{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:P2JFCQSC2BOHPYUBC3YG6FEV5B","short_pith_number":"pith:P2JFCQSC","schema_version":"1.0","canonical_sha256":"7e92514242d05c77e28116f06f1495e868f8fb23aa87606776afa25482bbf379","source":{"kind":"arxiv","id":"1506.01273","version":3},"attestation_state":"computed","paper":{"title":"Summarization of Films and Documentaries Based on Subtitles and Scripts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"David Martins de Matos, Francisco Raposo, Lu\\'is Marujo, Marta Apar\\'icio, Paulo Figueiredo, Ricardo Ribeiro","submitted_at":"2015-06-03T15:07:14Z","abstract_excerpt":"We assess the performance of generic text summarization algorithms applied to films and documentaries, using the well-known behavior of summarization of news articles as reference. We use three datasets: (i) news articles, (ii) film scripts and subtitles, and (iii) documentary subtitles. Standard ROUGE metrics are used for comparing generated summaries against news abstracts, plot summaries, and synopses. We show that the best performing algorithms are LSA, for news articles and documentaries, and LexRank and Support Sets, for films. Despite the different nature of films and documentaries, the"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1506.01273","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-03T15:07:14Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d337ea342803e5348e75063751e24bc63fc707aba431b8227841e986078297f5","abstract_canon_sha256":"c9ff07d00ae06649b2524637edd323be7f02253a82c433bf0f1d971c264cf07c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:20.560963Z","signature_b64":"hvsuEMLdbtL1G6gspJ9ROYY3XPQNcbYZthvfja1ATKHG+m7PkiIJrTlEG+jt6An0FxTvcLBsx0LUjoaxDVSECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e92514242d05c77e28116f06f1495e868f8fb23aa87606776afa25482bbf379","last_reissued_at":"2026-05-18T01:19:20.560535Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:20.560535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Summarization of Films and Documentaries Based on Subtitles and Scripts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"David Martins de Matos, Francisco Raposo, Lu\\'is Marujo, Marta Apar\\'icio, Paulo Figueiredo, Ricardo Ribeiro","submitted_at":"2015-06-03T15:07:14Z","abstract_excerpt":"We assess the performance of generic text summarization algorithms applied to films and documentaries, using the well-known behavior of summarization of news articles as reference. We use three datasets: (i) news articles, (ii) film scripts and subtitles, and (iii) documentary subtitles. Standard ROUGE metrics are used for comparing generated summaries against news abstracts, plot summaries, and synopses. We show that the best performing algorithms are LSA, for news articles and documentaries, and LexRank and Support Sets, for films. Despite the different nature of films and documentaries, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01273","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1506.01273","created_at":"2026-05-18T01:19:20.560597+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.01273v3","created_at":"2026-05-18T01:19:20.560597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01273","created_at":"2026-05-18T01:19:20.560597+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2JFCQSC2BOH","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2JFCQSC2BOHPYUB","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2JFCQSC","created_at":"2026-05-18T12:29:34.919912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B","json":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B.json","graph_json":"https://pith.science/api/pith-number/P2JFCQSC2BOHPYUBC3YG6FEV5B/graph.json","events_json":"https://pith.science/api/pith-number/P2JFCQSC2BOHPYUBC3YG6FEV5B/events.json","paper":"https://pith.science/paper/P2JFCQSC"},"agent_actions":{"view_html":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B","download_json":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B.json","view_paper":"https://pith.science/paper/P2JFCQSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.01273&json=true","fetch_graph":"https://pith.science/api/pith-number/P2JFCQSC2BOHPYUBC3YG6FEV5B/graph.json","fetch_events":"https://pith.science/api/pith-number/P2JFCQSC2BOHPYUBC3YG6FEV5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B/action/storage_attestation","attest_author":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B/action/author_attestation","sign_citation":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B/action/citation_signature","submit_replication":"https://pith.science/pith/P2JFCQSC2BOHPYUBC3YG6FEV5B/action/replication_record"}},"created_at":"2026-05-18T01:19:20.560597+00:00","updated_at":"2026-05-18T01:19:20.560597+00:00"}