{"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":"/dataset/webkb","name":"WebKB","full_name":"WebKB","description_markdown":"**WebKB** is a dataset that includes web pages from computer science departments of various universities. 4,518 web pages are categorized into 6 imbalanced categories (Student, Faculty, Staff, Department, Course, Project). Additionally there is Other miscellanea category that is not comparable to the rest.\r\n\r\nSource: [Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation](https://arxiv.org/abs/1606.04429)","description_withheld":null,"homepage":"http://www.cs.cmu.edu/~webkb/","introduced_date":"1998-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Learning to Extract Symbolic Knowledge from the World Wide Web","first_author":null,"url":"http://www.aaai.org/Library/AAAI/1998/aaai98-072.php"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Node Classification","url":"/task/node-classification","datasets_with_task":"/datasets/task/node-classification"},{"name":"Node Clustering","url":"/task/node-clustering","datasets_with_task":"/datasets/task/node-clustering"},{"name":"Imputation","url":"/task/imputation","datasets_with_task":"/datasets/task/imputation"},{"name":"Relational Reasoning","url":"/task/relational-reasoning","datasets_with_task":"/datasets/task/relational-reasoning"},{"name":"Bayesian Inference","url":"/task/bayesian-inference","datasets_with_task":"/datasets/task/bayesian-inference"}],"languages":[],"variants":["WebKB","Cornell","Texas","Wisconsin"],"data_loaders":[{"repo":"https://github.com/rusty1s/pytorch_geometric","url":"https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html","frameworks":["pytorch"]}],"num_papers_in_archive":113,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset_variant":"Wisconsin","rows":63,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"5-HiGCN","paper":"/paper/higher-order-graph-convolutional-network-with","metrics":{"Accuracy":"94.99±0.65"},"code_links":[{"title":"yiminghh/higcn","url":"https://github.com/yiminghh/higcn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset_variant":"Texas","rows":62,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RDGNN-S","paper":"/paper/graph-neural-reaction-diffusion-models","metrics":{"Accuracy":"94.59 ± 5.97"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":50,"of":50,"counts":{"papers_with_a_benchmark_row":50,"with_a_code_link":35,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":50,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/mamba-based-graph-convolutional-networks","slug":"mamba-based-graph-convolutional-networks","title":"Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space","date":"2025-01-26","arxiv_id":"2501.15461","rows_on_this_dataset":1,"code_links":0,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mamba-based-graph-convolutional-networks#ran","syntology_url":"https://syntology.ai/paper/2501.15461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15461"}}}},{"paper":"/paper/deltagnn-graph-neural-network-with","slug":"deltagnn-graph-neural-network-with","title":"DeltaGNN: Graph Neural Network with Information Flow Control","date":"2025-01-10","arxiv_id":"2501.06002","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/heterophilic-graph-neural-networks","slug":"heterophilic-graph-neural-networks","title":"Heterophilic Graph Neural Networks Optimization with Causal Message-passing","date":"2024-11-21","arxiv_id":"2411.13821","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-graph-neural-networks-by-learning","slug":"improving-graph-neural-networks-by-learning","title":"Improving Graph Neural Networks by Learning Continuous Edge Directions","date":"2024-10-18","arxiv_id":"2410.14109","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unigap-a-universal-and-adaptive-graph","slug":"unigap-a-universal-and-adaptive-graph","title":"UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks","date":"2024-07-28","arxiv_id":"2407.19420","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/the-heterophilic-snowflake-hypothesis","slug":"the-heterophilic-snowflake-hypothesis","title":"The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs","date":"2024-06-18","arxiv_id":"2406.12539","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/graph-neural-reaction-diffusion-models","slug":"graph-neural-reaction-diffusion-models","title":"Graph Neural Reaction Diffusion Models","date":"2024-06-16","arxiv_id":"2406.10871","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/transfer-entropy-in-graph-convolutional","slug":"transfer-entropy-in-graph-convolutional","title":"Transfer Entropy in Graph Convolutional Neural Networks","date":"2024-06-08","arxiv_id":"2406.06632","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/heterophilous-distribution-propagation-for","slug":"heterophilous-distribution-propagation-for","title":"Heterophilous Distribution Propagation for Graph Neural Networks","date":"2024-05-31","arxiv_id":"2405.20640","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sign-is-not-a-remedy-multiset-to-multiset","slug":"sign-is-not-a-remedy-multiset-to-multiset","title":"Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs","date":"2024-05-31","arxiv_id":"2405.20652","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/graph-neural-aggregation-diffusion-with","slug":"graph-neural-aggregation-diffusion-with","title":"Graph