{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FZSCVA4KDSETMIGGL6ZY5NXHDX","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":"f49f9157ac748c9cce5ed52561bd3fe6acfdcb9b609bdaf30a187a69fd63fb0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:44:09Z","title_canon_sha256":"9f56e7755f8e78645bd304f65710e440761fdf660b43350143b7a27ad5f24800"},"schema_version":"1.0","source":{"id":"2310.19773","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19773","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19773v1","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19773","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"FZSCVA4KDSET","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"FZSCVA4KDSETMIGG","created_at":"2026-07-05T07:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"FZSCVA4K","created_at":"2026-07-05T07:06:54Z"}],"graph_snapshots":[{"event_id":"sha256:299e3f93fdecd382919ad9a2db721336f23e428d577f35e7d6daf0822593a89d","target":"graph","created_at":"2026-07-05T07:06:54Z","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/2310.19773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MM-VID, an integrated system that harnesses the capabilities of GPT-4V, combined with specialized tools in vision, audio, and speech, to facilitate advanced video understanding. MM-VID is designed to address the challenges posed by long-form videos and intricate tasks such as reasoning within hour-long content and grasping storylines spanning multiple episodes. MM-VID uses a video-to-script generation with GPT-4V to transcribe multimodal elements into a long textual script. The generated script details character movements, actions, expressions, and dialogues, paving the way for larg","authors_text":"Ce Liu, Chung-Ching Lin, Ehsan Azarnasab, Faisal Ahmed, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Lin Liang, Yumao Lu, Zhengyuan Yang, Zicheng Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:44:09Z","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19773","kind":"arxiv","version":1},"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:cd6907d59a344a52c034ee7e6cfdb0dcde278c3f48da58504b3e26c3265aa6bf","target":"record","created_at":"2026-07-05T07:06:54Z","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":"f49f9157ac748c9cce5ed52561bd3fe6acfdcb9b609bdaf30a187a69fd63fb0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T17:44:09Z","title_canon_sha256":"9f56e7755f8e78645bd304f65710e440761fdf660b43350143b7a27ad5f24800"},"schema_version":"1.0","source":{"id":"2310.19773","kind":"arxiv","version":1}},"canonical_sha256":"2e642a838a1c893620c65fb38eb6e71dd533d339fd07750f96206ef654cb1888","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e642a838a1c893620c65fb38eb6e71dd533d339fd07750f96206ef654cb1888","first_computed_at":"2026-07-05T07:06:54.915144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:54.915144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O4ZPLIJXqGsbL00FUrRsFfU3zyrnMioeJMhb//ZTHzeEPIJpx/jxbLJzmfXiD9TdSIkpRnGQG7W5RR5sk4XNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:54.915679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19773","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd6907d59a344a52c034ee7e6cfdb0dcde278c3f48da58504b3e26c3265aa6bf","sha256:299e3f93fdecd382919ad9a2db721336f23e428d577f35e7d6daf0822593a89d"],"state_sha256":"8e2a0afd8d970331d15f70a2e58bbb5f850611e903868f3a714fbebb1ffd02d9"}