea2","n_bricks":2,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"2b7d556bf1ddeea2","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Attention","code_sha256":"ea7e984b0e2dc3d2","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"aeaecaa6e478a2d9","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a graph attention layer that computes attention coefficients for nodes in a graph and applies masked self-attentional layers to aggregate neighbor information.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"bfd816be65963aae","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"bfd816be65963aae","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b0ac5d5a91665a3e","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"Implements a graph attention layer that uses masked self-attentional mechanisms to weigh node features, as proposed in the Graph Attention Networks paper.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"7de5ed842bb1f8ae","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"7de5ed842bb1f8ae","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bc4ff4b04638c89a","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs), which use masked self-attentional layers to operate on graph-structured data, enabling nodes to attend over their neighborhoods.","centrality":"contribution","entry":"GAT","entry_sha256":"54ac990cf4b2df6b","n_bricks":2,"bricks":[{"entry":"GAT","code_sha256":"54ac990cf4b2df6b","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseGAttN","code_sha256":"ed5c43f164ad0b54","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bccceb390a0efc8a","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a single-head graph attention layer that computes attention coefficients between nodes in a graph and aggregates neighbor node features using these coefficients.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"c2cadcfe69abfe1c","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"c2cadcfe69abfe1c","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"be7f642f95506885","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs), a novel neural network architecture for graph-structured data using masked self-attentional layers.","centrality":"contribution","entry":"GATNet","entry_sha256":"ee89af6272fb3b86","n_bricks":1,"bricks":[{"entry":"GATNet","code_sha256":"ee89af6272fb3b86","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"c16a09447637da2b","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements graph attention layers that use masked self-attentional mechanisms to weigh node features in graph-structured data, as proposed by the paper.","centrality":"contribution","entry":"GraphAttention","entry_sha256":"89ba00d981eb9302","n_bricks":1,"bricks":[{"entry":"GraphAttention","code_sha256":"89ba00d981eb9302","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cce071df0b2280d3","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs), a neural network architecture that uses self-attentional layers to operate on graph-structured data, aggregating node features with learned attention weights.","centrality":"contribution","entry":"gat_model","entry_sha256":"710685ce65391a79","n_bricks":2,"bricks":[{"entry":"gat_model","code_sha256":"710685ce65391a79","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"attention_layer","code_sha256":"6ece140d37c4f3d6","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d034fa2a82a6c858","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks (GATs), a novel neural network architecture using masked self-attentional layers for graph-structured data.","centrality":"contribution","entry":"DAGAD_GAT","entry_sha256":"b44bbad1c454ebf4","n_bricks":1,"bricks":[{"entry":"DAGAD_GAT","code_sha256":"b44bbad1c454ebf4","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d5e8665cafaeb772","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks, a novel neural network architecture that operates on graph-structured data using masked self-attentional layers.","centrality":"contribution","entry":"GAT","entry_sha256":"605946bfc2bfb229","n_bricks":2,"bricks":[{"entry":"GAT","code_sha256":"605946bfc2bfb229","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"GraphAttentionLayer","code_sha256":"a1460d4df9be2ad5","role":"model","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d6786e913da8ece3","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs) for multiclass node classification using masked self-attentional layers on graph-structured data.","centrality":"contribution","entry":"GAT_HOMM_Network","entry_sha256":"2f96875be1432954","n_bricks":13,"bricks":[{"entry":"GAT_HOMM_Network","code_sha256":"2f96875be1432954","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"HoMLayer_gnn","code_sha256":"7d4a66310b01ccfe","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"HoMLayer","code_sha256":"7c99ecc825b89cb9","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"HoM","code_sha256":"c752223c4cff0254","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"hom","code_sha256":"87047d4b8762a1c3","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"high_order_aggregation_","code_sha256":"afe74d2db9b18ca4","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"high_order_selection_","code_sha256":"0a4305f7b4b34882","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"full_mask_mixer","code_sha256":"18df0c54b9715ca4","role":"helper","order":7,"level":1,"status":"ran_draft_wrong"},{"entry":"gelu","code_sha256":"5c5300f98cecf9cc","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"mask_mixer","code_sha256":"7c2fe0a109d8552e","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"po2","code_sha256":"9001a106b75860f4","role":"helper","order":10,"level":0,"status":"unverified"},{"entry":"po3","code_sha256":"0f67c084fcf7537d","role":"helper","order":11,"level":0,"status":"unverified"},{"entry":"po4","code_sha256":"71e010ae9e308364","role":"helper","order":12,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e228f4614f650890","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements Graph Attention Networks (GATs), which use masked self-attentional layers to operate on graph-structured data, allowing nodes to attend over their neighborhoods.","centrality":"contribution","entry":"GATLayer","entry_sha256":"bd896967c973d652","n_bricks":1,"bricks":[{"entry":"GATLayer","code_sha256":"bd896967c973d652","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e752b781688db95f","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements Graph Attention Networks (GATs), a novel neural network architecture that uses masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GAT","entry_sha256":"be71c975b356bf8f","n_bricks":2,"bricks":[{"entry":"GAT","code_sha256":"be71c975b356bf8f","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseGAttN","code_sha256":"33f413c8515b4a54","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ef10896ed0f3e9fb","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements graph attention networks (GATs), which are neural network architectures that operate on graph-structured data using masked self-attentional layers