Neural Aggregation-diffusion with Metastability","date":"2024-03-29","arxiv_id":"2403.20221","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learn-from-heterophily-heterophilous","slug":"learn-from-heterophily-heterophilous","title":"Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network","date":"2024-03-26","arxiv_id":"2403.17351","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/refining-latent-homophilic-structures-over","slug":"refining-latent-homophilic-structures-over","title":"Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks","date":"2023-12-27","arxiv_id":"2312.16418","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/graphrare-reinforcement-learning-enhanced","slug":"graphrare-reinforcement-learning-enhanced","title":"GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy","date":"2023-12-15","arxiv_id":"2312.09708","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/cat-a-causally-graph-attention-network-for","slug":"cat-a-causally-graph-attention-network-for","title":"CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph","date":"2023-12-14","arxiv_id":"2312.08672","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/breaking-the-entanglement-of-homophily-and","slug":"breaking-the-entanglement-of-homophily-and","title":"Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification","date":"2023-12-07","arxiv_id":"2312.04111","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/higher-order-graph-convolutional-network-with","slug":"higher-order-graph-convolutional-network-with","title":"Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes","date":"2023-09-22","arxiv_id":"2309.12971","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["yiminghh/higcn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/higher-order-graph-convolutional-network-with#ran","syntology_url":"https://syntology.ai/paper/2309.12971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12971"}}}},{"paper":"/paper/bregman-graph-neural-network","slug":"bregman-graph-neural-network","title":"Bregman Graph Neural Network","date":"2023-09-12","arxiv_id":"2309.06645","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transitivity-preserving-graph-representation","slug":"transitivity-preserving-graph-representation","title":"Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity","date":"2023-08-18","arxiv_id":"2308.09517","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":26,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":6,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["nslab-cuk/unified-graph-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/transitivity-preserving-graph-representation#ran","syntology_url":"https://syntology.ai/paper/2308.09517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09517"}}}},{"paper":"/paper/unig-encoder-a-universal-feature-encoder-for","slug":"unig-encoder-a-universal-feature-encoder-for","title":"UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification","date":"2023-08-03","arxiv_id":"2308.01650","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/diffusion-jump-gnns-homophiliation-via","slug":"diffusion-jump-gnns-homophiliation-via","title":"Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters","date":"2023-06-29","arxiv_id":"2306.16976","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["AhmedBegggaUA/TFM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusion-jump-gnns-homophiliation-via#ran","syntology_url":"https://syntology.ai/paper/2306.16976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16976"}}}},{"paper":"/paper/self-attention-dual-embedding-for-graphs-with","slug":"self-attention-dual-embedding-for-graphs-with","title":"Self-attention Dual Embedding for Graphs with Heterophily","date":"2023-05-28","arxiv_id":"2305.18385","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/gcnh-a-simple-method-for-representation","slug":"gcnh-a-simple-method-for-representation","title":"GCNH: A Simple Method For Representation Learning On Heterophilous Graphs","date":"2023-04-21","arxiv_id":"2304.10896","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ordered-gnn-ordering-message-passing-to-deal","slug":"ordered-gnn-ordering-message-passing-to-deal","title":"Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing","date":"2023-02-03","arxiv_id":"2302.01524","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":4,"pointer_only_for_licence":8,"official":{"repos":["lumia-group/orderedgnn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ordered-gnn-ordering-message-passing-to-deal#ran","syntology_url":"https://syntology.ai/paper/2302.01524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01524"}}}},{"paper":"/paper/enhancing-intra-class-information-extraction","slug":"enhancing-intra-class-information-extraction","title":"Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach","date":"2022-11-20","arxiv_id":"2211.10990","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/beyond-homophily-with-graph-echo-state-1","slug":"beyond-homophily-with-graph-echo-state-1","title":"Beyond Homophily with Graph Echo State Networks","date":"2022-10-27","arxiv_id":"2210.15731","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/revisiting-heterophily-for-graph-neural","slug":"revisiting-heterophily-for-graph-neural","title":"Revisiting Heterophily For Graph Neural