{"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/vcr","name":"VCR","full_name":"Visual Commonsense Reasoning","description_markdown":"**Visual Commonsense Reasoning** (**VCR**) is a large-scale dataset for cognition-level visual understanding. Given a challenging question about an image, machines need to present two sub-tasks: answer correctly and provide a rationale justifying its answer. The VCR dataset contains over 212K (training), 26K (validation) and 25K (testing) questions, answers and rationales derived from 110K movie scenes.\r\n\r\nSource: [Visual Commonsense R-CNN](https://arxiv.org/abs/2002.12204)\r\nImage Source: [From Recognition to Cognition: Visual Commonsense Reasoning](https://paperswithcode.com/paper/from-recognition-to-cognition-visual/)","description_withheld":null,"homepage":"https://visualcommonsense.com/","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/from-recognition-to-cognition-visual","title":"From Recognition to Cognition: Visual Commonsense Reasoning","first_author":"Rowan Zellers","url":null},"license":{"name":"Custom","url":"https://visualcommonsense.com/license/"},"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"},{"name":"Visual Commonsense Reasoning","url":"/task/visual-commonsense-reasoning","datasets_with_task":"/datasets/task/visual-commonsense-reasoning"},{"name":"Explanation Generation","url":"/task/explanation-generation","datasets_with_task":"/datasets/task/explanation-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VCR","VCR (QA-R) test","VCR (QA-R) dev","VCR (Q-AR) test","VCR (Q-AR) dev","VCR (Q-A) test","VCR (Q-A) dev"],"data_loaders":[],"num_papers_in_archive":179,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-vcr-q-a-test","task":"Visual Question Answering (VQA)","dataset_variant":"VCR (Q-A) test","rows":11,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT4RoI","paper":"/paper/gpt4roi-instruction-tuning-large-language","metrics":{"Accuracy":"89.4"},"code_links":[{"title":"jshilong/gpt4roi","url":"https://github.com/jshilong/gpt4roi"},{"title":"sunsmarterjie/chatterbox","url":"https://github.com/sunsmarterjie/chatterbox"},{"title":"qiujihao19/artemis","url":"https://github.com/qiujihao19/artemis"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vcr-qa-r-test","task":"Visual Question Answering (VQA)","dataset_variant":"VCR (QA-R) test","rows":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT4RoI","paper":"/paper/gpt4roi-instruction-tuning-large-language","metrics":{"Accuracy":"91.0"},"code_links":[{"title":"jshilong/gpt4roi","url":"https://github.com/jshilong/gpt4roi"},{"title":"sunsmarterjie/chatterbox","url":"https://github.com/sunsmarterjie/chatterbox"},{"title":"qiujihao19/artemis","url":"https://github.com/qiujihao19/artemis"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vcr-q-ar-test","task":"Visual Question Answering (VQA)","dataset_variant":"VCR (Q-AR) test","rows":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT4RoI","paper":"/paper/gpt4roi-instruction-tuning-large-language","metrics":{"Accuracy":"81.6"},"code_links":[{"title":"jshilong/gpt4roi","url":"https://github.com/jshilong/gpt4roi"},{"title":"sunsmarterjie/chatterbox","url":"https://github.com/sunsmarterjie/chatterbox"},{"title":"qiujihao19/artemis","url":"https://github.com/qiujihao19/artemis"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vcr-q-a-dev","task":"Visual Question Answering (VQA)","dataset_variant":"VCR (Q-A) dev","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VL-BERTLARGE","paper":"/paper/vl-bert-pre-training-of-generic-visual","metrics":{"Accuracy":"75.5"},"code_links":[{"title":"jackroos/VL-BERT","url":"https://github.com/jackroos/VL-BERT"},{"title":"ImperialNLP/BertGen","url":"https://github.com/ImperialNLP/BertGen"},{"title":"jules-samaran/vl-bert","url":"https://github.com/jules-samaran/vl-bert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vcr-q-ar-dev","task":"Visual Question Answering (VQA)","dataset_variant":"VCR (Q-AR) dev","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VL-BERTLARGE","paper":"/paper/vl-bert-pre-training-of-generic-visual","metrics":{"Accuracy":"58.9"},"code_links":[{"title":"jackroos/VL-BERT","url":"https://github.com/jackroos/VL-BERT"},{"title":"ImperialNLP/BertGen","url":"https://github.com/ImperialNLP/BertGen"},{"title":"jules-samaran/vl-bert","url":"https://github.com/jules-samaran/vl-bert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vcr-qa-r-dev","task":"Visual Question Answering (VQA)","dataset_variant":"VCR (QA-R) dev","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VL-BERTLARGE","paper":"/paper/vl-bert-pre-training-of-generic-visual","metrics":{"Accuracy":"77.9"},"code_links":[{"title":"jackroos/VL-BERT","url":"https://github.com/jackroos/VL-BERT"},{"title":"ImperialNLP/BertGen","url":"https://github.com/ImperialNLP/BertGen"},{"title":"jules-samaran/vl-bert","url":"https://github.com/jules-samaran/vl-bert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/explanation-generation-on-vcr","task":"Explanation Generation","dataset_variant":"VCR","rows":2,"metrics":["Human Explanation Rating"],"first_row_in_archive_order":{"model":"OFA-X-MT","paper":"/paper/harnessing-the-power-of-multi-task","metrics":{"Human Explanation Rating":"77.3"},"code_links":[{"title":"ofa-x/ofa-x","url":"https://github.com/ofa-x/ofa-x"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-commonsense-reasoning-on-vcr-q-a-dev","task":"Visual Commonsense Reasoning","dataset_variant":"VCR (Q-A) dev","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper":"/paper/pevl-position-enhanced-pre-training-and","metrics":{"Accuracy":"75.1"},"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/visual-commonsense-reasoning-on-vcr-q-a-test","task":"Visual Commonsense Reasoning","dataset_variant":"VCR (Q-A) test","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper":"/paper/pevl-position-enhanced-pre-training-and","metrics":{"Accuracy":"76.0"},"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/visual-commonsense-reasoning-on-vcr-q-ar-dev","task":"Visual Commonsense Reasoning","dataset_variant":"VCR (Q-AR) dev","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper":"/paper/pevl-position-enhanced-pre-training-and","metrics":{"Accuracy":"57.8"},"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/visual-commonsense-reasoning-on-vcr-q-ar-test","task":"Visual Commonsense Reasoning","dataset_variant":"VCR (Q-AR) test","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper":"/paper/pevl-position-enhanced-pre-training-and","metrics":{"Accuracy":"58.6"},"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/visual-commonsense-reasoning-on-vcr-qa-r-dev","task":"Visual Commonsense Reasoning","dataset_variant":"VCR (QA-R) dev","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper":"/paper/pevl-position-enhanced-pre-training-and","metrics":{"Accuracy":"76.4"},"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/visual-commonsense-reasoning-on-vcr-qa-r-test","task":"Visual Commonsense Reasoning","dataset_variant":"VCR (QA-R) test","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PEVL","paper":"/paper/pevl-position-enhanced-pre-training-and","metrics":{"Accuracy":"76.7"},"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"}],"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":10,"of":10,"counts":{"papers_with_a_benchmark_row":10,"with_a_code_link":7,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":10,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"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/gpt4roi-instruction-tuning-large-language","slug":"gpt4roi-instruction-tuning-large-language","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","date":"2023-07-07","arxiv_id":"2307.03601","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":5,"official":{"repos":["jshilong/gpt4roi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt4roi-instruction-tuning-large-language#ran","syntology_url":"https://syntology.ai/paper/2307.03601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03601"}}}},{"paper":"/paper/harnessing-the-power-of-multi-task","slug":"harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","arxiv_id":"2212.04231","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["ofa-x/ofa-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}}}},{"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":6,"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/multimodal-adaptive-distillation-for","slug":"multimodal-adaptive-distillation-for","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","date":"2022-04-22","arxiv_id":"2204.10496","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":10,"pointer_only_for_licence":0,"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}}}},{"paper":"/paper/kvl-bert-knowledge-enhanced-visual-and","slug":"kvl-bert-knowledge-enhanced-visual-and","title":"KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning","date":"2020-12-13","arxiv_id":"2012.07000","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/ernie-vil-knowledge-enhanced-vision-language","slug":"ernie-vil-knowledge-enhanced-vision-language","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","date":"2020-06-30","arxiv_id":"2006.16934","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","rows_on_this_dataset":5,"code_links":7,"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":2,"official":{"repos":["ChenRocks/UNITER"],"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/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}}}},{"paper":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","rows_on_this_dataset":9,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jackroos/VL-BERT"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}}}},{"paper":"/paper/visualbert-a-simple-and-performant-baseline","slug":"visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","date":"2019-08-09","arxiv_id":"1908.03557","rows_on_this_dataset":6,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":4,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visualbert-a-simple-and-performant-baseline#ran","syntology_url":"https://syntology.ai/paper/1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/gpt4roi-instruction-tuning-large-language","slug":"gpt4roi-instruction-tuning-large-language","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","date":"2023-07-07","arxiv_id":"2307.03601","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":5,"official":{"repos":["jshilong/gpt4roi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt4roi-instruction-tuning-large-language#ran","syntology_url":"https://syntology.ai/paper/2307.03601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03601"}}}},{"paper":"/paper/harnessing-the-power-of-multi-task","slug":"harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","arxiv_id":"2212.04231","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["ofa-x/ofa-x"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/harnessing-the-power-of-multi-task#ran","syntology_url":"https://syntology.ai/paper/2212.04231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04231"}}}},{"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":6,"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/multimodal-adaptive-distillation-for","slug":"multimodal-adaptive-distillation-for","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","date":"2022-04-22","arxiv_id":"2204.10496","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":10,"pointer_only_for_licence":0,"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}}}},{"paper":"/paper/kvl-bert-knowledge-enhanced-visual-and","slug":"kvl-bert-knowledge-enhanced-visual-and","title":"KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning","date":"2020-12-13","arxiv_id":"2012.07000","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/ernie-vil-knowledge-enhanced-vision-language","slug":"ernie-vil-knowledge-enhanced-vision-language","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","date":"2020-06-30","arxiv_id":"2006.16934","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","rows_on_this_dataset":5,"code_links":7,"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":2,"official":{"repos":["ChenRocks/UNITER"],"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/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}}}},{"paper":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","rows_on_this_dataset":9,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jackroos/VL-BERT"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}}}},{"paper":"/paper/visualbert-a-simple-and-performant-baseline","slug":"visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","date":"2019-08-09","arxiv_id":"1908.03557","rows_on_this_dataset":6,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":4,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visualbert-a-simple-and-performant-baseline#ran","syntology_url":"https://syntology.ai/paper/1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}}}}],"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/dataset/vcr/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/vcr/papers/ran/1","json":"/dataset/vcr/papers/ran/1.json","rows":7}],"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":7,"samples_harvested":45,"samples_ran":25,"samples_constructed":4,"samples_ran_checked":17,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":19,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":7,"papers_with_a_run_with_no_instrument_failure":6,"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":"aac8a2aee4ca97000201ea4a1c0253a7a25706c4b3fd6fd10da36f3701fc5e10","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}