{"schema":"record/v1","id":"src_01M569MG6NKVHTZ24Y08BMV58V","type":"source","revision":1,"etag":"\"r1.s0\"","title":"MovieSum: An Abstractive Summarization Dataset for Movie Screenplays","summary":null,"status":"active","body":{"text":"HF dataset size about 477 MB per the card; not downloaded. A different HF dataset chuanli1013/MovieSum exists (derivative; not read).","archived":false,"revision":{"ref":"v1 (submitted 12 Aug 2024; only version); comments: ACL 2024 Findings","pinned":true,"source_url":"https://arxiv.org/abs/2408.06281"},"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"ACL 2024 Findings dataset of 2,200 movie screenplays paired with Wikipedia plot summaries, formatted to keep structural elements and keyed by IMDb IDs. Useful as a test bed for screenplay summarization; the card's CC BY-NC license and unstated screenplay provenance make reuse uncertain.","source_type":"paper","availability":"available","dependencies":[],"source_owner":"Rohit Saxena, Frank Keller (University of Edinburgh)","canonical_url":"https://arxiv.org/abs/2408.06281","next_check_at":"2026-11-16T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["Source and copyright status of the 2,200 screenplays are not stated on the card.","License appears in card body text but not in HF machine-readable metadata.","Movie screenplays only (not TV episodes)."],"upstream_updated_at":"2024-08-12T16:43:09.000Z"},"categories":["T01"],"tags":["level:advanced","kind:dataset","task:screenplay-summarization","format:json"],"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/2408.06281","claim":"Abstract: 2,200 movie screenplays accompanied by Wikipedia plot summaries.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2408.06281","claim":"Abstract: the authors manually formatted the screenplays to represent structural elements.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2408.06281","claim":"Abstract: metadata with IMDb IDs is provided.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://huggingface.co/datasets/rohitsaxena/MovieSum","claim":"HF dataset card states the license as Creative Commons Attribution Non Commercial 4.0.","locator":"HF dataset card, License section","classification":"sourced_fact"},{"url":"https://huggingface.co/datasets/rohitsaxena/MovieSum","claim":"HF dataset card describes 2,200 screenplays and their Wikipedia summaries.","locator":"HF dataset card","classification":"sourced_fact"},{"url":"https://huggingface.co/api/datasets/rohitsaxena/MovieSum","claim":"The HF API record for the dataset (read via the fetch tool) lists no license tag and no cardData, so the license appears only in the card body text.","locator":"HF API tags","classification":"inference"},{"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 shows a 'view license' link to Creative Commons Attribution 4.0 for the paper text; attribution required. Says nothing about datasets or code.","hosting":"permitted","component":"documentation","license_id":"CC-BY-4.0","modification":"permitted","evidence_urls":["https://arxiv.org/abs/2408.06281"],"model_training":"unknown","redistribution":"permitted"},{"notes":"Card body says 'Creative Commons Attribution Non Commercial 4.0' (non-commercial only; attribution). The card does not say where the screenplays were obtained and does not address the copyright of the screenplays themselves, only the authors' dataset; the HF API record has no license tag. Non-commercial terms restrict commercial model training.","hosting":"restricted","component":"dataset","license_id":"CC-BY-NC-4.0","modification":"restricted","evidence_urls":["https://huggingface.co/datasets/rohitsaxena/MovieSum"],"model_training":"restricted","redistribution":"restricted"}],"attribution":{"origin":"research_agent","upstream_owner":"Rohit Saxena, Frank Keller (University of Edinburgh)","upstream_url":"https://arxiv.org/abs/2408.06281","imported_from":"content/seeds/research/wave-2/resources.jsonl#arxiv--2408-06281","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--2408-06281","name":"MovieSum: An Abstractive Summarization Dataset for Movie