Networks","date":"2022-10-14","arxiv_id":"2210.07606","rows_on_this_dataset":16,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["SitaoLuan/ACM-GNN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/revisiting-heterophily-for-graph-neural#ran","syntology_url":"https://syntology.ai/paper/2210.07606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07606"}}}},{"paper":"/paper/make-heterophily-graphs-better-fit-gnn-a","slug":"make-heterophily-graphs-better-fit-gnn-a","title":"Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach","date":"2022-09-17","arxiv_id":"2209.08264","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/sheaf-neural-networks-with-connection","slug":"sheaf-neural-networks-with-connection","title":"Sheaf Neural Networks with Connection Laplacians","date":"2022-06-17","arxiv_id":"2206.08702","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/diffwire-inductive-graph-rewiring-via-the","slug":"diffwire-inductive-graph-rewiring-via-the","title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","date":"2022-06-15","arxiv_id":"2206.07369","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/universal-deep-gnns-rethinking-residual","slug":"universal-deep-gnns-rethinking-residual","title":"Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing","date":"2022-05-30","arxiv_id":"2205.15127","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/finding-global-homophily-in-graph-neural","slug":"finding-global-homophily-in-graph-neural","title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","date":"2022-05-15","arxiv_id":"2205.07308","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/neural-sheaf-diffusion-a-topological","slug":"neural-sheaf-diffusion-a-topological","title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","date":"2022-02-09","arxiv_id":"2202.04579","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["twitter-research/neural-sheaf-diffusion"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-sheaf-diffusion-a-topological#ran","syntology_url":"https://syntology.ai/paper/2202.04579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04579"}}}},{"paper":"/paper/understanding-over-squashing-and-bottlenecks-1","slug":"understanding-over-squashing-and-bottlenecks-1","title":"Understanding over-squashing and bottlenecks on graphs via curvature","date":"2021-11-29","arxiv_id":"2111.14522","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["jctops/understanding-oversquashing"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understanding-over-squashing-and-bottlenecks-1#ran","syntology_url":"https://syntology.ai/paper/2111.14522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14522"}}}},{"paper":"/paper/cn-motifs-perceptive-graph-neural-networks","slug":"cn-motifs-perceptive-graph-neural-networks","title":"CN-Motifs Perceptive Graph Neural Networks","date":"2021-11-15","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/large-scale-learning-on-non-homophilous","slug":"large-scale-learning-on-non-homophilous","title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","date":"2021-10-27","arxiv_id":"2110.14446","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":15,"samples_constructed":5,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":6,"pointer_only_for_licence":11,"official":{"repos":["cuai/non-homophily-large-scale"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/large-scale-learning-on-non-homophilous#ran","syntology_url":"https://syntology.ai/paper/2110.14446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14446"}}}},{"paper":"/paper/fdgatii-fast-dynamic-graph-attention-with","slug":"fdgatii-fast-dynamic-graph-attention-with","title":"FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping","date":"2021-10-21","arxiv_id":"2110.11464","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/label-wise-message-passing-graph-neural","slug":"label-wise-message-passing-graph-neural","title":"Label-Wise Graph Convolutional Network for Heterophilic Graphs","date":"2021-10-15","arxiv_id":"2110.08128","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tree-decomposed-graph-neural-network","slug":"tree-decomposed-graph-neural-network","title":"Tree Decomposed Graph Neural Network","date":"2021-08-25","arxiv_id":"2108.11022","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/simple-truncated-svd-based-model-for-node","slug":"simple-truncated-svd-based-model-for-node","title":"Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs","date":"2021-06-24","arxiv_id":"2106.12807","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/breaking-the-limit-of-graph-neural-networks","slug":"breaking-the-limit-of-graph-neural-networks","title":"Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns","date":"2021-06-11","arxiv_id":"2106.06586","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["susheels/gnns-and-local-assortativity"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/breaking-the-limit-of-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2106.06586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06586"}}}},{"paper":"/paper/improving-graph-neural-networks-with-simple","slug":"improving-graph-neural-networks-with-simple","title":"Improving Graph Neural Networks with Simple Architecture