{"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/a-okvqa","name":"A-OKVQA","full_name":null,"description_markdown":"**A-OKVQA** is crowdsourced visual question answering dataset composed of a diverse set of about 25K questions requiring a broad base of commonsense and world knowledge to answer.","description_withheld":null,"homepage":"https://allenai.org/project/a-okvqa/home","introduced_date":"2022-06-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-okvqa-a-benchmark-for-visual-question","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","first_author":"Dustin Schwenk","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"}],"languages":[],"variants":["A-OKVQA"],"data_loaders":[],"num_papers_in_archive":154,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-a-okvqa","task":"Visual Question Answering (VQA)","dataset_variant":"A-OKVQA","rows":15,"metrics":["MC Accuracy","DA VQA Score"],"first_row_in_archive_order":{"model":"SMoLA-PaLI-X Specialist Model","paper":"/paper/omni-smola-boosting-generalist-multimodal","metrics":{"DA VQA Score":"70.55","MC Accuracy":"83.75"},"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":13,"of":13,"counts":{"papers_with_a_benchmark_row":13,"with_a_code_link":8,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/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/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/omni-smola-boosting-generalist-multimodal","slug":"omni-smola-boosting-generalist-multimodal","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","date":"2023-12-01","arxiv_id":"2312.00968","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/boosting-the-power-of-small-multimodal","slug":"boosting-the-power-of-small-multimodal","title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","date":"2023-11-23","arxiv_id":"2311.14109","rows_on_this_dataset":1,"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":["chengtan9907/mc-cot"],"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/boosting-the-power-of-small-multimodal#ran","syntology_url":"https://syntology.ai/paper/2311.14109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14109"}}}},{"paper":"/paper/a-simple-baseline-for-knowledge-based-visual","slug":"a-simple-baseline-for-knowledge-based-visual","title":"A Simple Baseline for Knowledge-Based Visual Question Answering","date":"2023-10-20","arxiv_id":"2310.13570","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":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-simple-baseline-for-knowledge-based-visual#ran","syntology_url":"https://syntology.ai/paper/2310.13570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13570"}}}},{"paper":"/paper/prompting-large-language-models-with-answer","slug":"prompting-large-language-models-with-answer","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","date":"2023-03-03","arxiv_id":"2303.01903","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["milvlg/prophet"],"state":"official (archive's flag): 6 ran","n_ran":6,"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/prompting-large-language-models-with-answer#ran","syntology_url":"https://syntology.ai/paper/2303.01903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01903"}}}},{"paper":"/paper/promptcap-prompt-guided-task-aware-image","slug":"promptcap-prompt-guided-task-aware-image","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","date":"2022-11-15","arxiv_id":"2211.09699","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlc-bert-visual-question-answering-with","slug":"vlc-bert-visual-question-answering-with","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","date":"2022-10-24","arxiv_id":"2210.13626","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["aditya10/vlc-bert"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlc-bert-visual-question-answering-with#ran","syntology_url":"https://syntology.ai/paper/2210.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13626"}}}},{"paper":"/paper/webly-supervised-concept-expansion-for","slug":"webly-supervised-concept-expansion-for","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","date":"2022-02-04","arxiv_id":"2202.02317","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/krisp-integrating-implicit-and-symbolic","slug":"krisp-integrating-implicit-and-symbolic","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","date":"2020-12-20","arxiv_id":"2012.11014","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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":1,"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/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","rows_on_this_dataset":3,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":24,"pointer_only_for_licence":34,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}}}},{"paper":"/paper/pythia-v01-the-winning-entry-to-the-vqa","slug":"pythia-v01-the-winning-entry-to-the-vqa","title":"Pythia v0.1: the Winning Entry to the VQA Challenge 2018","date":"2018-07-26","arxiv_id":"1807.09956","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["facebookresearch/pythia"],"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":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pythia-v01-the-winning-entry-to-the-vqa#ran","syntology_url":"https://syntology.ai/paper/1807.09956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09956"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"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/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/omni-smola-boosting-generalist-multimodal","slug":"omni-smola-boosting-generalist-multimodal","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","date":"2023-12-01","arxiv_id":"2312.00968","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/boosting-the-power-of-small-multimodal","slug":"boosting-the-power-of-small-multimodal","title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","date":"2023-11-23","arxiv_id":"2311.14109","rows_on_this_dataset":1,"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":["chengtan9907/mc-cot"],"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/boosting-the-power-of-small-multimodal#ran","syntology_url":"https://syntology.ai/paper/2311.14109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14109"}}}},{"paper":"/paper/a-simple-baseline-for-knowledge-based-visual","slug":"a-simple-baseline-for-knowledge-based-visual","title":"A Simple Baseline for Knowledge-Based Visual Question Answering","date":"2023-10-20","arxiv_id":"2310.13570","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":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-simple-baseline-for-knowledge-based-visual#ran","syntology_url":"https://syntology.ai/paper/2310.13570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13570"}}}},{"paper":"/paper/prompting-large-language-models-with-answer","slug":"prompting-large-language-models-with-answer","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","date":"2023-03-03","arxiv_id":"2303.01903","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["milvlg/prophet"],"state":"official (archive's flag): 6 ran","n_ran":6,"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/prompting-large-language-models-with-answer#ran","syntology_url":"https://syntology.ai/paper/2303.01903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01903"}}}},{"paper":"/paper/promptcap-prompt-guided-task-aware-image","slug":"promptcap-prompt-guided-task-aware-image","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","date":"2022-11-15","arxiv_id":"2211.09699","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlc-bert-visual-question-answering-with","slug":"vlc-bert-visual-question-answering-with","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","date":"2022-10-24","arxiv_id":"2210.13626","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["aditya10/vlc-bert"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlc-bert-visual-question-answering-with#ran","syntology_url":"https://syntology.ai/paper/2210.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13626"}}}},{"paper":"/paper/webly-supervised-concept-expansion-for","slug":"webly-supervised-concept-expansion-for","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","date":"2022-02-04","arxiv_id":"2202.02317","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/krisp-integrating-implicit-and-symbolic","slug":"krisp-integrating-implicit-and-symbolic","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","date":"2020-12-20","arxiv_id":"2012.11014","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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":1,"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/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","rows_on_this_dataset":3,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":24,"pointer_only_for_licence":34,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}}}},{"paper":"/paper/pythia-v01-the-winning-entry-to-the-vqa","slug":"pythia-v01-the-winning-entry-to-the-vqa","title":"Pythia v0.1: the Winning Entry to the VQA Challenge 2018","date":"2018-07-26","arxiv_id":"1807.09956","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["facebookresearch/pythia"],"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":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pythia-v01-the-winning-entry-to-the-vqa#ran","syntology_url":"https://syntology.ai/paper/1807.09956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09956"}}}}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/a-okvqa/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/a-okvqa/papers/ran/1","json":"/dataset/a-okvqa/papers/ran/1.json","rows":8}],"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":8,"samples_harvested":73,"samples_ran":32,"samples_constructed":10,"samples_ran_checked":22,"samples_ran_instrument_failed":10,"samples_unverified":41,"pointer_only_for_licence":43,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":5,"papers_where_every_run_was_an_instrument_failure":3,"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":3,"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-a-okvqa","since_archive":"/sota/visual-question-answering-on-a-okvqa#since-judged","papers_judged":3,"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":"f636cc628f351873ef7b8c0c55300fd2c0550b1bc8dddc3602fe76903bd21b71","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}