{"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/gqa","name":"GQA","full_name":"GQA","description_markdown":"The **GQA** dataset is a large-scale visual question answering dataset with real images from the Visual Genome dataset and balanced question-answer pairs. Each training and validation image is also associated with scene graph annotations describing the classes and attributes of those objects in the scene, and their pairwise relations. Along with the images and question-answer pairs, the GQA dataset provides two types of pre-extracted visual features for each image – convolutional grid features of size 7×7×2048 extracted from a ResNet-101 network trained on ImageNet, and object detection features of size Ndet×2048 (where Ndet is the number of detected objects in each image with a maximum of 100 per image) from a Faster R-CNN detector.\r\n\r\nSource: [Language-Conditioned Graph Networks for Relational Reasoning](https://arxiv.org/abs/1905.04405)\r\nImage Source: [https://arxiv.org/pdf/1902.09506.pdf](https://arxiv.org/pdf/1902.09506.pdf)","description_withheld":null,"homepage":"https://cs.stanford.edu/people/dorarad/gqa/","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/gqa-a-new-dataset-for-compositional-question","title":"GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering","first_author":"Drew A. Hudson","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"},{"name":"Scene Graph Generation","url":"/task/scene-graph-generation","datasets_with_task":"/datasets/task/scene-graph-generation"},{"name":"Graph Question Answering","url":"/task/graph-question-answering","datasets_with_task":"/datasets/task/graph-question-answering"}],"languages":[],"variants":["GQA test-std","GQA test-dev","GQA Test2019","GQA","GQA-OOD"],"data_loaders":[{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/vision/dataset_readers/gqa/","frameworks":["pytorch"]}],"num_papers_in_archive":749,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-gqa-test2019","task":"Visual Question Answering (VQA)","dataset_variant":"GQA Test2019","rows":127,"metrics":["Accuracy","Binary","Open","Consistency","Plausibility","Validity","Distribution"],"first_row_in_archive_order":{"model":"human","paper":null,"metrics":{"Accuracy":"89.3","Binary":"91.2","Consistency":"98.4","Distribution":"0.0","Open":"87.4","Plausibility":"97.2","Validity":"98.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset_variant":"GQA test-dev","rows":17,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CFR","paper":"/paper/coarse-to-fine-reasoning-for-visual-question","metrics":{"Accuracy":"72.1"},"code_links":[{"title":"aioz-ai/cfr_vqa","url":"https://github.com/aioz-ai/cfr_vqa"},{"title":"aioz-ai/crf_vqa","url":"https://github.com/aioz-ai/crf_vqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-std","task":"Visual Question Answering (VQA)","dataset_variant":"GQA test-std","rows":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ProTo","paper":"/paper/proto-program-guided-transformer-for-program","metrics":{"Accuracy":"65.14"},"code_links":[{"title":"sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks","url":"https://github.com/sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/graph-question-answering-on-gqa","task":"Graph Question Answering","dataset_variant":"GQA","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GraphVQA","paper":"/paper/graghvqa-language-guided-graph-neural","metrics":{"Accuracy":"96.30"},"code_links":[{"title":"codexxxl/GraphVQA","url":"https://github.com/codexxxl/GraphVQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-gqa","task":"Visual Question Answering (VQA)","dataset_variant":"GQA","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL+","paper":"/paper/pevl-position-enhanced-pre-training-and","metrics":{"Accuracy":"77"},"code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-gqa","task":"Object Detection","dataset_variant":"GQA","rows":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"KnowZRel","paper":"/paper/knowzrel-common-sense-knowledge-based-zero","metrics":{"mAP":"39"},"code_links":[{"title":"jaleedkhan/zsrr-sgg","url":"https://github.com/jaleedkhan/zsrr-sgg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/scene-graph-generation-on-gqa","task":"Scene Graph Generation","dataset_variant":"GQA","rows":1,"metrics":["zR@100","zR@20","zR@50"],"first_row_in_archive_order":{"model":"KnowZRel","paper":"/paper/knowzrel-common-sense-knowledge-based-zero","metrics":{"zR@100":"29.56","zR@20":"12.47","zR@50":"22.51"},"code_links":[{"title":"jaleedkhan/zsrr-sgg","url":"https://github.com/jaleedkhan/zsrr-sgg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-gqa-1","task":"Visual Question