Design","date":"2021-05-17","arxiv_id":"2105.07634","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/two-sides-of-the-same-coin-heterophily-and","slug":"two-sides-of-the-same-coin-heterophily-and","title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","date":"2021-02-12","arxiv_id":"2102.06462","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/beyond-low-frequency-information-in-graph","slug":"beyond-low-frequency-information-in-graph","title":"Beyond Low-frequency Information in Graph Convolutional Networks","date":"2021-01-04","arxiv_id":"2101.00797","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/simple-and-deep-graph-convolutional-networks-1","slug":"simple-and-deep-graph-convolutional-networks-1","title":"Simple and Deep Graph Convolutional Networks","date":"2020-07-04","arxiv_id":"2007.02133","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["chennnM/GCNII"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-deep-graph-convolutional-networks-1#ran","syntology_url":"https://syntology.ai/paper/2007.02133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02133"}}}},{"paper":"/paper/generalizing-graph-neural-networks-beyond","slug":"generalizing-graph-neural-networks-beyond","title":"Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs","date":"2020-06-20","arxiv_id":"2006.11468","rows_on_this_dataset":4,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":16,"samples_constructed":2,"samples_ran_checked":13,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":13,"official":{"repos":["GemsLab/H2GCN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generalizing-graph-neural-networks-beyond#ran","syntology_url":"https://syntology.ai/paper/2006.11468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11468"}}}},{"paper":"/paper/joint-adaptive-feature-smoothing-and-topology","slug":"joint-adaptive-feature-smoothing-and-topology","title":"Adaptive Universal Generalized PageRank Graph Neural Network","date":"2020-06-14","arxiv_id":"2006.07988","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["jianhao2016/GPRGNN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/joint-adaptive-feature-smoothing-and-topology#ran","syntology_url":"https://syntology.ai/paper/2006.07988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07988"}}}},{"paper":"/paper/non-local-graph-neural-networks","slug":"non-local-graph-neural-networks","title":"Non-Local Graph Neural Networks","date":"2020-05-29","arxiv_id":"2005.14612","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["divelab/Non-Local-GNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-local-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2005.14612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14612"}}}},{"paper":"/paper/geom-gcn-geometric-graph-convolutional-1","slug":"geom-gcn-geometric-graph-convolutional-1","title":"Geom-GCN: Geometric Graph Convolutional Networks","date":"2020-02-13","arxiv_id":"2002.05287","rows_on_this_dataset":6,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":7,"official":{"repos":["graphdml-uiuc-jlu/geom-gcn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/geom-gcn-geometric-graph-convolutional-1#ran","syntology_url":"https://syntology.ai/paper/2002.05287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05287"}}}},{"paper":"/paper/mixhop-higher-order-graph-convolution","slug":"mixhop-higher-order-graph-convolution","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","date":"2019-04-30","arxiv_id":"1905.00067","rows_on_this_dataset":2,"code_links":3,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/mamba-based-graph-convolutional-networks","slug":"mamba-based-graph-convolutional-networks","title":"Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space","date":"2025-01-26","arxiv_id":"2501.15461","rows_on_this_dataset":1,"code_links":0,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mamba-based-graph-convolutional-networks#ran","syntology_url":"https://syntology.ai/paper/2501.15461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15461"}}}},{"paper":"/paper/deltagnn-graph-neural-network-with","slug":"deltagnn-graph-neural-network-with","title":"DeltaGNN: Graph Neural Network with Information Flow Control","date":"2025-01-10","arxiv_id":"2501.06002","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/heterophilic-graph-neural-networks","slug":"heterophilic-graph-neural-networks","title":"Heterophilic Graph Neural Networks Optimization with Causal Message-passing","date":"2024-11-21","arxiv_id":"2411.13821","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-graph-neural-networks-by-learning","slug":"improving-graph-neural-networks-by-learning","title":"Improving Graph Neural Networks by Learning Continuous Edge Directions","date":"2024-10-18","arxiv_id":"2410.14109","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unigap-a-universal-and-adaptive-graph","slug":"unigap-a-universal-and-adaptive-graph","title":"UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks","date":"2024-07-28","arxiv_id":"2407.19420","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/the-heterophilic-snowflake-hypothesis","slug":"the-heterophilic-snowflake-hypothesis","title":"The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs","date":"2024-06-18","arxiv_id":"2406.12539","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/graph-neural-reaction-diffusion-models","slug":"graph-neural-reaction-diffusion-models","title":"Graph Neural Reaction Diffusion Models","date":"2024-06-16","arxiv_id":"2406.10871","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/transfer-entropy-in-graph-convolutional","slug":"transfer-entropy-in-graph-convolutional","title":"Transfer