{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5GGSPYKQK5ENH5WZCTOKTJBDLS","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":"a0bc1e6598520be442e644c73cdcb4a052fd88afc2967b669ca64646a05ef803","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T17:09:52Z","title_canon_sha256":"7d1d9c8160ab0de15f7bdccc785ac10c1f98ab5565871b27cc8c3bd6dc7a8263"},"schema_version":"1.0","source":{"id":"2312.02051","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02051","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02051v2","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02051","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"pith_short_12","alias_value":"5GGSPYKQK5EN","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"pith_short_16","alias_value":"5GGSPYKQK5ENH5WZ","created_at":"2026-07-05T08:01:35Z"},{"alias_kind":"pith_short_8","alias_value":"5GGSPYKQ","created_at":"2026-07-05T08:01:35Z"}],"graph_snapshots":[{"event_id":"sha256:77d4a1b8bf266d3cb47dd6d2af21c1545d551fd25d5d8b10ffe487bc33d3ce54","target":"graph","created_at":"2026-07-05T08:01:35Z","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/2312.02051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work proposes TimeChat, a time-sensitive multimodal large language model specifically designed for long video understanding. Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds visual content with the timestamp of each frame, and (2) a sliding video Q-Former that produces a video token sequence of varying lengths to accommodate videos of various durations. Additionally, we construct an instruction-tuning dataset, encompassing 6 tasks and a total of 125K instances, to further enhance TimeChat's instruction-following performance. Experi","authors_text":"Linli Yao, Lu Hou, Shicheng Li, Shuhuai Ren, Xu Sun","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T17:09:52Z","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02051","kind":"arxiv","version":2},"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:f54750a796dc28677688c65dc2c36a475042d2ad6577d5f87517517f44c86507","target":"record","created_at":"2026-07-05T08:01:35Z","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":"a0bc1e6598520be442e644c73cdcb4a052fd88afc2967b669ca64646a05ef803","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T17:09:52Z","title_canon_sha256":"7d1d9c8160ab0de15f7bdccc785ac10c1f98ab5565871b27cc8c3bd6dc7a8263"},"schema_version":"1.0","source":{"id":"2312.02051","kind":"arxiv","version":2}},"canonical_sha256":"e98d27e1505748d3f6d914dca9a4235c81ca1d58698c694eeae31ec90a97ce4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e98d27e1505748d3f6d914dca9a4235c81ca1d58698c694eeae31ec90a97ce4f","first_computed_at":"2026-07-05T08:01:35.247095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:35.247095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PBq/b1r8efsbmCJNqK+xpp06mu1BzvVnT5ueKN+bs5ztDr5Y4PEuDrIkwEx4U3hn0xFNQEvFqMcdbMf25KY3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:35.247609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02051","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f54750a796dc28677688c65dc2c36a475042d2ad6577d5f87517517f44c86507","sha256:77d4a1b8bf266d3cb47dd6d2af21c1545d551fd25d5d8b10ffe487bc33d3ce54"],"state_sha256":"41ed52f4503bbe8c760836c1a87149fe457c74f0a5f8c5dcde5bae7a8b832b07"}