{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OGF5BYBX6M2RPTFGD7EG7SNGLX","short_pith_number":"pith:OGF5BYBX","schema_version":"1.0","canonical_sha256":"718bd0e037f33517cca61fc86fc9a65dfd553beff98a4480e864f694de822605","source":{"kind":"arxiv","id":"2503.16357","version":1},"attestation_state":"computed","paper":{"title":"UniSync: A Unified Framework for Audio-Visual Synchronization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Fei Ma, Fei Yu, Jiyuan Song, Tao Feng, Xun Guan, Yifan Xie, Zhou Liu","submitted_at":"2025-03-20T17:16:03Z","abstract_excerpt":"Precise audio-visual synchronization in speech videos is crucial for content quality and viewer comprehension. Existing methods have made significant strides in addressing this challenge through rule-based approaches and end-to-end learning techniques. However, these methods often rely on limited audio-visual representations and suboptimal learning strategies, potentially constraining their effectiveness in more complex scenarios. To address these limitations, we present UniSync, a novel approach for evaluating audio-visual synchronization using embedding similarities. UniSync offers broad com"},"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":"2503.16357","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:16:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3691805342b31da8a1dabb6c026cc0be5a8d9c4f0ce072b730a7b9c7f6b5d372","abstract_canon_sha256":"19266c2adff1ff1dfe7c135b86d4769c7616f54f35386a048b71827c42726dc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:18.017882Z","signature_b64":"VZZXAr/dHg0XnCVI2aEbgCquktI5CYj2QQiKNyOVc0eUk2fBnTQ2nqghORZ+rG/RUPCW5uKtTurhs16zLrY6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718bd0e037f33517cca61fc86fc9a65dfd553beff98a4480e864f694de822605","last_reissued_at":"2026-07-05T10:36:18.017405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:18.017405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniSync: A Unified Framework for Audio-Visual Synchronization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Fei Ma, Fei Yu, Jiyuan Song, Tao Feng, Xun Guan, Yifan Xie, Zhou Liu","submitted_at":"2025-03-20T17:16:03Z","abstract_excerpt":"Precise audio-visual synchronization in speech videos is crucial for content quality and viewer comprehension. Existing methods have made significant strides in addressing this challenge through rule-based approaches and end-to-end learning techniques. However, these methods often rely on limited audio-visual representations and suboptimal learning strategies, potentially constraining their effectiveness in more complex scenarios. To address these limitations, we present UniSync, a novel approach for evaluating audio-visual synchronization using embedding similarities. UniSync offers broad com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16357","kind":"arxiv","version":1},"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/2503.16357/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":"2503.16357","created_at":"2026-07-05T10:36:18.017466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16357v1","created_at":"2026-07-05T10:36:18.017466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16357","created_at":"2026-07-05T10:36:18.017466+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGF5BYBX6M2R","created_at":"2026-07-05T10:36:18.017466+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGF5BYBX6M2RPTFG","created_at":"2026-07-05T10:36:18.017466+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGF5BYBX","created_at":"2026-07-05T10:36:18.017466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18810","citing_title":"Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX","json":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX.json","graph_json":"https://pith.science/api/pith-number/OGF5BYBX6M2RPTFGD7EG7SNGLX/graph.json","events_json":"https://pith.science/api/pith-number/OGF5BYBX6M2RPTFGD7EG7SNGLX/events.json","paper":"https://pith.science/paper/OGF5BYBX"},"agent_actions":{"view_html":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX","download_json":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX.json","view_paper":"https://pith.science/paper/OGF5BYBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16357&json=true","fetch_graph":"https://pith.science/api/pith-number/OGF5BYBX6M2RPTFGD7EG7SNGLX/graph.json","fetch_events":"https://pith.science/api/pith-number/OGF5BYBX6M2RPTFGD7EG7SNGLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX/action/storage_attestation","attest_author":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX/action/author_attestation","sign_citation":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX/action/citation_signature","submit_replication":"https://pith.science/pith/OGF5BYBX6M2RPTFGD7EG7SNGLX/action/replication_record"}},"created_at":"2026-07-05T10:36:18.017466+00:00","updated_at":"2026-07-05T10:36:18.017466+00:00"}