Entropy in Graph Convolutional Neural Networks","date":"2024-06-08","arxiv_id":"2406.06632","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/heterophilous-distribution-propagation-for","slug":"heterophilous-distribution-propagation-for","title":"Heterophilous Distribution Propagation for Graph Neural Networks","date":"2024-05-31","arxiv_id":"2405.20640","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sign-is-not-a-remedy-multiset-to-multiset","slug":"sign-is-not-a-remedy-multiset-to-multiset","title":"Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs","date":"2024-05-31","arxiv_id":"2405.20652","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/graph-neural-aggregation-diffusion-with","slug":"graph-neural-aggregation-diffusion-with","title":"Graph Neural Aggregation-diffusion with Metastability","date":"2024-03-29","arxiv_id":"2403.20221","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learn-from-heterophily-heterophilous","slug":"learn-from-heterophily-heterophilous","title":"Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network","date":"2024-03-26","arxiv_id":"2403.17351","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/refining-latent-homophilic-structures-over","slug":"refining-latent-homophilic-structures-over","title":"Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks","date":"2023-12-27","arxiv_id":"2312.16418","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/graphrare-reinforcement-learning-enhanced","slug":"graphrare-reinforcement-learning-enhanced","title":"GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy","date":"2023-12-15","arxiv_id":"2312.09708","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/cat-a-causally-graph-attention-network-for","slug":"cat-a-causally-graph-attention-network-for","title":"CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph","date":"2023-12-14","arxiv_id":"2312.08672","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/breaking-the-entanglement-of-homophily-and","slug":"breaking-the-entanglement-of-homophily-and","title":"Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification","date":"2023-12-07","arxiv_id":"2312.04111","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/higher-order-graph-convolutional-network-with","slug":"higher-order-graph-convolutional-network-with","title":"Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes","date":"2023-09-22","arxiv_id":"2309.12971","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["yiminghh/higcn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/higher-order-graph-convolutional-network-with#ran","syntology_url":"https://syntology.ai/paper/2309.12971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12971"}}}},{"paper":"/paper/bregman-graph-neural-network","slug":"bregman-graph-neural-network","title":"Bregman Graph Neural Network","date":"2023-09-12","arxiv_id":"2309.06645","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/transitivity-preserving-graph-representation","slug":"transitivity-preserving-graph-representation","title":"Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity","date":"2023-08-18","arxiv_id":"2308.09517","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":26,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":6,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["nslab-cuk/unified-graph-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/transitivity-preserving-graph-representation#ran","syntology_url":"https://syntology.ai/paper/2308.09517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09517"}}}},{"paper":"/paper/unig-encoder-a-universal-feature-encoder-for","slug":"unig-encoder-a-universal-feature-encoder-for","title":"UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification","date":"2023-08-03","arxiv_id":"2308.01650","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/diffusion-jump-gnns-homophiliation-via","slug":"diffusion-jump-gnns-homophiliation-via","title":"Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters","date":"2023-06-29","arxiv_id":"2306.16976","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["AhmedBegggaUA/TFM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusion-jump-gnns-homophiliation-via#ran","syntology_url":"https://syntology.ai/paper/2306.16976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16976"}}}},{"paper":"/paper/self-attention-dual-embedding-for-graphs-with","slug":"self-attention-dual-embedding-for-graphs-with","title":"Self-attention Dual Embedding for Graphs with Heterophily","date":"2023-05-28","arxiv_id":"2305.18385","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/gcnh-a-simple-method-for-representation","slug":"gcnh-a-simple-method-for-representation","title":"GCNH: A Simple Method For Representation Learning On Heterophilous