Answering","dataset_variant":"GQA","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LocVLM-L","paper":"/paper/learning-to-localize-objects-improves-spatial","metrics":{"Accuracy":"50.2"},"code_links":[{"title":"kahnchana/locvlm","url":"https://github.com/kahnchana/locvlm"}]},"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":24,"of":24,"counts":{"papers_with_a_benchmark_row":24,"with_a_code_link":21,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":24,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/knowzrel-common-sense-knowledge-based-zero","slug":"knowzrel-common-sense-knowledge-based-zero","title":"KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation","date":"2025-02-21","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}}}},{"paper":"/paper/learning-to-localize-objects-improves-spatial","slug":"learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","arxiv_id":"2404.07449","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hydra-a-hyper-agent-for-dynamic-compositional","slug":"hydra-a-hyper-agent-for-dynamic-compositional","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","date":"2024-03-19","arxiv_id":"2403.12884","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["ControlNet/HYDRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"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/hydra-a-hyper-agent-for-dynamic-compositional#ran","syntology_url":"https://syntology.ai/paper/2403.12884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12884"}}}},{"paper":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}}}},{"paper":"/paper/lyrics-boosting-fine-grained-language-vision","slug":"lyrics-boosting-fine-grained-language-vision","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","date":"2023-12-08","arxiv_id":"2312.05278","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/visual-program-distillation-distilling-tools","slug":"visual-program-distillation-distilling-tools","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","date":"2023-12-05","arxiv_id":"2312.03052","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vinvl-l-enriching-visual-representation-with","slug":"vinvl-l-enriching-visual-representation-with","title":"VinVL+L: Enriching Visual Representation with Location Context in VQA","date":"2023-02-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","rows_on_this_dataset":6,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["salesforce/lavis"],"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/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}}}},{"paper":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining","slug":"plug-and-play-vqa-zero-shot-vqa-by-conjoining","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","date":"2022-10-17","arxiv_id":"2210.08773","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["salesforce/lavis"],"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/plug-and-play-vqa-zero-shot-vqa-by-conjoining#ran","syntology_url":"https://syntology.ai/paper/2210.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08773"}}}},{"paper":"/paper/pevl-position-enhanced-pre-training-and","slug":"pevl-position-enhanced-pre-training-and","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","date":"2022-05-23","arxiv_id":"2205.11169","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}}}},{"paper":"/paper/relvit-concept-guided-vision-transformer-for-1","slug":"relvit-concept-guided-vision-transformer-for-1","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","date":"2022-04-24","arxiv_id":"2204.11167","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":1,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":10,"official":{"repos":["NVlabs/RelViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/relvit-concept-guided-vision-transformer-for-1#ran","syntology_url":"https://syntology.ai/paper/2204.11167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.11167"}}}},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-reasoning-for-visual-question","slug":"coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","arxiv_id":"2110.02526","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["aioz-ai/cfr_vqa","aioz-ai/crf_vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coarse-to-fine-reasoning-for-visual-question#ran","syntology_url":"https://syntology.ai/paper/2110.02526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02526"}}}},{"paper":"/paper/proto-program-guided-transformer-for-program","slug":"proto-program-guided-transformer-for-program","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","date":"2021-10-02","arxiv_id":"2110.00804","rows_on_this_dataset":1,"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":["sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks"],"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/proto-program-guided-transformer-for-program#ran","syntology_url":"https://syntology.ai/paper/2110.00804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00804"}}}},{"paper":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":4,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["ashkamath/mdetr"],"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/mdetr-modulated-detection-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12763"}}}},{"paper":"/paper/graghvqa-language-guided-graph-neural","slug":"graghvqa-language-guided-graph-neural","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","date":"2021-04-20","arxiv_id":"2104.10283","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["pzzhang/VinVL"],"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/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}}}},{"paper":"/paper/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","rows_on_this_dataset":4,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":3,"official":{"repos":["airsplay/lxmert"],"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/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}}}},{"paper":"/paper/graph-reasoning-networks-for-visual-question","slug":"graph-reasoning-networks-for-visual-question","title":"Bilinear Graph Networks for Visual Question Answering","date":"2019-07-23","arxiv_id":"1907.09815","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-by-abstraction-the-neural-state","slug":"learning-by-abstraction-the-neural-state","title":"Learning