{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OGNB7BNDKJ5PBYE5K37SMNOHA5","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":"651f95bd6378018a6519b26b1acf4c91ec38101363872ed16bd9638f13134252","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-15T05:48:30Z","title_canon_sha256":"a3e65e3ee685f938e3e1d36e0cf37fefdc9ec328f98c3b242573d83fddbb3482"},"schema_version":"1.0","source":{"id":"2410.22350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22350","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22350v1","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22350","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"OGNB7BNDKJ5P","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"OGNB7BNDKJ5PBYE5","created_at":"2026-07-05T09:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"OGNB7BND","created_at":"2026-07-05T09:28:15Z"}],"graph_snapshots":[{"event_id":"sha256:008806657520236e86492057b560cae72d74c16b5b41734bfa23b6881b4920fa","target":"graph","created_at":"2026-07-05T09:28:15Z","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/2410.22350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a quality-aware end-to-end audio-visual neural speaker diarization framework, which comprises three key techniques. First, our audio-visual model takes both audio and visual features as inputs, utilizing a series of binary classification output layers to simultaneously identify the activities of all speakers. This end-to-end framework is meticulously designed to effectively handle situations of overlapping speech, providing accurate discrimination between speech and non-speech segments through the utilization of multi-modal information. Next, we employ a quality-aware","authors_text":"Chin-Hui Lee, Jun Du, Mao-Kui He, Qing-Feng Liu, Shu-Tong Niu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-15T05:48:30Z","title":"Quality-Aware End-to-End Audio-Visual Neural Speaker Diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22350","kind":"arxiv","version":1},"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":"sha256:95479eac663bcc76e3cbec2cd6bb357dce855e37d1ff76afee639e521669a36b","target":"record","created_at":"2026-07-05T09:28:15Z","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":"651f95bd6378018a6519b26b1acf4c91ec38101363872ed16bd9638f13134252","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-15T05:48:30Z","title_canon_sha256":"a3e65e3ee685f938e3e1d36e0cf37fefdc9ec328f98c3b242573d83fddbb3482"},"schema_version":"1.0","source":{"id":"2410.22350","kind":"arxiv","version":1}},"canonical_sha256":"719a1f85a3527af0e09d56ff2635c70779906163359f0ab4ec986c85d30fa05f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"719a1f85a3527af0e09d56ff2635c70779906163359f0ab4ec986c85d30fa05f","first_computed_at":"2026-07-05T09:28:15.202689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:15.202689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LV9dy8+X0eVAe6WA+MLS8Wo7Yl6GiLoYLt5i+gz2NR0U/ziDSkk6G8lJF+iNhrcxGRLYE/6bqh+3bsgbZkqdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:15.203100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95479eac663bcc76e3cbec2cd6bb357dce855e37d1ff76afee639e521669a36b","sha256:008806657520236e86492057b560cae72d74c16b5b41734bfa23b6881b4920fa"],"state_sha256":"a1dd49830c789a6fbc5bdd12aac276adf41fa68fe5a1640101870260cd807de3"}