Graphs","date":"2023-04-21","arxiv_id":"2304.10896","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ordered-gnn-ordering-message-passing-to-deal","slug":"ordered-gnn-ordering-message-passing-to-deal","title":"Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing","date":"2023-02-03","arxiv_id":"2302.01524","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":4,"pointer_only_for_licence":8,"official":{"repos":["lumia-group/orderedgnn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ordered-gnn-ordering-message-passing-to-deal#ran","syntology_url":"https://syntology.ai/paper/2302.01524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01524"}}}},{"paper":"/paper/enhancing-intra-class-information-extraction","slug":"enhancing-intra-class-information-extraction","title":"Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach","date":"2022-11-20","arxiv_id":"2211.10990","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/beyond-homophily-with-graph-echo-state-1","slug":"beyond-homophily-with-graph-echo-state-1","title":"Beyond Homophily with Graph Echo State Networks","date":"2022-10-27","arxiv_id":"2210.15731","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/revisiting-heterophily-for-graph-neural","slug":"revisiting-heterophily-for-graph-neural","title":"Revisiting Heterophily For Graph Neural Networks","date":"2022-10-14","arxiv_id":"2210.07606","rows_on_this_dataset":16,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["SitaoLuan/ACM-GNN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/revisiting-heterophily-for-graph-neural#ran","syntology_url":"https://syntology.ai/paper/2210.07606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07606"}}}},{"paper":"/paper/make-heterophily-graphs-better-fit-gnn-a","slug":"make-heterophily-graphs-better-fit-gnn-a","title":"Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach","date":"2022-09-17","arxiv_id":"2209.08264","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/sheaf-neural-networks-with-connection","slug":"sheaf-neural-networks-with-connection","title":"Sheaf Neural Networks with Connection Laplacians","date":"2022-06-17","arxiv_id":"2206.08702","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/diffwire-inductive-graph-rewiring-via-the","slug":"diffwire-inductive-graph-rewiring-via-the","title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","date":"2022-06-15","arxiv_id":"2206.07369","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/universal-deep-gnns-rethinking-residual","slug":"universal-deep-gnns-rethinking-residual","title":"Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing","date":"2022-05-30","arxiv_id":"2205.15127","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/finding-global-homophily-in-graph-neural","slug":"finding-global-homophily-in-graph-neural","title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","date":"2022-05-15","arxiv_id":"2205.07308","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/neural-sheaf-diffusion-a-topological","slug":"neural-sheaf-diffusion-a-topological","title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","date":"2022-02-09","arxiv_id":"2202.04579","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["twitter-research/neural-sheaf-diffusion"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-sheaf-diffusion-a-topological#ran","syntology_url":"https://syntology.ai/paper/2202.04579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04579"}}}},{"paper":"/paper/understanding-over-squashing-and-bottlenecks-1","slug":"understanding-over-squashing-and-bottlenecks-1","title":"Understanding over-squashing and bottlenecks on graphs via curvature","date":"2021-11-29","arxiv_id":"2111.14522","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["jctops/understanding-oversquashing"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understanding-over-squashing-and-bottlenecks-1#ran","syntology_url":"https://syntology.ai/paper/2111.14522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14522"}}}},{"paper":"/paper/cn-motifs-perceptive-graph-neural-networks","slug":"cn-motifs-perceptive-graph-neural-networks","title":"CN-Motifs Perceptive Graph Neural Networks","date":"2021-11-15","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/large-scale-learning-on-non-homophilous","slug":"large-scale-learning-on-non-homophilous","title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","date":"2021-10-27","arxiv_id":"2110.14446","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":15,"samples_constructed":5,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":6,"pointer_only_for_licence":11,"official":{"repos":["cuai/non-homophily-large-scale"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/large-scale-learning-on-non-homophilous#ran","syntology_url":"https://syntology.ai/paper/2110.14446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14446"}}}},{"paper":"/paper/fdgatii-fast-dynamic-graph-attention-with","slug":"fdgatii-fast-dynamic-graph-attention-with","title":"FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping","date":"2021-10-21","arxiv_id":"2110.11464","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/label-wise-message-passing-graph-neural","slug":"label-wise-message-passing-graph-neural","title":"Label-Wise Graph Convolutional Network for Heterophilic Graphs","date":"2021-10-15","arxiv_id":"2110.08128","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tree-decomposed-graph-neural-network","slug":"tree-decomposed-graph-neural-network","title":"Tree Decomposed Graph Neural