{"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/tvqa","name":"TVQA","full_name":"TVQA","description_markdown":"The **TVQA** dataset is a large-scale video dataset for video question answering. It is based on 6 popular TV shows (Friends, The Big Bang Theory, How I Met Your Mother, House M.D., Grey's Anatomy, Castle). It includes 152,545 QA pairs from 21,793 TV show clips. The QA pairs are split into the ratio of 8:1:1 for training, validation, and test sets. The TVQA dataset provides the sequence of video frames extracted at 3 FPS, the corresponding subtitles with the video clips, and the query consisting of a question and four answer candidates. Among the four answer candidates, there is only one correct answer.\r\n\r\nSource: [Two-stream Spatiotemporal Feature for Video QA Task](https://arxiv.org/abs/1907.05006)\r\nImage Source: [https://arxiv.org/abs/1809.01696](https://arxiv.org/abs/1809.01696)","description_withheld":null,"homepage":"http://tvqa.cs.unc.edu/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/tvqa-localized-compositional-video-question","title":"TVQA: Localized, Compositional Video Question Answering","first_author":"Jie Lei","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Video Question Answering","url":"/task/video-question-answering","datasets_with_task":"/datasets/task/video-question-answering"},{"name":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","datasets_with_task":"/datasets/task/zeroshot-video-question-answer"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TVQA"],"data_loaders":[],"num_papers_in_archive":146,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/zero-shot-video-question-answer-on-tvqa","task":"Zero-Shot Video Question Answer","dataset_variant":"TVQA","rows":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FrozenBiLM (with speech)","paper":"/paper/zero-shot-video-question-answering-via-frozen","metrics":{"Accuracy":"59.7"},"code_links":[{"title":"antoyang/FrozenBiLM","url":"https://github.com/antoyang/FrozenBiLM"},{"title":"klauscc/dam","url":"https://github.com/klauscc/dam"},{"title":"sts-vlcc/sts-vlcc","url":"https://github.com/sts-vlcc/sts-vlcc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-question-answering-on-tvqa","task":"Video Question Answering","dataset_variant":"TVQA","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LLaMA-VQA","paper":"/paper/large-language-models-are-temporal-and-causal","metrics":{"Accuracy":"82.2"},"code_links":[{"title":"mlvlab/Flipped-VQA","url":"https://github.com/mlvlab/Flipped-VQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-learning-on-tvqa","task":"Zero-Shot Learning","dataset_variant":"TVQA","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VideoChat2","paper":"/paper/mvbench-a-comprehensive-multi-modal-video","metrics":{"Accuracy":"40.6"},"code_links":[{"title":"opengvlab/ask-anything","url":"https://github.com/opengvlab/ask-anything"},{"title":"magic-research/PLLaVA","url":"https://github.com/magic-research/PLLaVA"},{"title":"bytedance/tarsier","url":"https://github.com/bytedance/tarsier"}]},"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":11,"of":11,"counts":{"papers_with_a_benchmark_row":11,"with_a_code_link":10,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","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":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}}}},{"paper":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","slug":"an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","date":"2024-03-27","arxiv_id":"2403.18406","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["imagegridworth/IG-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-image-grid-can-be-worth-a-video-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18406"}}}},{"paper":"/paper/mvbench-a-comprehensive-multi-modal-video","slug":"mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/ask-anything"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mvbench-a-comprehensive-multi-modal-video#ran","syntology_url":"https://syntology.ai/paper/2311.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17005"}}}},{"paper":"/paper/large-language-models-are-temporal-and-causal","slug":"large-language-models-are-temporal-and-causal","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","date":"2023-10-24","arxiv_id":"2310.15747","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["mlvlab/Flipped-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/large-language-models-are-temporal-and-causal#ran","syntology_url":"https://syntology.ai/paper/2310.15747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15747"}}}},{"paper":"/paper/self-chained-image-language-model-for-video-1","slug":"self-chained-image-language-model-for-video-1","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","date":"2023-05-11","arxiv_id":"2305.06988","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["yui010206/sevila"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-chained-image-language-model-for-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.06988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06988"}}}},{"paper":"/paper/vindlu-a-recipe-for-effective-video-and","slug":"vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","date":"2022-12-09","arxiv_id":"2212.05051","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":1,"code_links":2,"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":0,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/zero-shot-video-question-answering-via-frozen","slug":"zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","arxiv_id":"2206.08155","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":14,"samples_constructed":9,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":20,"pointer_only_for_licence":1,"official":{"repos":["antoyang/FrozenBiLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zero-shot-video-question-answering-via-frozen#ran","syntology_url":"https://syntology.ai/paper/2206.