{"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/clevr-humans","name":"CLEVR-Humans","full_name":null,"description_markdown":"We collect  a  new  dataset  of  human-posed  free-form  natural  language  questions  about  CLEVR  images.    Many  of  these questions have out-of-vocabulary words and require reasoning skills that are absent from our model’s repertoire","description_withheld":null,"homepage":"https://cs.stanford.edu/people/jcjohns/iep/","introduced_date":"2017-05-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","first_author":"Justin Johnson","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":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CLEVR-Humans"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-clevr-humans","task":"Visual Question Answering (VQA)","dataset_variant":"CLEVR-Humans","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MDETR","paper":"/paper/mdetr-modulated-detection-for-end-to-end","metrics":{"Accuracy":"81.7"},"code_links":[{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"ashkamath/mdetr","url":"https://github.com/ashkamath/mdetr"},{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"},{"title":"b-faye/lightmdetr","url":"https://github.com/b-faye/lightmdetr"},{"title":"AleDella/mdter_eval","url":"https://github.com/AleDella/mdter_eval"}]},"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":5,"of":5,"counts":{"papers_with_a_benchmark_row":5,"with_a_code_link":5,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"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/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/neural-symbolic-vqa-disentangling-reasoning","slug":"neural-symbolic-vqa-disentangling-reasoning","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","date":"2018-10-04","arxiv_id":"1810.02338","rows_on_this_dataset":1,"code_links":2,"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":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-symbolic-vqa-disentangling-reasoning#ran","syntology_url":"https://syntology.ai/paper/1810.02338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02338"}}}},{"paper":"/paper/compositional-attention-networks-for-machine","slug":"compositional-attention-networks-for-machine","title":"Compositional Attention Networks for Machine Reasoning","date":"2018-03-08","arxiv_id":"1803.03067","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["stanfordnlp/mac-network"],"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/compositional-attention-networks-for-machine#ran","syntology_url":"https://syntology.ai/paper/1803.03067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03067"}}}},{"paper":"/paper/film-visual-reasoning-with-a-general","slug":"film-visual-reasoning-with-a-general","title":"FiLM: Visual Reasoning with a General Conditioning Layer","date":"2017-09-22","arxiv_id":"1709.07871","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":4,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["ethanjperez/film"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/film-visual-reasoning-with-a-general#ran","syntology_url":"https://syntology.ai/paper/1709.07871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.07871"}}}},{"paper":"/paper/inferring-and-executing-programs-for-visual","slug":"inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","date":"2017-05-10","arxiv_id":"1705.03633","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/clevr-iep"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/inferring-and-executing-programs-for-visual#ran","syntology_url":"https://syntology.ai/paper/1705.03633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.03633"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"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/neural-symbolic-vqa-disentangling-reasoning","slug":"neural-symbolic-vqa-disentangling-reasoning","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","date":"2018-10-04","arxiv_id":"1810.02338","rows_on_this_dataset":1,"code_links":2,"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":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-symbolic-vqa-disentangling-reasoning#ran","syntology_url":"https://syntology.ai/paper/1810.02338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02338"}}}},{"paper":"/paper/compositional-attention-networks-for-machine","slug":"compositional-attention-networks-for-machine","title":"Compositional Attention Networks for Machine Reasoning","date":"2018-03-08","arxiv_id":"1803.03067","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["stanfordnlp/mac-network"],"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/compositional-attention-networks-for-machine#ran","syntology_url":"https://syntology.ai/paper/1803.03067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03067"}}}},{"paper":"/paper/film-visual-reasoning-with-a-general","slug":"film-visual-reasoning-with-a-general","title":"FiLM: Visual Reasoning with a General Conditioning Layer","date":"2017-09-22","arxiv_id":"1709.07871","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":4,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["ethanjperez/film"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/film-visual-reasoning-with-a-general#ran","syntology_url":"https://syntology.ai/paper/1709.07871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.07871"}}}},{"paper":"/paper/inferring-and-executing-programs-for-visual","slug":"inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","date":"2017-05-10","arxiv_id":"1705.03633","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/clevr-iep"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/inferring-and-executing-programs-for-visual#ran","syntology_url":"https://syntology.ai/paper/1705.03633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.03633"}}}}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/clevr-humans/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/clevr-humans/papers/ran/1","json":"/dataset/clevr-humans/papers/ran/1.json","rows":5}],"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":5,"samples_harvested":36,"samples_ran":26,"samples_constructed":8,"samples_ran_checked":18,"samples_ran_instrument_failed":8,"samples_unverified":10,"pointer_only_for_licence":15,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":4,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"c02e9d6ba447fd879e72265d1e5c6a87c6b07bfd950bdc1c153bdae77a4d69ec","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}