{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2DMLWPZO7FE64PQNWXGGFXNV4L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a1e6865f046eeac5b9a0021af89641416a020c43de134c3a6b303e449d07bcd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-09T14:21:58Z","title_canon_sha256":"ca5fe348d226157ccf59059202fc5625bff823e208579b38703d82fe5ebec1c9"},"schema_version":"1.0","source":{"id":"2602.08711","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08711","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08711v3","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08711","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"2DMLWPZO7FE6","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"2DMLWPZO7FE64PQN","created_at":"2026-07-03T01:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"2DMLWPZO","created_at":"2026-07-03T01:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:e5aed11b52a3a46c94cb02ee5f7713174beb62fe4f8b83fa50628c23ff3da7d5","target":"graph","created_at":"2026-07-03T01:17:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.08711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-09T14:21:58Z","title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08711","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2eb94041483e131d6f8fda4c67bf68910522e409ea396c80c171407c6ed9aec","target":"record","created_at":"2026-07-03T01:17:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a1e6865f046eeac5b9a0021af89641416a020c43de134c3a6b303e449d07bcd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-09T14:21:58Z","title_canon_sha256":"ca5fe348d226157ccf59059202fc5625bff823e208579b38703d82fe5ebec1c9"},"schema_version":"1.0","source":{"id":"2602.08711","kind":"arxiv","version":3}},"canonical_sha256":"d0d8bb3f2ef949ee3e0db5cc62ddb5e2f04b0c73e8c513bb0ce3f4ef66d746c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0d8bb3f2ef949ee3e0db5cc62ddb5e2f04b0c73e8c513bb0ce3f4ef66d746c8","first_computed_at":"2026-07-03T01:17:17.479489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:17.479489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tkInmXz+KecfE7pWpwGy4EnHcZUBFWqs11sIydNKhxhUV5vA02qlls0+Z6iESMGypfyKkqsozPd3LTa8FOyGBg==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:17.479939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.08711","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2eb94041483e131d6f8fda4c67bf68910522e409ea396c80c171407c6ed9aec","sha256:e5aed11b52a3a46c94cb02ee5f7713174beb62fe4f8b83fa50628c23ff3da7d5"],"state_sha256":"cc30717d6c6c3cac791920d156a97b5fa19f3c3e19d24365fe436cf47da0a6c6"}