{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2DMLWPZO7FE64PQNWXGGFXNV4L","short_pith_number":"pith:2DMLWPZO","schema_version":"1.0","canonical_sha256":"d0d8bb3f2ef949ee3e0db5cc62ddb5e2f04b0c73e8c513bb0ce3f4ef66d746c8","source":{"kind":"arxiv","id":"2602.08711","version":3},"attestation_state":"computed","paper":{"title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifan Song, Kun Gai, Kun Ouyang, Lei Li, Lingpeng Kong, Linli Yao, Pengfei Wan, Qi Liu, Xinlong Chen, Xu Sun, Yaojie Zhang, Yuancheng Wei, Yuanxing Zhang, Yuanxin Liu, Ziyue Wang","submitted_at":"2026-02-09T14:21:58Z","abstract_excerpt":"This paper proposes Omni Dense Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit timestamps. To ensure dense semantic coverage, we introduce a six-dimensional structural schema to create \"script-like\" captions, enabling readers to vividly imagine the video content scene by scene, akin to a cinematographic screenplay. To facilitate research, we construct OmniDCBench, a high-quality, human-annotated benchmark, and propose SodaM, a unified metric that evaluates time-aware detailed descriptions while mitigating scene bounda"},"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":"2602.08711","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-09T14:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"ca5fe348d226157ccf59059202fc5625bff823e208579b38703d82fe5ebec1c9","abstract_canon_sha256":"a1e6865f046eeac5b9a0021af89641416a020c43de134c3a6b303e449d07bcd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:17.479939Z","signature_b64":"tkInmXz+KecfE7pWpwGy4EnHcZUBFWqs11sIydNKhxhUV5vA02qlls0+Z6iESMGypfyKkqsozPd3LTa8FOyGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0d8bb3f2ef949ee3e0db5cc62ddb5e2f04b0c73e8c513bb0ce3f4ef66d746c8","last_reissued_at":"2026-07-03T01:17:17.479489Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:17.479489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifan Song, Kun Gai, Kun Ouyang, Lei Li, Lingpeng Kong, Linli Yao, Pengfei Wan, Qi Liu, Xinlong Chen, Xu Sun, Yaojie Zhang, Yuancheng Wei, Yuanxing Zhang, Yuanxin Liu, Ziyue Wang","submitted_at":"2026-02-09T14:21:58Z","abstract_excerpt":"This paper proposes Omni Dense Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit timestamps. To ensure dense semantic coverage, we introduce a six-dimensional structural schema to create \"script-like\" captions, enabling readers to vividly imagine the video content scene by scene, akin to a cinematographic screenplay. To facilitate research, we construct OmniDCBench, a high-quality, human-annotated benchmark, and propose SodaM, a unified metric that evaluates time-aware detailed descriptions while mitigating scene bounda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08711","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.08711/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":"2602.08711","created_at":"2026-07-03T01:17:17.479546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.08711v3","created_at":"2026-07-03T01:17:17.479546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08711","created_at":"2026-07-03T01:17:17.479546+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DMLWPZO7FE6","created_at":"2026-07-03T01:17:17.479546+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DMLWPZO7FE64PQN","created_at":"2026-07-03T01:17:17.479546+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DMLWPZO","created_at":"2026-07-03T01:17:17.479546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.24636","citing_title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11102","citing_title":"OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04503","citing_title":"DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L","json":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L.json","graph_json":"https://pith.science/api/pith-number/2DMLWPZO7FE64PQNWXGGFXNV4L/graph.json","events_json":"https://pith.science/api/pith-number/2DMLWPZO7FE64PQNWXGGFXNV4L/events.json","paper":"https://pith.science/paper/2DMLWPZO"},"agent_actions":{"view_html":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L","download_json":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L.json","view_paper":"https://pith.science/paper/2DMLWPZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.08711&json=true","fetch_graph":"https://pith.science/api/pith-number/2DMLWPZO7FE64PQNWXGGFXNV4L/graph.json","fetch_events":"https://pith.science/api/pith-number/2DMLWPZO7FE64PQNWXGGFXNV4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L/action/storage_attestation","attest_author":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L/action/author_attestation","sign_citation":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L/action/citation_signature","submit_replication":"https://pith.science/pith/2DMLWPZO7FE64PQNWXGGFXNV4L/action/replication_record"}},"created_at":"2026-07-03T01:17:17.479546+00:00","updated_at":"2026-07-03T01:17:17.479546+00:00"}