{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JVIHQ4V2ZWFPD3QUZYPCPQYTRY","short_pith_number":"pith:JVIHQ4V2","schema_version":"1.0","canonical_sha256":"4d507872bacd8af1ee14ce1e27c3138e2249356929cf84c78fffa8a563c8646b","source":{"kind":"arxiv","id":"2411.16213","version":2},"attestation_state":"computed","paper":{"title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haodong Xu, Jungang Li, Linfeng Zhang, Sicheng Tao, Xiaojie Gu, Xuming Hu, Xu Zheng, Yibo Yan, Yuanhuiyi Lyu","submitted_at":"2024-11-25T09:22:13Z","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. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.16213","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T09:22:13Z","cross_cats_sorted":[],"title_canon_sha256":"3e674b2cb8b3c59565b0e18a6c7f0d1ef5d269ee8f31e4c76717a080ef5f674a","abstract_canon_sha256":"b38ae2efb39cc20b908ae277c25c1189760925265ac85c3f0310d2bc44760832"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:36.594060Z","signature_b64":"UhTDKvWffiJuV46lVv+OOLBqz6o+LTsMguhbGFMD1OaS8o08JtJCUQd+4Xq4d2UkktHsOIA+6pMskvPJm+9SBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d507872bacd8af1ee14ce1e27c3138e2249356929cf84c78fffa8a563c8646b","last_reissued_at":"2026-07-05T09:47:36.593473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:36.593473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haodong Xu, Jungang Li, Linfeng Zhang, Sicheng Tao, Xiaojie Gu, Xuming Hu, Xu Zheng, Yibo Yan, Yuanhuiyi Lyu","submitted_at":"2024-11-25T09:22:13Z","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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16213","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.16213/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.16213","created_at":"2026-07-05T09:47:36.593539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16213v2","created_at":"2026-07-05T09:47:36.593539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16213","created_at":"2026-07-05T09:47:36.593539+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVIHQ4V2ZWFP","created_at":"2026-07-05T09:47:36.593539+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVIHQ4V2ZWFPD3QU","created_at":"2026-07-05T09:47:36.593539+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVIHQ4V2","created_at":"2026-07-05T09:47:36.593539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07016","citing_title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY","json":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY.json","graph_json":"https://pith.science/api/pith-number/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/graph.json","events_json":"https://pith.science/api/pith-number/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/events.json","paper":"https://pith.science/paper/JVIHQ4V2"},"agent_actions":{"view_html":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY","download_json":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY.json","view_paper":"https://pith.science/paper/JVIHQ4V2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16213&json=true","fetch_graph":"https://pith.science/api/pith-number/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/graph.json","fetch_events":"https://pith.science/api/pith-number/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/action/storage_attestation","attest_author":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/action/author_attestation","sign_citation":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/action/citation_signature","submit_replication":"https://pith.science/pith/JVIHQ4V2ZWFPD3QUZYPCPQYTRY/action/replication_record"}},"created_at":"2026-07-05T09:47:36.593539+00:00","updated_at":"2026-07-05T09:47:36.593539+00:00"}