{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7ZKXMR65NYYANALUW5MYHR6LHP","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":"34328a7626cdc7625c1a8c676f4a3bb5607a5b6f3cf191a9c617b043c7f1488d","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-06T05:07:11Z","title_canon_sha256":"8a7871681112ac53d09721d2627f17445716f44139b797e5c60d830715c63383"},"schema_version":"1.0","source":{"id":"2505.03186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03186","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03186v2","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03186","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"7ZKXMR65NYYA","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"7ZKXMR65NYYANALU","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"7ZKXMR65","created_at":"2026-07-05T11:03:24Z"}],"graph_snapshots":[{"event_id":"sha256:5487334661e0521e81f740fe734bd06c68c47c3de2010be0a18612197626ff58","target":"graph","created_at":"2026-07-05T11:03:24Z","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/2505.03186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The inherent synchronization between a speaker's lip movements, voice, and the underlying linguistic content offers a rich source of information for improving speech processing tasks, especially in challenging conditions where traditional audio-only systems falter. We introduce CoGenAV, a powerful and data-efficient model designed to learn versatile audio-visual representations applicable across a wide range of speech and audio-visual tasks. CoGenAV is trained by optimizing a dual objective derived from natural audio-visual synchrony, contrastive feature alignment and generative text predictio","authors_text":"Detao Bai, Liefeng Bo, Xihan Wei, Zhiheng Ma","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-06T05:07:11Z","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03186","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:fd2db8887148ff04f527ac0cf24334bba0af78196e4f6293951178af5a70e232","target":"record","created_at":"2026-07-05T11:03:24Z","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":"34328a7626cdc7625c1a8c676f4a3bb5607a5b6f3cf191a9c617b043c7f1488d","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-06T05:07:11Z","title_canon_sha256":"8a7871681112ac53d09721d2627f17445716f44139b797e5c60d830715c63383"},"schema_version":"1.0","source":{"id":"2505.03186","kind":"arxiv","version":2}},"canonical_sha256":"fe557647dd6e30068174b75983c7cb3be582fa412dbb5a033f76da5a9bfbac08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe557647dd6e30068174b75983c7cb3be582fa412dbb5a033f76da5a9bfbac08","first_computed_at":"2026-07-05T11:03:24.079948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:24.079948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"82fnPqmRXA/YSYPcayMaRrzHa7sCvYHH2pwXhlPfzaO7Baw3EkQK+hUTn6Z3mcDL3TpNYQNUyLrQmqDmg2AvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:24.080332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd2db8887148ff04f527ac0cf24334bba0af78196e4f6293951178af5a70e232","sha256:5487334661e0521e81f740fe734bd06c68c47c3de2010be0a18612197626ff58"],"state_sha256":"5b2a46ad60a9a34bf3c64b8c59fa94e79c3b5321894e6e89e4c15af8d1573512"}