{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D3C4YGCU3KLZ44ITEVVKHQY4H2","short_pith_number":"pith:D3C4YGCU","schema_version":"1.0","canonical_sha256":"1ec5cc1854da979e7113256aa3c31c3eb8f6df571054b1ace3b73e8375cfdda5","source":{"kind":"arxiv","id":"2305.12140","version":2},"attestation_state":"computed","paper":{"title":"Movie101: A New Movie Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Anwen Hu, Liang Zhang, Qin Jin, Qi Zhang, Zihao Yue, Ziheng Wang","submitted_at":"2023-05-20T08:43:51Z","abstract_excerpt":"To help the visually impaired enjoy movies, automatic movie narrating systems are expected to narrate accurate, coherent, and role-aware plots when there are no speaking lines of actors. Existing works benchmark this challenge as a normal video captioning task via some simplifications, such as removing role names and evaluating narrations with ngram-based metrics, which makes it difficult for automatic systems to meet the needs of real application scenarios. To narrow this gap, we construct a large-scale Chinese movie benchmark, named Movie101. Closer to real scenarios, the Movie Clip Narratin"},"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":"2305.12140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-20T08:43:51Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"bbb58d08d7550afb64c4d38e89a8dfa062cfb245baa8593e8016757c83edb50f","abstract_canon_sha256":"b136eba413297afcfcad8b4b283b79dce62d1f8b692b8d7c6098d7023579f30a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:50.141216Z","signature_b64":"CC3EDnKSeiuKrCT7rCRs9Q0pVFaACLXzY22EAcgg4D8nIPwmpVH/Xl1HEHrBy0D9ZR9I5888PW9Um2WAHjDkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ec5cc1854da979e7113256aa3c31c3eb8f6df571054b1ace3b73e8375cfdda5","last_reissued_at":"2026-07-05T06:24:50.140845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:50.140845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Movie101: A New Movie Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Anwen Hu, Liang Zhang, Qin Jin, Qi Zhang, Zihao Yue, Ziheng Wang","submitted_at":"2023-05-20T08:43:51Z","abstract_excerpt":"To help the visually impaired enjoy movies, automatic movie narrating systems are expected to narrate accurate, coherent, and role-aware plots when there are no speaking lines of actors. Existing works benchmark this challenge as a normal video captioning task via some simplifications, such as removing role names and evaluating narrations with ngram-based metrics, which makes it difficult for automatic systems to meet the needs of real application scenarios. To narrow this gap, we construct a large-scale Chinese movie benchmark, named Movie101. Closer to real scenarios, the Movie Clip Narratin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12140","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/2305.12140/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":"2305.12140","created_at":"2026-07-05T06:24:50.140908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12140v2","created_at":"2026-07-05T06:24:50.140908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12140","created_at":"2026-07-05T06:24:50.140908+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3C4YGCU3KLZ","created_at":"2026-07-05T06:24:50.140908+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3C4YGCU3KLZ44IT","created_at":"2026-07-05T06:24:50.140908+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3C4YGCU","created_at":"2026-07-05T06:24:50.140908+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20163","citing_title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2","json":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2.json","graph_json":"https://pith.science/api/pith-number/D3C4YGCU3KLZ44ITEVVKHQY4H2/graph.json","events_json":"https://pith.science/api/pith-number/D3C4YGCU3KLZ44ITEVVKHQY4H2/events.json","paper":"https://pith.science/paper/D3C4YGCU"},"agent_actions":{"view_html":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2","download_json":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2.json","view_paper":"https://pith.science/paper/D3C4YGCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12140&json=true","fetch_graph":"https://pith.science/api/pith-number/D3C4YGCU3KLZ44ITEVVKHQY4H2/graph.json","fetch_events":"https://pith.science/api/pith-number/D3C4YGCU3KLZ44ITEVVKHQY4H2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2/action/storage_attestation","attest_author":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2/action/author_attestation","sign_citation":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2/action/citation_signature","submit_replication":"https://pith.science/pith/D3C4YGCU3KLZ44ITEVVKHQY4H2/action/replication_record"}},"created_at":"2026-07-05T06:24:50.140908+00:00","updated_at":"2026-07-05T06:24:50.140908+00:00"}