to compute node representations.","centrality":"contribution","entry":"GraphAttentionNetwork","entry_sha256":"0426746ace37676b","n_bricks":3,"bricks":[{"entry":"GraphAttentionNetwork","code_sha256":"0426746ace37676b","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"GraphAttentionLayer","code_sha256":"5ae6f08a8fb439cf","role":"model","order":1,"level":1,"status":"ran"},{"entry":"GraphAttentionHead","code_sha256":"01569d1c8b54aedd","role":"model","order":2,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f2cdcb21a85752a1","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a graph attention layer that computes attention coefficients for nodes in a graph and applies these coefficients to aggregate neighbor node features, realizing the Graph Attention Network (GAT) mechanism described in the paper.","centrality":"contribution","entry":"GraphAttention","entry_sha256":"5e93c4b4d21d5d71","n_bricks":1,"bricks":[{"entry":"GraphAttention","code_sha256":"5e93c4b4d21d5d71","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f575b1d52c8773af","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The code implements a graph attention layer that uses masked self-attentional mechanisms to weigh node features in graph-structured data, as proposed in the Graph Attention Networks (GATs) paper.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"81f6c5575edeb0bf","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"81f6c5575edeb0bf","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f9a4d9d482a8dd2e","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims to implement Graph Attention Networks (GATs), which use masked self-attentional layers to operate on graph-structured data.","centrality":"contribution","entry":"GraphConvolution_G","entry_sha256":"5f34746d6309d7fe","n_bricks":1,"bricks":[{"entry":"GraphConvolution_G","code_sha256":"5f34746d6309d7fe","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"fb169a647a0004a0","source_kind":"harvested","method_name":"Graph Attention Networks (GATs)","realizes_method":"Graph Attention Networks (GATs)","graph_method":"Graph Attention Networks (GATs)","realizes_severed":false,"claim":"The paper claims this code implements graph attention layers that use masked self-attentional mechanisms to operate on graph-structured data, addressing limitations of prior graph convolution methods.","centrality":"contribution","entry":"GraphAttentionLayer","entry_sha256":"d1505ed1f609826b","n_bricks":1,"bricks":[{"entry":"GraphAttentionLayer","code_sha256":"d1505ed1f609826b","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b0d2b28ab26","n_siblings":43,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"4b0d2b28ab26","realizes_method":"Graph Attention Networks (GATs)","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["04c39c60787f7b72","0dce3d1c873ac859","2347fc8cf4df093b","299da02c12f88aba","2cd00679918f825e","2cf1576e12e6dc90","37b9aa138e348924","38ae770461a6599b","46f561be134d600b","4b31d0d3f3f64b41","4fb9859d6935a9f7","5ff3cf1c8202907a","629239bdf72434d4","71e0da22858fec3a","744503198745d3cc","7615c10688a2c1f7","7cb27231a3b4b1a7","83a249c080779876","98481af5e742f0f3","98af3f0f75e1e1ef","9df756d0a3aa5b02","9ff236658b1cb2f1","a22832cf566c81a3","a57858ef3cdc8bda","ac217b2dbeb06b1e","ad6d62a394f95785","ad948e5630cf2918","aeaecaa6e478a2d9","b0ac5d5a91665a3e","bc4ff4b04638c89a","bccceb390a0efc8a","be7f642f95506885","c16a09447637da2b","cce071df0b2280d3","d034fa2a82a6c858","d5e8665cafaeb772","d6786e913da8ece3","e228f4614f650890","e752b781688db95f","ef10896ed0f3e9fb","f2cdcb21a85752a1","f575b1d52c8773af","f9a4d9d482a8dd2e","fb169a647a0004a0"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"1710.10903"},"call":"assembly(arxiv_id=\"1710.10903\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1710.10903.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1710.10903.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PetarV-/GAT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Diego999/pyGAT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/taishan1994/pytorch_gat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gayanku/FDGATII","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vailatuts/SSFG-regularization","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ds4dm/sGat","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joaopedromattos/gnee","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tatp22/pytorch-fast-GAT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexOarga/haiku-geometric","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fanzhenliu/dagad","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ColdenChan/GAT_D","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/calciver/Graph-Attention-Networks","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marble0117/GNN_models_pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhangbo2008/GAT_network","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-4/tree/main/gat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shi27feng/transformers.satisfy","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/basiralab/Reproducible-Generative-Learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gmum/umwpl2021","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shenweichen/GraphNeuralNetwork","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/handasontam/GAT-with-edgewise-attention","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mitya8128/experiments_notes","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wan2000/mc-mot","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/gat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WantingZhao/my_GAT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":49,"ran_draft_wrong":8,"ran_violates":2,"ran_fixture":1,"ran_honours":1,"unverified":45},"n_samples":106,"n_ran":61,"n_constructed":28,"n_ran_checked":52,"n_instrument":9,"n_unverified":45,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":106,"ran":61,"n_ran_checked":52,"n_instrument":9,"repositories":52}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"official_not_harvested":{"repositories":["PetarV-/GAT"],"harvested_for_other_papers":[1],"samples_from_other_repositories":106,"other_repositories":52,"samples_unlocated":0},"n_pointer_only_for_licence":46,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":3,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing","signature_not_shown":"the graph records a signature for this sample and it is not shown; signature_not_shown_because names why, as the export's field-exclusion