{"schema":"record/v1","id":"src_01M569MG7WV7BNG0A8248TSP6Y","type":"source","revision":1,"etag":"\"r1.s0\"","title":"SummScreen: A Dataset for Abstractive Screenplay Summarization","summary":null,"status":"active","body":{"text":"Repository contents (GitHub contents API): training/generation code, BPE files and scripts folder; no scraping scripts observed.","archived":false,"revision":{"ref":"v3 (submitted 6 Jun 2022); comments: ACL 2022","pinned":true,"source_url":"https://arxiv.org/abs/2104.07091"},"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"ACL 2022 dataset pairing TV series transcripts with human-written recaps (TVMegaSite, Wikipedia, TVmaze, ForeverDreaming), with entity-centric metrics and a finding that even strong models generate unfaithful plot facts. The only TV-episode corpus in this lane; code is public but no license is stated and the data sit on Google Drive.","source_type":"paper","availability":"available","dependencies":[],"source_owner":"Mingda Chen, Zewei Chu, Sam Wiseman, Kevin Gimpel","canonical_url":"https://arxiv.org/abs/2104.07091","next_check_at":"2026-11-16T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["No license anywhere in the sources read; third-party transcript copyright is unaddressed.","The repository holds code and links to Google Drive archives, not the data itself; the links are not stable sources.","Last push 2022-05-22; v1 of the abstract page is older than v3 (2022-06-06)."],"upstream_updated_at":"2022-06-06T19:02:30.000Z"},"categories":["T01"],"tags":["level:advanced","kind:dataset","task:tv-transcript-summarization","task:faithfulness"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://arxiv.org/abs/2104.07091","claim":"Abstract: SummScreen pairs TV series transcripts with human-written recaps.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2104.07091","claim":"Abstract: the authors propose two entity-centric evaluation metrics because characters are fundamental to TV series.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2104.07091","claim":"Abstract: both oracle and non-oracle models generate unfaithful facts.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://github.com/mingdachen/SummScreen","claim":"GitHub README: SummScreen was sourced from TVMegaSite, Wikipedia, TVmaze and ForeverDreaming.","locator":"Repository README","classification":"sourced_fact"},{"url":"https://api.github.com/repos/mingdachen/SummScreen","claim":"GitHub API reports no license for the repository (null).","locator":"evidence/github/mingdachen--summscreen.json","classification":"sourced_fact"},{"url":"https://api.github.com/repos/mingdachen/SummScreen","claim":"GitHub API: repository not archived; last push 2022-05-22.","locator":"evidence/github/mingdachen--summscreen.json","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"arXiv abs page links the arXiv non-exclusive distribution license 1.0 for the paper text; that license grants arXiv distribution rights and its third-party reuse terms were not read.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://arxiv.org/abs/2104.07091"],"model_training":"unknown","redistribution":"unknown"},{"notes":"No license file or license statement found in the repository; GitHub reports none.","hosting":"unknown","component":"code","license_id":null,"modification":"unknown","evidence_urls":["https://api.github.com/repos/mingdachen/SummScreen","https://github.com/mingdachen/SummScreen"],"model_training":"unknown","redistribution":"unknown"},{"notes":"Data are transcripts and recaps scraped from third-party TV sites; the README states no license and the archives are hosted on Google Drive links. Rights of the underlying transcripts and recaps are not addressed.","hosting":"unknown","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/mingdachen/SummScreen"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"Mingda Chen, Zewei Chu, Sam Wiseman, Kevin Gimpel","upstream_url":"https://arxiv.org/abs/2104.07091","imported_from":"content/seeds/research/wave-2/resources.jsonl#arxiv--2104-07091","import_batch_id":"l07-wave-2-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-wave-2-2026-10-17","original":{"id":"arxiv--2104-07091","name":"SummScreen: A Dataset for Abstractive Screenplay Summarization","tags":["level:advanced","kind:dataset","task:tv-transcript-summarization","task:faithfulness"],"notes":"Repository contents (GitHub contents API): training/generation code, BPE files and scripts folder; no scraping scripts observed.","rights":[{"notes":"arXiv abs page links the arXiv non-exclusive distribution license 1.0 for the paper text; that license grants arXiv distribution rights and its third-party reuse terms were not