{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:S76EFBZLPAC4HB2ZTLNJIZVEN5","short_pith_number":"pith:S76EFBZL","schema_version":"1.0","canonical_sha256":"97fc42872b7805c387599ada9466a46f4602c320076fb3f02f52c54b3085cee9","source":{"kind":"arxiv","id":"2005.04208","version":2},"attestation_state":"computed","paper":{"title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Brown, Andrew Zisserman, Arsha Nagrani, Max Bain","submitted_at":"2020-05-08T17:55:03Z","abstract_excerpt":"Our objective in this work is long range understanding of the narrative structure of movies. Instead of considering the entire movie, we propose to learn from the `key scenes' of the movie, providing a condensed look at the full storyline. To this end, we make the following three contributions: (i) We create the Condensed Movies Dataset (CMD) consisting of the key scenes from over 3K movies: each key scene is accompanied by a high level semantic description of the scene, character face-tracks, and metadata about the movie. The dataset is scalable, obtained automatically from YouTube, and is fr"},"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":"2005.04208","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-08T17:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"d15db7eb17e16ecf4a02b07f55363b69327ec77262bc108ccb689c7af39f350e","abstract_canon_sha256":"282e840f40b7e81704961c0fdb2769810b8138c3d4bea6f13b2b852df04a7642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:26.911667Z","signature_b64":"gGyUmF9sbAYosLTG7sDR1KvlFmj4x+VC3hAUEuIkHiaIirwbM0k2W4zoA3Cw/D/60Xczsiiqytx9bH/xpG68Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97fc42872b7805c387599ada9466a46f4602c320076fb3f02f52c54b3085cee9","last_reissued_at":"2026-07-05T01:45:26.911230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:26.911230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Brown, Andrew Zisserman, Arsha Nagrani, Max Bain","submitted_at":"2020-05-08T17:55:03Z","abstract_excerpt":"Our objective in this work is long range understanding of the narrative structure of movies. Instead of considering the entire movie, we propose to learn from the `key scenes' of the movie, providing a condensed look at the full storyline. To this end, we make the following three contributions: (i) We create the Condensed Movies Dataset (CMD) consisting of the key scenes from over 3K movies: each key scene is accompanied by a high level semantic description of the scene, character face-tracks, and metadata about the movie. The dataset is scalable, obtained automatically from YouTube, and is fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04208","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/2005.04208/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":"2005.04208","created_at":"2026-07-05T01:45:26.911289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.04208v2","created_at":"2026-07-05T01:45:26.911289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04208","created_at":"2026-07-05T01:45:26.911289+00:00"},{"alias_kind":"pith_short_12","alias_value":"S76EFBZLPAC4","created_at":"2026-07-05T01:45:26.911289+00:00"},{"alias_kind":"pith_short_16","alias_value":"S76EFBZLPAC4HB2Z","created_at":"2026-07-05T01:45:26.911289+00:00"},{"alias_kind":"pith_short_8","alias_value":"S76EFBZL","created_at":"2026-07-05T01:45:26.911289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01900","citing_title":"Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5","json":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5.json","graph_json":"https://pith.science/api/pith-number/S76EFBZLPAC4HB2ZTLNJIZVEN5/graph.json","events_json":"https://pith.science/api/pith-number/S76EFBZLPAC4HB2ZTLNJIZVEN5/events.json","paper":"https://pith.science/paper/S76EFBZL"},"agent_actions":{"view_html":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5","download_json":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5.json","view_paper":"https://pith.science/paper/S76EFBZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.04208&json=true","fetch_graph":"https://pith.science/api/pith-number/S76EFBZLPAC4HB2ZTLNJIZVEN5/graph.json","fetch_events":"https://pith.science/api/pith-number/S76EFBZLPAC4HB2ZTLNJIZVEN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5/action/storage_attestation","attest_author":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5/action/author_attestation","sign_citation":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5/action/citation_signature","submit_replication":"https://pith.science/pith/S76EFBZLPAC4HB2ZTLNJIZVEN5/action/replication_record"}},"created_at":"2026-07-05T01:45:26.911289+00:00","updated_at":"2026-07-05T01:45:26.911289+00:00"}