{"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/vidchapters-7m","name":"VidChapters-7M","full_name":null,"description_markdown":"VidChapters-7M is a dataset of 817K user-chaptered videos including 7M chapters in total. VidChapters-7M is automatically created from videos online in a scalable manner by scraping user-annotated chapters and hence without any additional manual annotation. It is designed for training and evaluating models for video chapter generation with or without ground-truth boundaries, and video chapter grounding, as well as for video-language pretraining.","description_withheld":null,"homepage":"https://antoyang.github.io/vidchapters.html","introduced_date":"2023-09-25","introduced_date_note":null,"introduced_by":null,"license":{"name":"MIT","url":"https://github.com/antoyang/VidChapters/blob/main/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Dense Video Captioning","url":"/task/dense-video-captioning","datasets_with_task":"/datasets/task/dense-video-captioning"},{"name":"Language-Based Temporal Localization","url":"/task/language-based-temporal-localization","datasets_with_task":"/datasets/task/language-based-temporal-localization"},{"name":"Video Chaptering","url":"/task/video-chaptering","datasets_with_task":"/datasets/task/video-chaptering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VidChapters-7M"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-based-temporal-localization-on","task":"Language-Based Temporal Localization","dataset_variant":"VidChapters-7M","rows":2,"metrics":["R1@.9","R@10s"],"first_row_in_archive_order":{"model":"ReVisionLLM","paper":"/paper/revisionllm-recursive-vision-language-model","metrics":{"R1@.9":"15.2"},"code_links":[{"title":"tanveer81/revisionllm","url":"https://github.com/tanveer81/revisionllm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-chaptering-on-vidchapters-7m","task":"Video Chaptering","dataset_variant":"VidChapters-7M","rows":2,"metrics":["P@5s","CIDEr","P@0.5","P@0.7","P@3s","R@0.5","R@0.7","R@3s","R@5s","SODA"],"first_row_in_archive_order":{"model":"Chapter-Llama","paper":"/paper/chapter-llama-efficient-chaptering-in-hour-1","metrics":{"P@5s":"52.0"},"code_links":[{"title":"lucas-ventura/chapter-llama","url":"https://github.com/lucas-ventura/chapter-llama"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/dense-video-captioning-on-vidchapters-7m","task":"Dense Video Captioning","dataset_variant":"VidChapters-7M","rows":1,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"Vid2Seq","paper":null,"metrics":{"CIDEr":"55.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-captioning-on-vidchapters-7m","task":"Video Captioning","dataset_variant":"VidChapters-7M","rows":1,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"Vid2Seq","paper":null,"metrics":{"CIDEr":"120.5"},"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":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/chapter-llama-efficient-chaptering-in-hour-1","slug":"chapter-llama-efficient-chaptering-in-hour-1","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","date":"2025-03-31","arxiv_id":"2504.00072","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revisionllm-recursive-vision-language-model","slug":"revisionllm-recursive-vision-language-model","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","date":"2024-11-22","arxiv_id":"2411.14901","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vidchapters-7m-video-chapters-at-scale","slug":"vidchapters-7m-video-chapters-at-scale","title":"VidChapters-7M: Video Chapters at Scale","date":"2023-09-25","arxiv_id":"2309.13952","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vidchapters-7m-video-chapters-at-scale#ran","syntology_url":"https://syntology.ai/paper/2309.13952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13952"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/chapter-llama-efficient-chaptering-in-hour-1","slug":"chapter-llama-efficient-chaptering-in-hour-1","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","date":"2025-03-31","arxiv_id":"2504.00072","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revisionllm-recursive-vision-language-model","slug":"revisionllm-recursive-vision-language-model","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","date":"2024-11-22","arxiv_id":"2411.14901","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vidchapters-7m-video-chapters-at-scale","slug":"vidchapters-7m-video-chapters-at-scale","title":"VidChapters-7M: Video Chapters at Scale","date":"2023-09-25","arxiv_id":"2309.13952","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vidchapters-7m-video-chapters-at-scale#ran","syntology_url":"https://syntology.ai/paper/2309.13952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13952"}}}}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/vidchapters-7m/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/vidchapters-7m/papers/ran/1","json":"/dataset/vidchapters-7m/papers/ran/1.json","rows":1}],"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":1,"samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"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":"02db7222fd5ea0d371ecdc6565d3548cabfea09abfa40b1518a164d34a4c33fb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}