{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OBXBUGYTGBJAEWHC7H4DJ46U57","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":"d69b29a37b500be13d32867d335316d6ee59c54d03b1c7e300f9b5bf071d0755","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T17:51:22Z","title_canon_sha256":"d963a97373c4c0a6948419196ba7495e3beea906063f3530040077103063c207"},"schema_version":"1.0","source":{"id":"2305.13292","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13292","created_at":"2026-07-05T06:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13292v2","created_at":"2026-07-05T06:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13292","created_at":"2026-07-05T06:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"OBXBUGYTGBJA","created_at":"2026-07-05T06:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"OBXBUGYTGBJAEWHC","created_at":"2026-07-05T06:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"OBXBUGYT","created_at":"2026-07-05T06:12:51Z"}],"graph_snapshots":[{"event_id":"sha256:6f33ff3ab72f087c83caf8e8e8921c4b091cb9e2e7e8cbec79f760d259786037","target":"graph","created_at":"2026-07-05T06:12:51Z","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/2305.13292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the exponential growth of video data, there is an urgent need for automated technology to analyze and comprehend video content. However, existing video understanding models are often task-specific and lack a comprehensive capability of handling diverse tasks. The success of large language models (LLMs) like GPT has demonstrated their impressive abilities in sequence causal reasoning. Building upon this insight, we propose a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs from natural language processing (NLP) for video sequence unders","authors_text":"Guo Chen, Jiahao Wang, Jilan Xu, Junting Pan, Limin Wang, Tong Lu, Yali Wang, Yifei Huang, Yin-Dong Zheng, Yi Wang, Yu Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T17:51:22Z","title":"VideoLLM: Modeling Video Sequence with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13292","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":"sha256:5ef65d58ec47ee6119c6475c53aed5736c46b578a6951632674ce905505e524f","target":"record","created_at":"2026-07-05T06:12:51Z","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":"d69b29a37b500be13d32867d335316d6ee59c54d03b1c7e300f9b5bf071d0755","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-22T17:51:22Z","title_canon_sha256":"d963a97373c4c0a6948419196ba7495e3beea906063f3530040077103063c207"},"schema_version":"1.0","source":{"id":"2305.13292","kind":"arxiv","version":2}},"canonical_sha256":"706e1a1b1330520258e2f9f834f3d4efcdcf20c5f62da36f70b2a0550e5024c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"706e1a1b1330520258e2f9f834f3d4efcdcf20c5f62da36f70b2a0550e5024c6","first_computed_at":"2026-07-05T06:12:51.388620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:51.388620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jUf/BE+ruV7jMmRlQVcuYfnSEZAhjaVPJ2vH/HFpmicFaGidjtDPyVPWNeQwKQ4Km1/HdAidofV4IkKfktJlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:51.389061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13292","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ef65d58ec47ee6119c6475c53aed5736c46b578a6951632674ce905505e524f","sha256:6f33ff3ab72f087c83caf8e8e8921c4b091cb9e2e7e8cbec79f760d259786037"],"state_sha256":"df9d1c037e88e1472f5aeb42f6b3ad2db62610c1a5b84d9177eb4a16b32f31da"}