by Abstraction: The Neural State Machine","date":"2019-07-09","arxiv_id":"1907.03950","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":1,"samples_unverified":8,"pointer_only_for_licence":3,"official":{"repos":["stanfordnlp/mac-network"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-by-abstraction-the-neural-state#ran","syntology_url":"https://syntology.ai/paper/1907.03950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.03950"}}}},{"paper":"/paper/language-conditioned-graph-networks-for","slug":"language-conditioned-graph-networks-for","title":"Language-Conditioned Graph Networks for Relational Reasoning","date":"2019-05-10","arxiv_id":"1905.04405","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-conditioned-graph-networks-for#ran","syntology_url":"https://syntology.ai/paper/1905.04405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04405"}}}},{"paper":"/paper/gqa-a-new-dataset-for-compositional-question","slug":"gqa-a-new-dataset-for-compositional-question","title":"GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering","date":"2019-02-25","arxiv_id":"1902.09506","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/bottom-up-and-top-down-attention-for-image","slug":"bottom-up-and-top-down-attention-for-image","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","date":"2017-07-25","arxiv_id":"1707.07998","rows_on_this_dataset":1,"code_links":65,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":8,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["peteanderson80/bottom-up-attention"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bottom-up-and-top-down-attention-for-image#ran","syntology_url":"https://syntology.ai/paper/1707.07998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.07998"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/knowzrel-common-sense-knowledge-based-zero","slug":"knowzrel-common-sense-knowledge-based-zero","title":"KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation","date":"2025-02-21","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}}}},{"paper":"/paper/learning-to-localize-objects-improves-spatial","slug":"learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","arxiv_id":"2404.07449","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hydra-a-hyper-agent-for-dynamic-compositional","slug":"hydra-a-hyper-agent-for-dynamic-compositional","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","date":"2024-03-19","arxiv_id":"2403.12884","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["ControlNet/HYDRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"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/hydra-a-hyper-agent-for-dynamic-compositional#ran","syntology_url":"https://syntology.ai/paper/2403.12884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12884"}}}},{"paper":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}}}},{"paper":"/paper/lyrics-boosting-fine-grained-language-vision","slug":"lyrics-boosting-fine-grained-language-vision","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","date":"2023-12-08","arxiv_id":"2312.05278","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/visual-program-distillation-distilling-tools","slug":"visual-program-distillation-distilling-tools","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","date":"2023-12-05","arxiv_id":"2312.03052","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vinvl-l-enriching-visual-representation-with","slug":"vinvl-l-enriching-visual-representation-with","title":"VinVL+L: Enriching Visual Representation with Location Context in VQA","date":"2023-02-22","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","rows_on_this_dataset":6,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["salesforce/lavis"],"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/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}}}},{"paper":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining","slug":"plug-and-play-vqa-zero-shot-vqa-by-conjoining","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","date":"2022-10-17","arxiv_id":"2210.08773","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["salesforce/lavis"],"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/plug-and-play-vqa-zero-shot-vqa-by-conjoining#ran","syntology_url":"https://syntology.ai/paper/2210.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08773"}}}},{"paper":"/paper/pevl-position-enhanced-pre-training-and","slug":"pevl-position-enhanced-pre-training-and","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","date":"2022-05-23","arxiv_id":"2205.11169","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}}}},{"paper":"/paper/relvit-concept-guided-vision-transformer-for-1","slug":"relvit-concept-guided-vision-transformer-for-1","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","date":"2022-04-24","arxiv_id":"2204.11167","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":1,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":10,"official":{"repos":["NVlabs/RelViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/relvit-concept-guided-vision-transformer-for-1#ran","syntology_url":"https://syntology.ai/paper/2204.11167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.11167"}}}},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-reasoning-for-visual-question","slug":"coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","arxiv_id":"2110.02526","