Screenplays","tags":["level:advanced","kind:dataset","task:screenplay-summarization","format:json"],"notes":"HF dataset size about 477 MB per the card; not downloaded. A different HF dataset chuanli1013/MovieSum exists (derivative; not read).","rights":[{"notes":"arXiv abs page shows a 'view license' link to Creative Commons Attribution 4.0 for the paper text; attribution required. Says nothing about datasets or code.","hosting":"permitted","component":"documentation","license_id":"CC-BY-4.0","modification":"permitted","evidence_urls":["https://arxiv.org/abs/2408.06281"],"model_training":"unknown","redistribution":"permitted"},{"notes":"Card body says 'Creative Commons Attribution Non Commercial 4.0' (non-commercial only; attribution). The card does not say where the screenplays were obtained and does not address the copyright of the screenplays themselves, only the authors' dataset; the HF API record has no license tag. Non-commercial terms restrict commercial model training.","hosting":"restricted","component":"dataset","license_id":"CC-BY-NC-4.0","modification":"restricted","evidence_urls":["https://huggingface.co/datasets/rohitsaxena/MovieSum"],"model_training":"restricted","redistribution":"restricted"}],"archived":false,"evidence":[{"url":"https://arxiv.org/abs/2408.06281","claim":"Abstract: 2,200 movie screenplays accompanied by Wikipedia plot summaries.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2408.06281","claim":"Abstract: the authors manually formatted the screenplays to represent structural elements.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://arxiv.org/abs/2408.06281","claim":"Abstract: metadata with IMDb IDs is provided.","locator":"Abstract","classification":"upstream_claim"},{"url":"https://huggingface.co/datasets/rohitsaxena/MovieSum","claim":"HF dataset card states the license as Creative Commons Attribution Non Commercial 4.0.","locator":"HF dataset card, License section","classification":"sourced_fact"},{"url":"https://huggingface.co/datasets/rohitsaxena/MovieSum","claim":"HF dataset card describes 2,200 screenplays and their Wikipedia summaries.","locator":"HF dataset card","classification":"sourced_fact"},{"url":"https://huggingface.co/api/datasets/rohitsaxena/MovieSum","claim":"The HF API record for the dataset (read via the fetch tool) lists no license tag and no cardData, so the license appears only in the card body text.","locator":"HF API tags","classification":"inference"}],"language":"en","revision":{"ref":"v1 (submitted 12 Aug 2024; only version); comments: ACL 2024 Findings","pinned":true,"source_url":"https://arxiv.org/abs/2408.06281"},"checked_on":"2026-10-17","parent_url":null,"usefulness":"ACL 2024 Findings dataset of 2,200 movie screenplays paired with Wikipedia plot summaries, formatted to keep structural elements and keyed by IMDb IDs. Useful as a test bed for screenplay summarization; the card's CC BY-NC license and unstated screenplay provenance make reuse uncertain.","source_type":"paper","category_ids":["T01"],"dependencies":[],"source_owner":"Rohit Saxena, Frank Keller (University of Edinburgh)","canonical_url":"https://arxiv.org/abs/2408.06281","review_status":"reviewed","successor_url":null,"hardware_notes":null,"schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","known_limitations":["Source and copyright status of the 2,200 screenplays are not stated on the card.","License appears in card body text but not in HF machine-readable metadata.","Movie screenplays only (not TV episodes)."],"upstream_updated_at":"2024-08-12T16:43:09Z","proposed_next_action":"inspect"},"collector":{"id":"arxiv--2408-06281","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--2408-06281","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--2408-06281","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":"fc54c9b188e07f995753cf461088630476a782d4e8172d479d75c71a1a989679","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_01M569MG6NKVHTZ24Y08BMV58V","api_url":"https://veyrul.com/v1/records/src_01M569MG6NKVHTZ24Y08BMV58V","created_at":"2026-10-18T01:22:19.978Z","updated_at":"2026-10-18T01:22:19.978Z","last_activity_at":"2026-10-18T01:22:19.978Z"}