{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JVIHQ4V2ZWFPD3QUZYPCPQYTRY","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":"b38ae2efb39cc20b908ae277c25c1189760925265ac85c3f0310d2bc44760832","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T09:22:13Z","title_canon_sha256":"3e674b2cb8b3c59565b0e18a6c7f0d1ef5d269ee8f31e4c76717a080ef5f674a"},"schema_version":"1.0","source":{"id":"2411.16213","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16213","created_at":"2026-07-05T09:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16213v2","created_at":"2026-07-05T09:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16213","created_at":"2026-07-05T09:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"JVIHQ4V2ZWFP","created_at":"2026-07-05T09:47:36Z"},{"alias_kind":"pith_short_16","alias_value":"JVIHQ4V2ZWFPD3QU","created_at":"2026-07-05T09:47:36Z"},{"alias_kind":"pith_short_8","alias_value":"JVIHQ4V2","created_at":"2026-07-05T09:47:36Z"}],"graph_snapshots":[{"event_id":"sha256:1f3ec3b886569e617550aa2802a7eff5e403a1b974f13a9d62092c60b8990112","target":"graph","created_at":"2026-07-05T09:47:36Z","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/2411.16213/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Endeavors have been made to explore Large Language Models for video analysis (Video-LLMs), particularly in understanding and interpreting long videos. However, existing Video-LLMs still face challenges in effectively integrating the rich and diverse audio-visual information inherent in long videos, which is crucial for comprehensive understanding. This raises the question: how can we leverage embedded audio-visual information to enhance long video understanding? Therefore, (i) we introduce SAVEn-Vid, the first-ever long audio-visual video dataset comprising over 58k audio-visual instructions. ","authors_text":"Haodong Xu, Jungang Li, Linfeng Zhang, Sicheng Tao, Xiaojie Gu, Xuming Hu, Xu Zheng, Yibo Yan, Yuanhuiyi Lyu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T09:22:13Z","title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16213","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":"sha256:6e20d7c902eeb0cdf2b32b2a2528ee9dc30e2411b508b741a6318f05b121a0d4","target":"record","created_at":"2026-07-05T09:47:36Z","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":"b38ae2efb39cc20b908ae277c25c1189760925265ac85c3f0310d2bc44760832","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T09:22:13Z","title_canon_sha256":"3e674b2cb8b3c59565b0e18a6c7f0d1ef5d269ee8f31e4c76717a080ef5f674a"},"schema_version":"1.0","source":{"id":"2411.16213","kind":"arxiv","version":2}},"canonical_sha256":"4d507872bacd8af1ee14ce1e27c3138e2249356929cf84c78fffa8a563c8646b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d507872bacd8af1ee14ce1e27c3138e2249356929cf84c78fffa8a563c8646b","first_computed_at":"2026-07-05T09:47:36.593473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:36.593473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UhTDKvWffiJuV46lVv+OOLBqz6o+LTsMguhbGFMD1OaS8o08JtJCUQd+4Xq4d2UkktHsOIA+6pMskvPJm+9SBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:36.594060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16213","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e20d7c902eeb0cdf2b32b2a2528ee9dc30e2411b508b741a6318f05b121a0d4","sha256:1f3ec3b886569e617550aa2802a7eff5e403a1b974f13a9d62092c60b8990112"],"state_sha256":"066a64deb820a1eb0df69b4beecf83852bfe8a43f98092804cf0200734f01c23"}