reason","signature_not_shown_because":{"signature_is_harness_probe_not_fixture_args":"for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments"}},"n_ran_with_level_date":59,"n_ran_without_level_date":2,"n_ran_signature_not_shown":4,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"ea7e984b0e2dc3d2","code_sha256_prefix":"ea7e984b0e2dc3d2","entry":"Attention","repo":"Aveek-Saha/Graph-Attention-Net","repo_kind":"listed","path":"gat.py","file_url":"https://github.com/Aveek-Saha/Graph-Attention-Net/blob/HEAD/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Attention","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/attention","census":{"url":"/census/attention","implementations":13,"papers":12,"distinct_outputs":10,"n_buckets":4,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ea7e984b0e2dc3d2"}},{"code_sha256":"a17fe9c7a3d566f4","code_sha256_prefix":"a17fe9c7a3d566f4","entry":"AttentionAggregator","repo":"GraphSAINT/GraphSAINT","repo_kind":"listed","path":"graphsaint/pytorch_version/layers.py","file_url":"https://github.com/GraphSAINT/GraphSAINT/blob/HEAD/graphsaint/pytorch_version/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"AttentionAggregator","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a17fe9c7a3d566f4"}},{"code_sha256":"3db162112d63db34","code_sha256_prefix":"3db162112d63db34","entry":"BaseGraphAttentionLayer","repo":"Yindong-Zhang/myGAT","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/Yindong-Zhang/myGAT/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"BaseGraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3db162112d63db34"}},{"code_sha256":"5afc838eec40772e","code_sha256_prefix":"5afc838eec40772e","entry":"Dropout","repo":"gcucurull/jax-gat","repo_kind":"listed","path":"models.py","file_url":"https://github.com/gcucurull/jax-gat/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"rate:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5afc838eec40772e"},"code_page":"/code/dropout-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, gcucurull/jax-gat when it was checked","mcp_get_code":{"code_sha256":"5afc838eec40772e"}},{"code_sha256":"0543c5506767fe53","code_sha256_prefix":"0543c5506767fe53","entry":"GAT","repo":"isotlaboratory/ml4vrp","repo_kind":"listed","path":"modules/layers.py","file_url":"https://github.com/isotlaboratory/ml4vrp/blob/HEAD/modules/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"GAT","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gat","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, isotlaboratory/ml4vrp when it was checked","mcp_get_code":{"code_sha256":"0543c5506767fe53"}},{"code_sha256":"ef36abf2c8ed6532","code_sha256_prefix":"ef36abf2c8ed6532","entry":"GAT","repo":"marblet/GNN_models_pytorch_geometric","repo_kind":"listed","path":"models/gat.py","file_url":"https://github.com/marblet/GNN_models_pytorch_geometric/blob/HEAD/models/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"GAT","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gat","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ef36abf2c8ed6532"}},{"code_sha256":"14b29bb3c2e77060","code_sha256_prefix":"14b29bb3c2e77060","entry":"GAT","repo":"marblet/gat-pytorch","repo_kind":"listed","path":"gat.py","file_url":"https://github.com/marblet/gat-pytorch/blob/HEAD/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GAT","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gat","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"14b29bb3c2e77060"}},{"code_sha256":"1d632b6bedff39f7","code_sha256_prefix":"1d632b6bedff39f7","entry":"GAT","repo":"labmlai/annotated_deep_learning_paper_implementations","repo_kind":"listed","path":"labml_nn/graphs/gat/experiment.py","file_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/HEAD/labml_nn/graphs/gat/experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GAT","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gat","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1d632b6bedff39f7"}},{"code_sha256":"605946bfc2bfb229","code_sha256_prefix":"605946bfc2bfb229","entry":"GAT","repo":"weiyangfb/PyTorchSparseGAT","repo_kind":"listed","path":"models.py","file_url":"https://github.com/weiyangfb/PyTorchSparseGAT/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float, adj:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gat","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"605946bfc2bfb229"}},{"code_sha256":"600d032886c740f2","code_sha256_prefix":"600d032886c740f2","entry":"GATConv","repo":"marblet/gat-pytorch","repo_kind":"listed","path":"gat.py","file_url":"https://github.com/marblet/gat-pytorch/blob/HEAD/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GATConv","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"600d032886c740f2"}},{"code_sha256":"9b65469bbd07b3db","code_sha256_prefix":"9b65469bbd07b3db","entry":"GATHead","repo":"lukecavabarrett/pna","repo_kind":"listed","path":"models/pytorch/gat/layer.py","file_url":"https://github.com/lukecavabarrett/pna/blob/HEAD/models/pytorch/gat/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"GATHead","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9b65469bbd07b3db"}},{"code_sha256":"5d5e29ef042a08a8","code_sha256_prefix":"5d5e29ef042a08a8","entry":"GATLayer","repo":"gordicaleksa/pytorch-GAT","repo_kind":"listed","path":"models/definitions/GAT.py","file_url":"https://github.com/gordicaleksa/pytorch-GAT/blob/HEAD/models/definitions/GAT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"GATLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gatlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5d5e29ef042a08a8"}},{"code_sha256":"50fe8f71c8211753","code_sha256_prefix":"50fe8f71c8211753","entry":"GATLayer","repo":"lukecavabarrett/pna","repo_kind":"listed","path":"models/pytorch/gat/layer.py","file_url":"https://github.com/lukecavabarrett/pna/blob/HEAD/models/pytorch/gat/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"GATLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gatlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"50fe8f71c8211753"}},{"code_sha256":"084e19b084167399","code_sha256_prefix":"084e19b084167399","entry":"GATLayer","repo":"snowkylin/gnn","repo_kind":"listed","path":"gnn.py","file_url":"https://github.com/snowkylin/gnn/blob/HEAD/gnn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GATLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gatlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, snowkylin/gnn when it was checked","mcp_get_code":{"code_sha256":"084e19b084167399"}},{"code_sha256":"2e1cd02fdff09cfc","code_sha256_prefix":"2e1cd02fdff09cfc","entry":"GATLayer","repo":"zhao-tong/GNNs-easy-to-use","repo_kind":"listed","path":"GNNs.py","file_url":"https://github.com/zhao-tong/GNNs-easy-to-use/blob/HEAD/GNNs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GATLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gatlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhao-tong/GNNs-easy-to-use when it was checked","mcp_get_code":{"code_sha256":"2e1cd02fdff09cfc"}},{"code_sha256":"52e34cb027943420","code_sha256_prefix":"52e34cb027943420","entry":"GATLayer","repo":"giuseppefutia/link-prediction-code","repo_kind":"listed","path":"net.py","file_url":"https://github.com/giuseppefutia/link-prediction-code/blob/HEAD/net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GATLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/gatlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, giuseppefutia/link-prediction-code when it was checked","mcp_get_code":{"code_sha256":"52e34cb027943420"}},{"code_sha256":"21ba3ceb8353096e","code_sha256_prefix":"21ba3ceb8353096e","entry":"GATLayerImp3","repo":"gordicaleksa/pytorch-GAT","repo_kind":"listed","path":"models/definitions/GAT.py","file_url":"https://github.com/gordicaleksa/pytorch-GAT/blob/HEAD/models/definitions/GAT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"GATLayerImp3","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"21ba3ceb8353096e"}},{"code_sha256":"ee89af6272fb3b86","code_sha256_prefix":"ee89af6272fb3b86","entry":"GATNet","repo":"yururyuru00/GAT_pyG","repo_kind":"listed","path":"models.py","file_url":"https://github.com/yururyuru00/GAT_pyG/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float, edge_index:Tensor/2/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yururyuru00/GAT_pyG when it was checked","mcp_get_code":{"code_sha256":"ee89af6272fb3b86"}},{"code_sha256":"3b5dfe5f6487483a","code_sha256_prefix":"3b5dfe5f6487483a","entry":"GATNode","repo":"nnaakkaaii/g2-MLP","repo_kind":"listed","path":"gnn/src/models/networks/gat_node.py","file_url":"https://github.com/nnaakkaaii/g2-MLP/blob/HEAD/gnn/src/models/networks/gat_node.