Network","date":"2021-08-25","arxiv_id":"2108.11022","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/simple-truncated-svd-based-model-for-node","slug":"simple-truncated-svd-based-model-for-node","title":"Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs","date":"2021-06-24","arxiv_id":"2106.12807","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/breaking-the-limit-of-graph-neural-networks","slug":"breaking-the-limit-of-graph-neural-networks","title":"Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns","date":"2021-06-11","arxiv_id":"2106.06586","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["susheels/gnns-and-local-assortativity"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/breaking-the-limit-of-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2106.06586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06586"}}}},{"paper":"/paper/improving-graph-neural-networks-with-simple","slug":"improving-graph-neural-networks-with-simple","title":"Improving Graph Neural Networks with Simple Architecture Design","date":"2021-05-17","arxiv_id":"2105.07634","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/two-sides-of-the-same-coin-heterophily-and","slug":"two-sides-of-the-same-coin-heterophily-and","title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","date":"2021-02-12","arxiv_id":"2102.06462","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/beyond-low-frequency-information-in-graph","slug":"beyond-low-frequency-information-in-graph","title":"Beyond Low-frequency Information in Graph Convolutional Networks","date":"2021-01-04","arxiv_id":"2101.00797","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/simple-and-deep-graph-convolutional-networks-1","slug":"simple-and-deep-graph-convolutional-networks-1","title":"Simple and Deep Graph Convolutional Networks","date":"2020-07-04","arxiv_id":"2007.02133","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["chennnM/GCNII"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-deep-graph-convolutional-networks-1#ran","syntology_url":"https://syntology.ai/paper/2007.02133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02133"}}}},{"paper":"/paper/generalizing-graph-neural-networks-beyond","slug":"generalizing-graph-neural-networks-beyond","title":"Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs","date":"2020-06-20","arxiv_id":"2006.11468","rows_on_this_dataset":4,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":16,"samples_constructed":2,"samples_ran_checked":13,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":13,"official":{"repos":["GemsLab/H2GCN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generalizing-graph-neural-networks-beyond#ran","syntology_url":"https://syntology.ai/paper/2006.11468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11468"}}}},{"paper":"/paper/joint-adaptive-feature-smoothing-and-topology","slug":"joint-adaptive-feature-smoothing-and-topology","title":"Adaptive Universal Generalized PageRank Graph Neural Network","date":"2020-06-14","arxiv_id":"2006.07988","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["jianhao2016/GPRGNN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/joint-adaptive-feature-smoothing-and-topology#ran","syntology_url":"https://syntology.ai/paper/2006.07988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07988"}}}},{"paper":"/paper/non-local-graph-neural-networks","slug":"non-local-graph-neural-networks","title":"Non-Local Graph Neural Networks","date":"2020-05-29","arxiv_id":"2005.14612","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["divelab/Non-Local-GNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/non-local-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2005.14612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14612"}}}},{"paper":"/paper/geom-gcn-geometric-graph-convolutional-1","slug":"geom-gcn-geometric-graph-convolutional-1","title":"Geom-GCN: Geometric Graph Convolutional Networks","date":"2020-02-13","arxiv_id":"2002.05287","rows_on_this_dataset":6,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":7,"official":{"repos":["graphdml-uiuc-jlu/geom-gcn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/geom-gcn-geometric-graph-convolutional-1#ran","syntology_url":"https://syntology.ai/paper/2002.05287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05287"}}}},{"paper":"/paper/mixhop-higher-order-graph-convolution","slug":"mixhop-higher-order-graph-convolution","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","date":"2019-04-30","arxiv_id":"1905.00067","rows_on_this_dataset":2,"code_links":3,"syntology":null}],"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/dataset/webkb/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/webkb/papers/ran/1","json":"/dataset/webkb/papers/ran/1.json","rows":13}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":15,"samples_harvested":127,"samples_ran":89,"samples_constructed":16,"samples_ran_checked":57,"samples_ran_instrument_failed":32,"samples_unverified":38,"pointer_only_for_licence":55,"papers_with_no_sample_that_ran":2,"papers_with_a_sample_that_ran":13,"papers_with_a_run_with_no_instrument_failure":9,"papers_where_every_run_was_an_instrument_failure":4,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":12,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/node-classification-on-wisconsin","since_archive":"/sota/node-classification-on-wisconsin#since-judged","papers_judged":10,"placed":1},{"leaderboard":"/sota/node-classification-on-texas","since_archive":"/sota/node-classification-on-texas#since-judged","papers_judged":9,"placed":1}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"63042687b36f1c58f69501f3fc55b7bd95fe7d348982668b36b903efd45d3c99","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}