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08155"}}}},{"paper":"/paper/iperceive-applying-common-sense-reasoning-to-1","slug":"iperceive-applying-common-sense-reasoning-to-1","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","date":"2020-11-16","arxiv_id":"2011.07735","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}}}},{"paper":"/paper/tvqa-spatio-temporal-grounding-for-video","slug":"tvqa-spatio-temporal-grounding-for-video","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","date":"2019-04-25","arxiv_id":"1904.11574","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["jayleicn/TVQA-PLUS","jayleicn/TVQAplus"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tvqa-spatio-temporal-grounding-for-video#ran","syntology_url":"https://syntology.ai/paper/1904.11574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11574"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","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":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}}}},{"paper":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","slug":"an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","date":"2024-03-27","arxiv_id":"2403.18406","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["imagegridworth/IG-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-image-grid-can-be-worth-a-video-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18406"}}}},{"paper":"/paper/mvbench-a-comprehensive-multi-modal-video","slug":"mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/ask-anything"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mvbench-a-comprehensive-multi-modal-video#ran","syntology_url":"https://syntology.ai/paper/2311.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17005"}}}},{"paper":"/paper/large-language-models-are-temporal-and-causal","slug":"large-language-models-are-temporal-and-causal","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","date":"2023-10-24","arxiv_id":"2310.15747","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["mlvlab/Flipped-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/large-language-models-are-temporal-and-causal#ran","syntology_url":"https://syntology.ai/paper/2310.15747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15747"}}}},{"paper":"/paper/self-chained-image-language-model-for-video-1","slug":"self-chained-image-language-model-for-video-1","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","date":"2023-05-11","arxiv_id":"2305.06988","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["yui010206/sevila"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-chained-image-language-model-for-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.06988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06988"}}}},{"paper":"/paper/vindlu-a-recipe-for-effective-video-and","slug":"vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","date":"2022-12-09","arxiv_id":"2212.05051","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":1,"code_links":2,"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":0,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/zero-shot-video-question-answering-via-frozen","slug":"zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","arxiv_id":"2206.08155","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":14,"samples_constructed":9,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":20,"pointer_only_for_licence":1,"official":{"repos":["antoyang/FrozenBiLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zero-shot-video-question-answering-via-frozen#ran","syntology_url":"https://syntology.ai/paper/2206.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08155"}}}},{"paper":"/paper/iperceive-applying-common-sense-reasoning-to-1","slug":"iperceive-applying-common-sense-reasoning-to-1","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","date":"2020-11-16","arxiv_id":"2011.07735","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":8,"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}}}},{"paper":"/paper/tvqa-spatio-temporal-grounding-for-video","slug":"tvqa-spatio-temporal-grounding-for-video","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","date":"2019-04-25","arxiv_id":"1904.11574","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["jayleicn/TVQA-PLUS","jayleicn/TVQAplus"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tvqa-spatio-temporal-grounding-for-video#ran","syntology_url":"https://syntology.ai/paper/1904.11574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11574"}}}}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/tvqa/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/tvqa/papers/ran/1","json":"/dataset/tvqa/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":9,"samples_harvested":89,"samples_ran":57,"samples_constructed":9,"samples_ran_checked":39,"samples_ran_instrument_failed":18,"samples_unverified":32,"pointer_only_for_licence":20,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":6,"papers_where_every_run_was_an_instrument_failure":2,"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":"6970c5768fc6c0cd4b37f0dc5d45fdc3c75220b070fc249762c9613a8dbcd1fc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}