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GATNode","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3b5dfe5f6487483a"}},{"code_sha256":"c5acf386fe00c470","code_sha256_prefix":"c5acf386fe00c470","entry":"GET_BLOCKS","repo":"whut2962575697/gat_sementic_segmentation","repo_kind":"listed","path":"roi_pooling/functions/roi_pooling.py","file_url":"https://github.com/whut2962575697/gat_sementic_segmentation/blob/HEAD/roi_pooling/functions/roi_pooling.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"N:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"c5acf386fe00c470"},"code_page":"/code/get-blocks-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c5acf386fe00c470"}},{"code_sha256":"3bd3e21f7881b3ad","code_sha256_prefix":"3bd3e21f7881b3ad","entry":"GraphAttention","repo":"noahtren/Graph-Attention-Networks-TensorFlow-2","repo_kind":"listed","path":"gat.py","file_url":"https://github.com/noahtren/Graph-Attention-Networks-TensorFlow-2/blob/HEAD/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GraphAttention","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattention","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3bd3e21f7881b3ad"}},{"code_sha256":"ef1e2b2dc826e35c","code_sha256_prefix":"ef1e2b2dc826e35c","entry":"GraphAttentionLayer","repo":"pengsl-lab/mssl","repo_kind":"listed","path":"MSSL/models/layers.py","file_url":"https://github.com/pengsl-lab/mssl/blob/HEAD/MSSL/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, pengsl-lab/mssl when it was checked","mcp_get_code":{"code_sha256":"ef1e2b2dc826e35c"}},{"code_sha256":"2b9d25ebc1ad21fe","code_sha256_prefix":"2b9d25ebc1ad21fe","entry":"GraphAttentionLayer","repo":"subercui/pyGConvAT","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/subercui/pyGConvAT/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2b9d25ebc1ad21fe"}},{"code_sha256":"f133a4cc58a34a5b","code_sha256_prefix":"f133a4cc58a34a5b","entry":"GraphAttentionLayer","repo":"labmlai/annotated_deep_learning_paper_implementations","repo_kind":"listed","path":"labml_nn/graphs/gat/experiment.py","file_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/HEAD/labml_nn/graphs/gat/experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f133a4cc58a34a5b"}},{"code_sha256":"4830f24ef485057f","code_sha256_prefix":"4830f24ef485057f","entry":"GraphAttentionLayer","repo":"Messham87/COVID_GAT","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/Messham87/COVID_GAT/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4830f24ef485057f"}},{"code_sha256":"deefaca543b8cc51","code_sha256_prefix":"deefaca543b8cc51","entry":"GraphAttentionLayer","repo":"Yindong-Zhang/myGAT","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/Yindong-Zhang/myGAT/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"deefaca543b8cc51"}},{"code_sha256":"aaafc660d13f4e16","code_sha256_prefix":"aaafc660d13f4e16","entry":"GraphAttentionLayer","repo":"gcucurull/jax-gat","repo_kind":"listed","path":"models.py","file_url":"https://github.com/gcucurull/jax-gat/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"out_dim:int/0/int, dropout:float/0/float, residual:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"aaafc660d13f4e16"},"code_page":"/code/graphattentionlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, gcucurull/jax-gat when it was checked","mcp_get_code":{"code_sha256":"aaafc660d13f4e16"}},{"code_sha256":"2b7d556bf1ddeea2","code_sha256_prefix":"2b7d556bf1ddeea2","entry":"GraphAttentionLayer","repo":"Aveek-Saha/Graph-Attention-Net","repo_kind":"listed","path":"gat.py","file_url":"https://github.com/Aveek-Saha/Graph-Attention-Net/blob/HEAD/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2b7d556bf1ddeea2"}},{"code_sha256":"bfd816be65963aae","code_sha256_prefix":"bfd816be65963aae","entry":"GraphAttentionLayer","repo":"AngusMonroe/GAT-pytorch","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/AngusMonroe/GAT-pytorch/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bfd816be65963aae"}},{"code_sha256":"7de5ed842bb1f8ae","code_sha256_prefix":"7de5ed842bb1f8ae","entry":"GraphAttentionLayer","repo":"basiralab/RG-Select","repo_kind":"listed","path":"models_gat.py","file_url":"https://github.com/basiralab/RG-Select/blob/HEAD/models_gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"GraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, basiralab/RG-Select when it was checked","mcp_get_code":{"code_sha256":"7de5ed842bb1f8ae"}},{"code_sha256":"a1460d4df9be2ad5","code_sha256_prefix":"a1460d4df9be2ad5","entry":"GraphAttentionLayer","repo":"weiyangfb/PyTorchSparseGAT","repo_kind":"listed","path":"models.py","file_url":"https://github.com/weiyangfb/PyTorchSparseGAT/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"input:Tensor/2/float, adj:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a1460d4df9be2ad5"}},{"code_sha256":"5ae6f08a8fb439cf","code_sha256_prefix":"5ae6f08a8fb439cf","entry":"GraphAttentionLayer","repo":"tatp22/pytorch-fast-GAT","repo_kind":"listed","path":"fast_gat/GAT.py","file_url":"https://github.com/tatp22/pytorch-fast-GAT/blob/HEAD/fast_gat/GAT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"nodes:Tensor/2/float, edges:dict/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5ae6f08a8fb439cf"}},{"code_sha256":"81f6c5575edeb0bf","code_sha256_prefix":"81f6c5575edeb0bf","entry":"GraphAttentionLayer","repo":"dzb1998/pyGAT","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/dzb1998/pyGAT/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"input:Tensor/2/float, adj:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"81f6c5575edeb0bf"}},{"code_sha256":"d1505ed1f609826b","code_sha256_prefix":"d1505ed1f609826b","entry":"GraphAttentionLayer","repo":"fongyk/graph-attention","repo_kind":"listed","path":"layer.py","file_url":"https://github.com/fongyk/graph-attention/blob/HEAD/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"global_feature:Tensor/2/float, nodes:list/1/int, neighbors_list:list/1/set","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/graphattentionlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fongyk/graph-attention when it was