{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IMAPATQDT5IQOLZLUCEHWXAJAQ","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":"d7df50e206eb1d80be386e83a96d455951c57edb78faa63237092e0027ab8303","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-17T10:19:00Z","title_canon_sha256":"b550b41623b6a108ca793cd57b0377579d00b159d7aaf9984a90eb5439a5dc05"},"schema_version":"1.0","source":{"id":"2507.12972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12972","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12972v1","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12972","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"IMAPATQDT5IQ","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"IMAPATQDT5IQOLZL","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"IMAPATQD","created_at":"2026-07-05T11:38:42Z"}],"graph_snapshots":[{"event_id":"sha256:ea2e13acd398103bcfedc6671969769cb3df5c4476ac104b5b241f1f2d62d1ee","target":"graph","created_at":"2026-07-05T11:38:42Z","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/2507.12972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge of speaker counts in mixtures. The limited research addressing unknown speaker quantity scenarios exhibits significantly constrained generalization capabilities in real acoustic environments. To overcome these challenges, this paper proposes AVFSNet -- an audio-visual speech separation model integrating multi-scale encoding and parallel architecture -- join","authors_text":"Daning Zhang, Ying Wei","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-17T10:19:00Z","title":"AVFSNet: Audio-Visual Speech Separation for Flexible Number of Speakers with Multi-Scale and Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12972","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:ed1599876f701d1dc627ecc78d06d956d839dad5c5262e0e2db8915a14e717b7","target":"record","created_at":"2026-07-05T11:38:42Z","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":"d7df50e206eb1d80be386e83a96d455951c57edb78faa63237092e0027ab8303","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-17T10:19:00Z","title_canon_sha256":"b550b41623b6a108ca793cd57b0377579d00b159d7aaf9984a90eb5439a5dc05"},"schema_version":"1.0","source":{"id":"2507.12972","kind":"arxiv","version":1}},"canonical_sha256":"4300f04e039f51072f2ba0887b5c090437ad704d08d3462ee93753f5f0f14653","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4300f04e039f51072f2ba0887b5c090437ad704d08d3462ee93753f5f0f14653","first_computed_at":"2026-07-05T11:38:42.379703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:42.379703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RAtrVSKQr6446g6YHiv2+ng55XTl11RCYpbfmhHeXwrqAosaQ4eoY/6a7IMozxEAwb/EoRD2qr5UNB8jGDfGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:42.380187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed1599876f701d1dc627ecc78d06d956d839dad5c5262e0e2db8915a14e717b7","sha256:ea2e13acd398103bcfedc6671969769cb3df5c4476ac104b5b241f1f2d62d1ee"],"state_sha256":"d1e97f86c4a774a14a4576e138aef693390baa8ff502855beef6d7d0786ed23c"}