{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DSQIMVHIOBJVTJ7RJYM3FSYA46","short_pith_number":"pith:DSQIMVHI","schema_version":"1.0","canonical_sha256":"1ca08654e8705359a7f14e19b2cb00e7adc0817c143846b26b511240e22dd80b","source":{"kind":"arxiv","id":"2111.08774","version":2},"attestation_state":"computed","paper":{"title":"Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frank Keller, Mirella Lapata, Pinelopi Papalampidi","submitted_at":"2021-11-16T20:50:52Z","abstract_excerpt":"Movie trailers perform multiple functions: they introduce viewers to the story, convey the mood and artistic style of the film, and encourage audiences to see the movie. These diverse functions make trailer creation a challenging endeavor. In this work, we focus on finding trailer moments in a movie, i.e., shots that could be potentially included in a trailer. We decompose this task into two subtasks: narrative structure identification and sentiment prediction. We model movies as graphs, where nodes are shots and edges denote semantic relations between them. We learn these relations using join"},"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":"2111.08774","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-16T20:50:52Z","cross_cats_sorted":[],"title_canon_sha256":"79579fa716a50ec4618e1cb665a0b4ca679620a70c739019ce2c4934dc279350","abstract_canon_sha256":"47ea566bcaab1e6286b6345bd8a23077e15846b7a4491e2eef16c7639f792ab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:04.739591Z","signature_b64":"p3yaNvqQueNPR0H4f3YBAd1xLbnLUvixFaeYt5iUPhuqsU7ZOAD8NH24JatxRxbrp/Nv6FWvJMlEN+Ll+d2jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca08654e8705359a7f14e19b2cb00e7adc0817c143846b26b511240e22dd80b","last_reissued_at":"2026-07-05T09:55:04.739141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:04.739141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frank Keller, Mirella Lapata, Pinelopi Papalampidi","submitted_at":"2021-11-16T20:50:52Z","abstract_excerpt":"Movie trailers perform multiple functions: they introduce viewers to the story, convey the mood and artistic style of the film, and encourage audiences to see the movie. These diverse functions make trailer creation a challenging endeavor. In this work, we focus on finding trailer moments in a movie, i.e., shots that could be potentially included in a trailer. We decompose this task into two subtasks: narrative structure identification and sentiment prediction. We model movies as graphs, where nodes are shots and edges denote semantic relations between them. We learn these relations using join"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08774","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.08774/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2111.08774","created_at":"2026-07-05T09:55:04.739197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08774v2","created_at":"2026-07-05T09:55:04.739197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08774","created_at":"2026-07-05T09:55:04.739197+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSQIMVHIOBJV","created_at":"2026-07-05T09:55:04.739197+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSQIMVHIOBJVTJ7R","created_at":"2026-07-05T09:55:04.739197+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSQIMVHI","created_at":"2026-07-05T09:55:04.739197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00239","citing_title":"Generating a Low-code Complete Workflow via Task Decomposition and RAG","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46","json":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46.json","graph_json":"https://pith.science/api/pith-number/DSQIMVHIOBJVTJ7RJYM3FSYA46/graph.json","events_json":"https://pith.science/api/pith-number/DSQIMVHIOBJVTJ7RJYM3FSYA46/events.json","paper":"https://pith.science/paper/DSQIMVHI"},"agent_actions":{"view_html":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46","download_json":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46.json","view_paper":"https://pith.science/paper/DSQIMVHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08774&json=true","fetch_graph":"https://pith.science/api/pith-number/DSQIMVHIOBJVTJ7RJYM3FSYA46/graph.json","fetch_events":"https://pith.science/api/pith-number/DSQIMVHIOBJVTJ7RJYM3FSYA46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46/action/storage_attestation","attest_author":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46/action/author_attestation","sign_citation":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46/action/citation_signature","submit_replication":"https://pith.science/pith/DSQIMVHIOBJVTJ7RJYM3FSYA46/action/replication_record"}},"created_at":"2026-07-05T09:55:04.739197+00:00","updated_at":"2026-07-05T09:55:04.739197+00:00"}