checked","mcp_get_code":{"code_sha256":"d1505ed1f609826b"}},{"code_sha256":"0426746ace37676b","code_sha256_prefix":"0426746ace37676b","entry":"GraphAttentionNetwork","repo":"tatp22/pytorch-fast-GAT","repo_kind":"listed","path":"fast_gat/GAT.py","file_url":"https://github.com/tatp22/pytorch-fast-GAT/blob/HEAD/fast_gat/GAT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"nodes:Tensor/2/float, edges:dict/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0426746ace37676b"}},{"code_sha256":"1dbf66eba24dbc7e","code_sha256_prefix":"1dbf66eba24dbc7e","entry":"GraphConvolutionLayer","repo":"Yindong-Zhang/myGAT","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/Yindong-Zhang/myGAT/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"feat:Tensor/2/float, adj:Tensor/2/float","fixture_out_type":"NoneType","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1dbf66eba24dbc7e"},"code_page":"/code/graphconvolutionlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1dbf66eba24dbc7e"}},{"code_sha256":"5a977055a872edd8","code_sha256_prefix":"5a977055a872edd8","entry":"MultiHeadLayer","repo":"gcucurull/jax-gat","repo_kind":"listed","path":"models.py","file_url":"https://github.com/gcucurull/jax-gat/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"nheads:int/0/int, nhid:int/0/int, dropout:float/0/float, residual:bool/0/bool, last_layer:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5a977055a872edd8"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, gcucurull/jax-gat when it was checked","mcp_get_code":{"code_sha256":"5a977055a872edd8"}},{"code_sha256":"debb79dfd7fbb165","code_sha256_prefix":"debb79dfd7fbb165","entry":"NodeApplyModule","repo":"giuseppefutia/link-prediction-code","repo_kind":"listed","path":"net.py","file_url":"https://github.com/giuseppefutia/link-prediction-code/blob/HEAD/net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"NodeApplyModule","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, giuseppefutia/link-prediction-code when it was checked","mcp_get_code":{"code_sha256":"debb79dfd7fbb165"}},{"code_sha256":"f2e88290d89e5830","code_sha256_prefix":"f2e88290d89e5830","entry":"SpGraphAttentionLayer","repo":"HazyResearch/hgcn","repo_kind":"listed","path":"layers/att_layers.py","file_url":"https://github.com/HazyResearch/hgcn/blob/HEAD/layers/att_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"SpGraphAttentionLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HazyResearch/hgcn when it was checked","mcp_get_code":{"code_sha256":"f2e88290d89e5830"}},{"code_sha256":"3e9e9056af401802","code_sha256_prefix":"3e9e9056af401802","entry":"SpecialSpmmFunction","repo":"HazyResearch/hgcn","repo_kind":"listed","path":"layers/att_layers.py","file_url":"https://github.com/HazyResearch/hgcn/blob/HEAD/layers/att_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SpecialSpmmFunction","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HazyResearch/hgcn when it was checked","mcp_get_code":{"code_sha256":"3e9e9056af401802"}},{"code_sha256":"5a0b371866f14f67","code_sha256_prefix":"5a0b371866f14f67","entry":"adj_to_bias","repo":"404nofound/gat","repo_kind":"listed","path":"utils/process.py","file_url":"https://github.com/404nofound/gat/blob/HEAD/utils/process.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"adj:ndarray/3/float, sizes:ndarray/1/int, nhood:int/0/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5a0b371866f14f67"}},{"code_sha256":"6ece140d37c4f3d6","code_sha256_prefix":"6ece140d37c4f3d6","entry":"attention_layer","repo":"liu6zijian/simplified-gcn-model","repo_kind":"listed","path":"gat.py","file_url":"https://github.com/liu6zijian/simplified-gcn-model/blob/HEAD/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:Tensor/2/float, adj:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/attention-layer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, liu6zijian/simplified-gcn-model when it was checked","mcp_get_code":{"code_sha256":"6ece140d37c4f3d6"}},{"code_sha256":"fa7f6abbe630e912","code_sha256_prefix":"fa7f6abbe630e912","entry":"dfs_split","repo":"404nofound/gat","repo_kind":"listed","path":"utils/process_ppi.py","file_url":"https://github.com/404nofound/gat/blob/HEAD/utils/process_ppi.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"adj:csr_matrix/2/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fa7f6abbe630e912"}},{"code_sha256":"3ab88254add4c192","code_sha256_prefix":"3ab88254add4c192","entry":"encode_onehot","repo":"Anak2016/GAT","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Anak2016/GAT/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"labels:ndarray/1/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"3ab88254add4c192"},"code_page":"/code/encode-onehot","census":{"url":"/census/encode-onehot","implementations":3,"papers":5,"distinct_outputs":2,"n_buckets":2,"bucket_key":[[1,"int","int64"]],"bucket_index":1,"bucket_label":"arg 1: rank 1, kind int, dtype int64"},"census_bucket_fragment":"bucket-1","licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3ab88254add4c192"}},{"code_sha256":"1562c6eb2b599cd7","code_sha256_prefix":"1562c6eb2b599cd7","entry":"encode_onehot_dict","repo":"joaopedromattos/gnee","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/joaopedromattos/gnee/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"labels:list/1/str","fixture_out_type":"dict","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1562c6eb2b599cd7"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1562c6eb2b599cd7"}},{"code_sha256":"18df0c54b9715ca4","code_sha256_prefix":"18df0c54b9715ca4","entry":"full_mask_mixer","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"h:Tensor/3/float, mask:Tensor/3/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"18df0c54b9715ca4"}},{"code_sha256":"710685ce65391a79","code_sha256_prefix":"710685ce65391a79","entry":"gat_model","repo":"liu6zijian/simplified-gcn-model","repo_kind":"listed","path":"gat.py","file_url":"https://github.com/liu6zijian/simplified-gcn-model/blob/HEAD/gat.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:Tensor/3/float, adj:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, liu6zijian/simplified-gcn-model when it was checked","mcp_get_code":{"code_sha256":"710685ce65391a79"}},{"code_sha256":"6083fea83bb7098c","code_sha256_prefix":"6083fea83bb7098c","entry":"gat_msg","repo":"giuseppefutia/link-prediction-code","repo_kind":"listed","path":"net.py","file_url":"https://github.com/giuseppefutia/link-prediction-code/blob/HEAD/net.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"edge:MockEdgeData/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, giuseppefutia/link-prediction-code when it was checked","mcp_get_code":{"code_sha256":"6083fea83bb7098c"}},{"code_sha256":"6e566909474e4531","code_sha256_prefix":"6e566909474e4531","entry":"getpid","repo":"zxhhh97/ABot","repo_kind":"listed","path":"scorelist.py","file_url":"https://github.com/zxhhh97/ABot/blob/HEAD/scorelist.