read.","hosting":"unknown","component":"documentation","license_id":null,"modification":"unknown","evidence_urls":["https://arxiv.org/abs/2104.07091"],"model_training":"unknown","redistribution":"unknown"},{"notes":"No license file or license statement found in the repository; GitHub reports none.","hosting":"unknown","component":"code","license_id":null,"modification":"unknown","evidence_urls":["https://api.github.com/repos/mingdachen/SummScreen","https://github.com/mingdachen/SummScreen"],"model_training":"unknown","redistribution":"unknown"},{"notes":"Data are transcripts and recaps scraped from third-party TV sites; the README states no license and the archives are hosted on Google Drive links. Rights of the underlying transcripts and recaps are not addressed.","hosting":"unknown","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/mingdachen/SummScreen"],"model_training":"unknown","redistribution":"unknown"}],"archived":false,"evidence":[{"url":"https://arxiv.org/abs/2104.07091","claim":"Abstract: SummScreen pairs TV series transcripts with human-written recaps.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2104.07091","claim":"Abstract: the authors propose two entity-centric evaluation metrics because characters are fundamental to TV series.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2104.07091","claim":"Abstract: both oracle and non-oracle models generate unfaithful facts.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://github.com/mingdachen/SummScreen","claim":"GitHub README: SummScreen was sourced from TVMegaSite, Wikipedia, TVmaze and ForeverDreaming.","locator":"Repository README","classification":"sourced_fact"},{"url":"https://api.github.com/repos/mingdachen/SummScreen","claim":"GitHub API reports no license for the repository (null).","locator":"evidence/github/mingdachen--summscreen.json","classification":"sourced_fact"},{"url":"https://api.github.com/repos/mingdachen/SummScreen","claim":"GitHub API: repository not archived; last push 2022-05-22.","locator":"evidence/github/mingdachen--summscreen.json","classification":"sourced_fact"}],"language":"en","revision":{"ref":"v3 (submitted 6 Jun 2022); comments: ACL 2022","pinned":true,"source_url":"https://arxiv.org/abs/2104.07091"},"checked_on":"2026-10-17","parent_url":null,"usefulness":"ACL 2022 dataset pairing TV series transcripts with human-written recaps (TVMegaSite, Wikipedia, TVmaze, ForeverDreaming), with entity-centric metrics and a finding that even strong models generate unfaithful plot facts. The only TV-episode corpus in this lane; code is public but no license is stated and the data sit on Google Drive.","source_type":"paper","category_ids":["T01"],"dependencies":[],"source_owner":"Mingda Chen, Zewei Chu, Sam Wiseman, Kevin Gimpel","canonical_url":"https://arxiv.org/abs/2104.07091","review_status":"reviewed","successor_url":null,"hardware_notes":null,"schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","known_limitations":["No license anywhere in the sources read; third-party transcript copyright is unaddressed.","The repository holds code and links to Google Drive archives, not the data itself; the links are not stable sources.","Last push 2022-05-22; v1 of the abstract page is older than v3 (2022-06-06)."],"upstream_updated_at":"2022-06-06T19:02:30Z","proposed_next_action":"inspect"},"collector":{"id":"arxiv--2104-07091","file":"research-results/L07/wave-2/w2-t01/resources.jsonl","kind":"resource","lane":"w2-t01","wave":"l07-wave-2-2026-10-17","collector":"Claude Sonnet 5.5, wave-2 lane w2-t01 (T01 series bibles, breakdowns, story development), dispatched by the L07 session, founder-run","merged_from":[],"original_id":"arxiv--2104-07091","review_reason":"L07 wave 2: lane w2-t01 accepted after validation (0 errors/0 warnings), automated metadata re-check (GitHub/arXiv/HTTP; 0 license/archive/rename mismatches) and mechanical quote verification (143/143 found); claim-to-quote sample and arXiv license links checked by L07.","review_status":"reviewed"},"observed_on":"2026-10-17","original_id":"arxiv--2104-07091","source_file":"content/seeds/research/wave-2/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"en","execution_status":"not_run","inspection_status":"source_inspected","proposed_next_action":"inspect"},"source_schema":"resource-candidate/0.1","original_sha256":"ee5c17175c38579b6a763b4740fadc6065823eb9eb546312263821e67a32a494","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569MG7WV7BNG0A8248TSP6Y","api_url":"https://veyrul.com/v1/records/src_01M569MG7WV7BNG0A8248TSP6Y","created_at":"2026-10-18T01:22:20.018Z","updated_at":"2026-10-18T01:22:20.018Z","last_activity_at":"2026-10-18T01:22:20.018Z"}