{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DQH4FNN2DN6H4KTCZARN3ILOH2","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":"f54024f51fcc527acaf49a7d41c4a5c9a42f92edb9ec22412a8327a55ce4a107","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T15:51:48Z","title_canon_sha256":"e155c3f6fad7b0e8bd7504a2ac32b37d4f78557f3fda0114435c718005d48fab"},"schema_version":"1.0","source":{"id":"2411.07076","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07076","created_at":"2026-07-05T11:45:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07076v3","created_at":"2026-07-05T11:45:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07076","created_at":"2026-07-05T11:45:29Z"},{"alias_kind":"pith_short_12","alias_value":"DQH4FNN2DN6H","created_at":"2026-07-05T11:45:29Z"},{"alias_kind":"pith_short_16","alias_value":"DQH4FNN2DN6H4KTC","created_at":"2026-07-05T11:45:29Z"},{"alias_kind":"pith_short_8","alias_value":"DQH4FNN2","created_at":"2026-07-05T11:45:29Z"}],"graph_snapshots":[{"event_id":"sha256:54718196cdcb7a7f1aa6a30c400a2f3302059b09e257950ef65ae16b011a25ec","target":"graph","created_at":"2026-07-05T11:45:29Z","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/2411.07076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing large vision-language models (LVLMs) are largely limited to processing short, seconds-long videos and struggle with generating coherent descriptions for extended video spanning minutes or more. Long video description introduces new challenges, such as consistent character identification and plot-level descriptions incorporating both visual and audio information. To address these, we figure out audio-visual character identification, matching character names to each dialogue, as a key factor. We propose StoryTeller, a system for generating dense descriptions of long videos, incorporatin","authors_text":"Hanchong Zhang, Jianchao Wu, Ruicheng Le, Yichen He, Yuan Lin, Yuchen Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T15:51:48Z","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07076","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":"sha256:7e4c32857279cadf90689167d9507606554454a32d532947c8786f65146c83d1","target":"record","created_at":"2026-07-05T11:45:29Z","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":"f54024f51fcc527acaf49a7d41c4a5c9a42f92edb9ec22412a8327a55ce4a107","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T15:51:48Z","title_canon_sha256":"e155c3f6fad7b0e8bd7504a2ac32b37d4f78557f3fda0114435c718005d48fab"},"schema_version":"1.0","source":{"id":"2411.07076","kind":"arxiv","version":3}},"canonical_sha256":"1c0fc2b5ba1b7c7e2a62c822dda16e3e85c5fa7fb8c7103a3efc86ef971339e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c0fc2b5ba1b7c7e2a62c822dda16e3e85c5fa7fb8c7103a3efc86ef971339e1","first_computed_at":"2026-07-05T11:45:29.668990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:29.668990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cSeWF796VzkGFavVfFfgKbYbB7wMNP0gCyGVT24ENcUp6WCTSigw6HdSp3mQxwGDJJdtNaJZBmG5EnPavCI0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:29.669526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07076","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e4c32857279cadf90689167d9507606554454a32d532947c8786f65146c83d1","sha256:54718196cdcb7a7f1aa6a30c400a2f3302059b09e257950ef65ae16b011a25ec"],"state_sha256":"78472c7bb305d7faf319e4be977c2f309d8ae3526b916d4b80fb096e907d85f7"}