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"_:NoneType/0/?","fixture_out_type":"int","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6e566909474e4531"}},{"code_sha256":"df538da77a5d06bd","code_sha256_prefix":"df538da77a5d06bd","entry":"group_norm","repo":"whut2962575697/gat_sementic_segmentation","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/whut2962575697/gat_sementic_segmentation/blob/HEAD/layers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"input:Tensor/4/float, group:int/0/int, running_mean:Tensor/1/float, running_var:Tensor/1/float, weight:Tensor/1/float, bias:Tensor/1/float, use_input_stats:bool/0/bool, momentum:float/0/float, eps:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"df538da77a5d06bd"},"code_page":"/code/group-norm","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from astuary/flow, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"df538da77a5d06bd"}},{"code_sha256":"bca7f86b2fb5bf67","code_sha256_prefix":"bca7f86b2fb5bf67","entry":"make_dot","repo":"Anak2016/GAT","repo_kind":"listed","path":"visualize_graph.py","file_url":"https://github.com/Anak2016/GAT/blob/HEAD/visualize_graph.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"var:Tensor/0/float, params:dict/0/?","fixture_out_type":"Digraph","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/make-dot","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bca7f86b2fb5bf67"}},{"code_sha256":"7c2fe0a109d8552e","code_sha256_prefix":"7c2fe0a109d8552e","entry":"mask_mixer","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"h:Tensor/3/float, mask:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7c2fe0a109d8552e"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"7c2fe0a109d8552e"}},{"code_sha256":"cb6188faef06c446","code_sha256_prefix":"cb6188faef06c446","entry":"matmul","repo":"ds4dm/sGat","repo_kind":"listed","path":"sgcn/masked/functions.py","file_url":"https://github.com/ds4dm/sGat/blob/HEAD/sgcn/masked/functions.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"indices:Tensor/2/int, values:Tensor/1/float, size:Size/1/int, B:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":"/code/matmul","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cb6188faef06c446"}},{"code_sha256":"8d9b7d17ab1ab2c1","code_sha256_prefix":"8d9b7d17ab1ab2c1","entry":"matmulmasked","repo":"ds4dm/sGat","repo_kind":"listed","path":"sgcn/masked/functions.py","file_url":"https://github.com/ds4dm/sGat/blob/HEAD/sgcn/masked/functions.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"A:Tensor/2/float, B:Tensor/2/float, indices:tuple/1/Tensor","fixture_out_type":"Tensor","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8d9b7d17ab1ab2c1"}},{"code_sha256":"d45f434d25f2e870","code_sha256_prefix":"d45f434d25f2e870","entry":"normalize_adj","repo":"Anak2016/GAT","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Anak2016/GAT/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"mx:csr_matrix/2/float","fixture_out_type":"csc_matrix","code_page":"/code/normalize-adj","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from triplej0079/DeepIM, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"d45f434d25f2e870"}},{"code_sha256":"c1d6392f89c5e495","code_sha256_prefix":"c1d6392f89c5e495","entry":"parse_index_file","repo":"404nofound/gat","repo_kind":"listed","path":"utils/process.py","file_url":"https://github.com/404nofound/gat/blob/HEAD/utils/process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"filename:str/0/str","fixture_out_type":"list","code_page":"/code/parse-index-file","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from DSL-Lab/Specformer, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"c1d6392f89c5e495"}},{"code_sha256":"588bba8cc8a33264","code_sha256_prefix":"588bba8cc8a33264","entry":"process_event_dataset_from_networkx","repo":"joaopedromattos/gnee","repo_kind":"listed","path":"event_graph_utils.py","file_url":"https://github.com/joaopedromattos/gnee/blob/HEAD/event_graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"G:Graph/0/?, features_attr:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"588bba8cc8a33264"}},{"code_sha256":"1e557c37f1d14adf","code_sha256_prefix":"1e557c37f1d14adf","entry":"roi_pooling_2d_pytorch","repo":"whut2962575697/gat_sementic_segmentation","repo_kind":"listed","path":"roi_pooling/functions/roi_pooling.py","file_url":"https://github.com/whut2962575697/gat_sementic_segmentation/blob/HEAD/roi_pooling/functions/roi_pooling.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input:Tensor/4/float, rois:Tensor/2/float, output_size:tuple/1/int, spatial_scale:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1e557c37f1d14adf"}},{"code_sha256":"b32fd748b4bbe3bf","code_sha256_prefix":"b32fd748b4bbe3bf","entry":"sample_mask","repo":"404nofound/gat","repo_kind":"listed","path":"utils/process.py","file_url":"https://github.com/404nofound/gat/blob/HEAD/utils/process.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"idx:int/0/int, l:int/0/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b32fd748b4bbe3bf"},"code_page":"/code/sample-mask","census":{"url":"/census/sample-mask","implementations":4,"papers":5,"distinct_outputs":4,"n_buckets":1,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b32fd748b4bbe3bf"}},{"code_sha256":"d465a0df5a49343f","code_sha256_prefix":"d465a0df5a49343f","entry":"setup_logger","repo":"whut2962575697/gat_sementic_segmentation","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/whut2962575697/gat_sementic_segmentation/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"name:str/0/str, save_dir:str/0/str, distributed_rank:int/0/int, train:bool/0/bool","fixture_out_type":"Logger","level_recorded_at":"2026-09-26T05:00:14.332320+00:00","code_page":"/code/setup-logger","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d465a0df5a49343f"}},{"code_sha256":"cbd09a8688d1836a","code_sha256_prefix":"cbd09a8688d1836a","entry":"test","repo":"404nofound/gat","repo_kind":"listed","path":"utils/process_ppi.py","file_url":"https://github.com/404nofound/gat/blob/HEAD/utils/process_ppi.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"adj:csr_matrix/2/int, mapping:list/1/int","fixture_out_type":"bool","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":"/code/test","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cbd09a8688d1836a"}},{"code_sha256":"ed5c43f164ad0b54","code_sha256_prefix":"ed5c43f164ad0b54","entry":"BaseGAttN","repo":"ColdenChan/GAT_D","repo_kind":"listed","path":"models/gat.py","file_url":"https://github.com/ColdenChan/GAT_D/blob/HEAD/models/gat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ed5c43f164ad0b54"}},{"code_sha256":"33f413c8515b4a54","code_sha256_prefix":"33f413c8515b4a54","entry":"BaseGAttN","repo":"handasontam/GAT-with-edgewise-attention","repo_kind":"listed","path":"models/gat.py","file_url":"https://github.com/handasontam/GAT-with-edgewise-attention/blob/HEAD/models/gat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"33f413c8515b4a54"}},{"code_sha256":"b63d599a318b4057","code_sha256_prefix":"b63d599a318b4057","entry":"BaseHGAttN","repo":"ydzhang-stormstout/HAT","repo_kind":"listed","path":"models/sp_prod_mhat.py","file_url":"https://github.com/ydzhang-stormstout/HAT/blob/HEAD/models/sp_prod_mhat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ydzhang-stormstout/HAT