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["aioz-ai/cfr_vqa","aioz-ai/crf_vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coarse-to-fine-reasoning-for-visual-question#ran","syntology_url":"https://syntology.ai/paper/2110.02526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02526"}}}},{"paper":"/paper/proto-program-guided-transformer-for-program","slug":"proto-program-guided-transformer-for-program","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","date":"2021-10-02","arxiv_id":"2110.00804","rows_on_this_dataset":1,"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":["sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks"],"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/proto-program-guided-transformer-for-program#ran","syntology_url":"https://syntology.ai/paper/2110.00804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00804"}}}},{"paper":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":4,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["ashkamath/mdetr"],"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/mdetr-modulated-detection-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12763"}}}},{"paper":"/paper/graghvqa-language-guided-graph-neural","slug":"graghvqa-language-guided-graph-neural","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","date":"2021-04-20","arxiv_id":"2104.10283","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["pzzhang/VinVL"],"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/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}}}},{"paper":"/paper/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","rows_on_this_dataset":4,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":3,"official":{"repos":["airsplay/lxmert"],"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/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}}}},{"paper":"/paper/graph-reasoning-networks-for-visual-question","slug":"graph-reasoning-networks-for-visual-question","title":"Bilinear Graph Networks for Visual Question Answering","date":"2019-07-23","arxiv_id":"1907.09815","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-by-abstraction-the-neural-state","slug":"learning-by-abstraction-the-neural-state","title":"Learning by Abstraction: The Neural State Machine","date":"2019-07-09","arxiv_id":"1907.03950","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":1,"samples_unverified":8,"pointer_only_for_licence":3,"official":{"repos":["stanfordnlp/mac-network"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-by-abstraction-the-neural-state#ran","syntology_url":"https://syntology.ai/paper/1907.03950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.03950"}}}},{"paper":"/paper/language-conditioned-graph-networks-for","slug":"language-conditioned-graph-networks-for","title":"Language-Conditioned Graph Networks for Relational Reasoning","date":"2019-05-10","arxiv_id":"1905.04405","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-conditioned-graph-networks-for#ran","syntology_url":"https://syntology.ai/paper/1905.04405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04405"}}}},{"paper":"/paper/gqa-a-new-dataset-for-compositional-question","slug":"gqa-a-new-dataset-for-compositional-question","title":"GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering","date":"2019-02-25","arxiv_id":"1902.09506","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/bottom-up-and-top-down-attention-for-image","slug":"bottom-up-and-top-down-attention-for-image","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","date":"2017-07-25","arxiv_id":"1707.07998","rows_on_this_dataset":1,"code_links":65,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":8,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["peteanderson80/bottom-up-attention"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bottom-up-and-top-down-attention-for-image#ran","syntology_url":"https://syntology.ai/paper/1707.07998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.07998"}}}}],"papers_where_code_ran":14,"papers_where_code_ran_first_page":"/dataset/gqa/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/gqa/papers/ran/1","json":"/dataset/gqa/papers/ran/1.json","rows":14}],"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":131,"samples_ran":81,"samples_constructed":13,"samples_ran_checked":47,"samples_ran_instrument_failed":34,"samples_unverified":50,"pointer_only_for_licence":35,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":14,"papers_with_a_run_with_no_instrument_failure":13,"papers_where_every_run_was_an_instrument_failure":1,"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":16,"papers_placed":0,"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/visual-question-answering-on-gqa-test2019","since_archive":"/sota/visual-question-answering-on-gqa-test2019#since-judged","papers_judged":5,"placed":0},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","since_archive":"/sota/visual-question-answering-on-gqa-test-dev#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/visual-question-answering-on-gqa","since_archive":"/sota/visual-question-answering-on-gqa#since-judged","papers_judged":9,"placed":0},{"leaderboard":"/sota/visual-question-answering-on-gqa-1","since_archive":"/sota/visual-question-answering-on-gqa-1#since-judged","papers_judged":7,"placed":0}]},"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":"62fbd34bf9a3fd62c484666f0f2fa42effab00da35867cea074edb86d8a25379","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}