when it was checked","mcp_get_code":{"code_sha256":"b63d599a318b4057"}},{"code_sha256":"550882cf5406f142","code_sha256_prefix":"550882cf5406f142","entry":"CustomGATHeadLayer","repo":"vailatuts/SSFG-regularization","repo_kind":"listed","path":"layers/gat_layer.py","file_url":"https://github.com/vailatuts/SSFG-regularization/blob/HEAD/layers/gat_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, vailatuts/SSFG-regularization (NOASSERTION)","mcp_get_code":{"code_sha256":"550882cf5406f142"}},{"code_sha256":"69bb60470be073ba","code_sha256_prefix":"69bb60470be073ba","entry":"CustomGATLayer","repo":"vailatuts/SSFG-regularization","repo_kind":"listed","path":"layers/gat_layer.py","file_url":"https://github.com/vailatuts/SSFG-regularization/blob/HEAD/layers/gat_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, vailatuts/SSFG-regularization (NOASSERTION)","mcp_get_code":{"code_sha256":"69bb60470be073ba"}},{"code_sha256":"b44bbad1c454ebf4","code_sha256_prefix":"b44bbad1c454ebf4","entry":"DAGAD_GAT","repo":"fanzhenliu/dagad","repo_kind":"listed","path":"DAGAD.py","file_url":"https://github.com/fanzhenliu/dagad/blob/HEAD/DAGAD.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b44bbad1c454ebf4"}},{"code_sha256":"a71b339ad4cd268f","code_sha256_prefix":"a71b339ad4cd268f","entry":"Dtype","repo":"whut2962575697/gat_sementic_segmentation","repo_kind":"listed","path":"roi_pooling/utils.py","file_url":"https://github.com/whut2962575697/gat_sementic_segmentation/blob/HEAD/roi_pooling/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/dtype","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a71b339ad4cd268f"}},{"code_sha256":"8e9b126f3a88cbdd","code_sha256_prefix":"8e9b126f3a88cbdd","entry":"GAT","repo":"ColdenChan/GAT_D","repo_kind":"listed","path":"models/gat.py","file_url":"https://github.com/ColdenChan/GAT_D/blob/HEAD/models/gat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/gat","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8e9b126f3a88cbdd"}},{"code_sha256":"ca3843aa2d3c4206","code_sha256_prefix":"ca3843aa2d3c4206","entry":"GAT","repo":"taishan1994/pytorch_gat","repo_kind":"listed","path":"model.py","file_url":"https://github.com/taishan1994/pytorch_gat/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/gat","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, taishan1994/pytorch_gat when it was checked","mcp_get_code":{"code_sha256":"ca3843aa2d3c4206"}},{"code_sha256":"628b8816e46fa27f","code_sha256_prefix":"628b8816e46fa27f","entry":"GAT","repo":"gcucurull/jax-gat","repo_kind":"listed","path":"models.py","file_url":"https://github.com/gcucurull/jax-gat/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/gat","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, gcucurull/jax-gat when it was checked","mcp_get_code":{"code_sha256":"628b8816e46fa27f"}},{"code_sha256":"fb04b1d471c6acc1","code_sha256_prefix":"fb04b1d471c6acc1","entry":"GAT","repo":"Kaimaoge/IGNNK","repo_kind":"listed","path":"basic_structure.py","file_url":"https://github.com/Kaimaoge/IGNNK/blob/HEAD/basic_structure.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/gat","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Kaimaoge/IGNNK when it was checked","mcp_get_code":{"code_sha256":"fb04b1d471c6acc1"}},{"code_sha256":"be71c975b356bf8f","code_sha256_prefix":"be71c975b356bf8f","entry":"GAT","repo":"handasontam/GAT-with-edgewise-attention","repo_kind":"listed","path":"models/gat.py","file_url":"https://github.com/handasontam/GAT-with-edgewise-attention/blob/HEAD/models/gat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/gat","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"be71c975b356bf8f"}},{"code_sha256":"bd896967c973d652","code_sha256_prefix":"bd896967c973d652","entry":"GATLayer","repo":"shenweichen/GraphNeuralNetwork","repo_kind":"listed","path":"gnn/gat.py","file_url":"https://github.com/shenweichen/GraphNeuralNetwork/blob/HEAD/gnn/gat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/gatlayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bd896967c973d652"}},{"code_sha256":"2f96875be1432954","code_sha256_prefix":"2f96875be1432954","entry":"GAT_HOMM_Network","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"2f96875be1432954"}},{"code_sha256":"5ef6599b549742dd","code_sha256_prefix":"5ef6599b549742dd","entry":"GraphAttention","repo":"meliketoy/graph-cnn.pytorch","repo_kind":"listed","path":"layers.py","file_url":"https://github.com/meliketoy/graph-cnn.pytorch/blob/HEAD/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/graphattention","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5ef6599b549742dd"}},{"code_sha256":"89ba00d981eb9302","code_sha256_prefix":"89ba00d981eb9302","entry":"GraphAttention","repo":"YunseobShin/wiki_GAT","repo_kind":"listed","path":"keras_gat/graph_attention_layer.py","file_url":"https://github.com/YunseobShin/wiki_GAT/blob/HEAD/keras_gat/graph_attention_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/graphattention","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"89ba00d981eb9302"}},{"code_sha256":"5e93c4b4d21d5d71","code_sha256_prefix":"5e93c4b4d21d5d71","entry":"GraphAttention","repo":"abhilash1910/GraphAttentionNetworks","repo_kind":"listed","path":"GraphAttentionNetworks/GraphMultiheadAttention.py","file_url":"https://github.com/abhilash1910/GraphAttentionNetworks/blob/HEAD/GraphAttentionNetworks/GraphMultiheadAttention.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/graphattention","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, abhilash1910/GraphAttentionNetworks (NOASSERTION)","mcp_get_code":{"code_sha256":"5e93c4b4d21d5d71"}},{"code_sha256":"01569d1c8b54aedd","code_sha256_prefix":"01569d1c8b54aedd","entry":"GraphAttentionHead","repo":"tatp22/pytorch-fast-GAT","repo_kind":"listed","path":"fast_gat/GAT.py","file_url":"https://github.com/tatp22/pytorch-fast-GAT/blob/HEAD/fast_gat/GAT.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"01569d1c8b54aedd"}},{"code_sha256":"c2cadcfe69abfe1c","code_sha256_prefix":"c2cadcfe69abfe1c","entry":"GraphAttentionLayer","repo":"4pygmalion/GAT_tensorflow","repo_kind":"listed","path":"GAT/_model.py","file_url":"https://github.com/4pygmalion/GAT_tensorflow/blob/HEAD/GAT/_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/graphattentionlayer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, 4pygmalion/GAT_tensorflow when it was checked","mcp_get_code":{"code_sha256":"c2cadcfe69abfe1c"}},{"code_sha256":"5f34746d6309d7fe","code_sha256_prefix":"5f34746d6309d7fe","entry":"GraphConvolution_G","repo":"gayanku/FDGATII","repo_kind":"listed","path":"models.py","file_url":"https://github.com/gayanku/FDGATII/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5f34746d6309d7fe"}},{"code_sha256":"c752223c4cff0254","code_sha256_prefix":"c752223c4cff0254","entry":"HoM","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"c752223c4cff0254"}},{"code_sha256":"7c99ecc825b89cb9","code_sha256_prefix":"7c99ecc825b89cb9","entry":"HoMLayer","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"7c99ecc825b89cb9"}},{"code_sha256":"7d4a66310b01ccfe","code_sha256_prefix":"7d4a66310b01ccfe","entry":"HoMLayer_gnn","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"7d4a66310b01ccfe"}},{"code_sha256":"fc520c658083198c","code_sha256_prefix":"fc520c658083198c","entry":"HyperGATConv","repo":"galkampel/HyperNetworks","repo_kind":"listed","path":"model/gat.py","file_url":"https://github.com/galkampel/HyperNetworks/blob/HEAD/model/gat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, galkampel/HyperNetworks when it was checked","mcp_get_code":{"code_sha256":"fc520c658083198c"}},{"code_sha256":"dcd585593f9c47a5","code_sha256_prefix":"dcd585593f9c47a5","entry":"LayerType","repo":"gordicaleksa/pytorch-GAT","repo_kind":"listed","path":"models/definitions/GAT.py","file_url":"https://github.com/gordicaleksa/pytorch-GAT/blob/HEAD/models/definitions/GAT.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dcd585593f9c47a5"}},{"code_sha256":"b5b7966d6d562760","code_sha256_prefix":"b5b7966d6d562760","entry":"SpMHGAT","repo":"ydzhang-stormstout/HAT","repo_kind":"listed","path":"models/sp_prod_mhat.py","file_url":"https://github.com/ydzhang-stormstout/HAT/blob/HEAD/models/sp_prod_mhat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ydzhang-stormstout/HAT when it was checked","mcp_get_code":{"code_sha256":"b5b7966d6d562760"}},{"code_sha256":"499f87bed1d30f44","code_sha256_prefix":"499f87bed1d30f44","entry":"SpecialSpmm","repo":"HazyResearch/hgcn","repo_kind":"listed","path":"layers/att_layers.py","file_url":"https://github.com/HazyResearch/hgcn/blob/HEAD/layers/att_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HazyResearch/hgcn when it was checked","mcp_get_code":{"code_sha256":"499f87bed1d30f44"}},{"code_sha256":"2e935d44457aab07","code_sha256_prefix":"2e935d44457aab07","entry":"StructuralAttentionLayer","repo":"wan2000/mc-mot","repo_kind":"listed","path":"stgat/layers.py","file_url":"https://github.com/wan2000/mc-mot/blob/HEAD/stgat/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, wan2000/mc-mot when it was checked","mcp_get_code":{"code_sha256":"2e935d44457aab07"}},{"code_sha256":"f52a4f3483c697c3","code_sha256_prefix":"f52a4f3483c697c3","entry":"cora_networkx","repo":"joaopedromattos/gnee","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/joaopedromattos/gnee/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f52a4f3483c697c3"}},{"code_sha256":"6beddb1e8d4bd5ff","code_sha256_prefix":"6beddb1e8d4bd5ff","entry":"find_split","repo":"404nofound/gat","repo_kind":"listed","path":"utils/process_ppi.py","file_url":"https://github.com/404nofound/gat/blob/HEAD/utils/process_ppi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6beddb1e8d4bd5ff"}},{"code_sha256":"9dc615acb2d8de00","code_sha256_prefix":"9dc615acb2d8de00","entry":"gat_reduce","repo":"giuseppefutia/link-prediction-code","repo_kind":"listed","path":"net.py","file_url":"https://github.com/giuseppefutia/link-prediction-code/blob/HEAD/net.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, giuseppefutia/link-prediction-code when it was checked","mcp_get_code":{"code_sha256":"9dc615acb2d8de00"}},{"code_sha256":"5c5300f98cecf9cc","code_sha256_prefix":"5c5300f98cecf9cc","entry":"gelu","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/gelu","census":{"url":"/census/gelu","implementations":43,"papers":74,"distinct_outputs":6,"n_buckets":1,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"5c5300f98cecf9cc"}},{"code_sha256":"be1dbf9aac65198d","code_sha256_prefix":"be1dbf9aac65198d","entry":"get_planetoid_dataset","repo":"marble0117/GNN_models_pytorch","repo_kind":"listed","path":"datasets.py","file_url":"https://github.com/marble0117/GNN_models_pytorch/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"be1dbf9aac65198d"}},{"code_sha256":"afe74d2db9b18ca4","code_sha256_prefix":"afe74d2db9b18ca4","entry":"high_order_aggregation_","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"afe74d2db9b18ca4"}},{"code_sha256":"0a4305f7b4b34882","code_sha256_prefix":"0a4305f7b4b34882","entry":"high_order_selection_","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"0a4305f7b4b34882"}},{"code_sha256":"87047d4b8762a1c3","code_sha256_prefix":"87047d4b8762a1c3","entry":"hom","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"87047d4b8762a1c3"}},{"code_sha256":"c10da56a392c8053","code_sha256_prefix":"c10da56a392c8053","entry":"load_data","repo":"Anak2016/GAT","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Anak2016/GAT/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-data","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c10da56a392c8053"}},{"code_sha256":"a043edcfa5bf7c76","code_sha256_prefix":"a043edcfa5bf7c76","entry":"load_data","repo":"ChengyuSun/gat","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ChengyuSun/gat/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-data","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a043edcfa5bf7c76"}},{"code_sha256":"976ef4bf64ce0be7","code_sha256_prefix":"976ef4bf64ce0be7","entry":"load_data","repo":"danielegrattarola/keras-gat","repo_kind":"listed","path":"keras_gat/utils.py","file_url":"https://github.com/danielegrattarola/keras-gat/blob/HEAD/keras_gat/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-data","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"976ef4bf64ce0be7"}},{"code_sha256":"017f3d425a9cd13e","code_sha256_prefix":"017f3d425a9cd13e","entry":"mask_features","repo":"marble0117/GNN_models_pytorch","repo_kind":"listed","path":"models/masked_gcn.py","file_url":"https://github.com/marble0117/GNN_models_pytorch/blob/HEAD/models/masked_gcn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"017f3d425a9cd13e"}},{"code_sha256":"9001a106b75860f4","code_sha256_prefix":"9001a106b75860f4","entry":"po2","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"9001a106b75860f4"}},{"code_sha256":"0f67c084fcf7537d","code_sha256_prefix":"0f67c084fcf7537d","entry":"po3","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"0f67c084fcf7537d"}},{"code_sha256":"71e010ae9e308364","code_sha256_prefix":"71e010ae9e308364","entry":"po4","repo":"davidpicard/homm","repo_kind":"listed","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, davidpicard/homm when it was checked","mcp_get_code":{"code_sha256":"71e010ae9e308364"}},{"code_sha256":"725414c560fb8a82","code_sha256_prefix":"725414c560fb8a82","entry":"regularization","repo":"joaopedromattos/gnee","repo_kind":"listed","path":"event_graph_utils.py","file_url":"https://github.com/joaopedromattos/gnee/blob/HEAD/event_graph_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/regularization","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"725414c560fb8a82"}},{"code_sha256":"94585c35bb20a736","code_sha256_prefix":"94585c35bb20a736","entry":"roi_pooling_2d","repo":"whut2962575697/gat_sementic_segmentation","repo_kind":"listed","path":"roi_pooling/functions/roi_pooling.py","file_url":"https://github.com/whut2962575697/gat_sementic_segmentation/blob/HEAD/roi_pooling/functions/roi_pooling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"94585c35bb20a736"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3b91a3b4da7935a9c5098cf75da3afac36a11bd0805def9837c80bf64d62db23","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}