{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SANUBS7C5YK5TWDBP2TMDHBUP4","short_pith_number":"pith:SANUBS7C","schema_version":"1.0","canonical_sha256":"901b40cbe2ee15d9d8617ea6c19c347f325563bbe0fc30be832be1d277bb4ead","source":{"kind":"arxiv","id":"2608.03964","version":1},"attestation_state":"computed","paper":{"title":"Identity-Faithful Audio-Visual Target Speaker Extraction with QIANGDA and VOXBLINK2-AVSE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Juan Liu, Ming Li, Peijun Yang, Zhan Jin","submitted_at":"2026-08-04T17:28:41Z","abstract_excerpt":"Audio-visual target speaker extraction should return the speaker indicated by the video, yet a separator can ignore the visual cue and repeatedly output the acoustically dominant voice. We introduce QIANGDA, a Mandarin AV-TSE benchmark of jointly recorded real two-speaker mixtures with synchronized multi-view video. Each scene also contains preceding A-only and B-only stages that provide in-scene speaker references. It contains 77 scenes and 7,598 clips (11.84 hours), including 6,042 dual-annotated mixtures. After processing there leave 6,038 evaluable mixtures and 12,076 target-speaker rows. "},"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":"2608.03964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-04T17:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"42a92fcec6abee5315f55e970391a91e2564885bd66ecb50592cdc4d9124b2aa","abstract_canon_sha256":"e57ce43a16c4a1cbe693f4cfdd3bea80d19e71e477466a4eb52bbe16ed280f0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:35.857360Z","signature_b64":"aD8uozaIxC14mmRVx4EUKIT+wIan3bDq8W9uAu81NY97+IuSzWSLIRtzt/owegUvhYFgsFN6Lja5bJvumCf7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"901b40cbe2ee15d9d8617ea6c19c347f325563bbe0fc30be832be1d277bb4ead","last_reissued_at":"2026-08-05T01:37:35.855966Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:35.855966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identity-Faithful Audio-Visual Target Speaker Extraction with QIANGDA and VOXBLINK2-AVSE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Juan Liu, Ming Li, Peijun Yang, Zhan Jin","submitted_at":"2026-08-04T17:28:41Z","abstract_excerpt":"Audio-visual target speaker extraction should return the speaker indicated by the video, yet a separator can ignore the visual cue and repeatedly output the acoustically dominant voice. We introduce QIANGDA, a Mandarin AV-TSE benchmark of jointly recorded real two-speaker mixtures with synchronized multi-view video. Each scene also contains preceding A-only and B-only stages that provide in-scene speaker references. It contains 77 scenes and 7,598 clips (11.84 hours), including 6,042 dual-annotated mixtures. After processing there leave 6,038 evaluable mixtures and 12,076 target-speaker rows. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03964","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/2608.03964/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":"2608.03964","created_at":"2026-08-05T01:37:35.856435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03964v1","created_at":"2026-08-05T01:37:35.856435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03964","created_at":"2026-08-05T01:37:35.856435+00:00"},{"alias_kind":"pith_short_12","alias_value":"SANUBS7C5YK5","created_at":"2026-08-05T01:37:35.856435+00:00"},{"alias_kind":"pith_short_16","alias_value":"SANUBS7C5YK5TWDB","created_at":"2026-08-05T01:37:35.856435+00:00"},{"alias_kind":"pith_short_8","alias_value":"SANUBS7C","created_at":"2026-08-05T01:37:35.856435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4","json":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4.json","graph_json":"https://pith.science/api/pith-number/SANUBS7C5YK5TWDBP2TMDHBUP4/graph.json","events_json":"https://pith.science/api/pith-number/SANUBS7C5YK5TWDBP2TMDHBUP4/events.json","paper":"https://pith.science/paper/SANUBS7C"},"agent_actions":{"view_html":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4","download_json":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4.json","view_paper":"https://pith.science/paper/SANUBS7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03964&json=true","fetch_graph":"https://pith.science/api/pith-number/SANUBS7C5YK5TWDBP2TMDHBUP4/graph.json","fetch_events":"https://pith.science/api/pith-number/SANUBS7C5YK5TWDBP2TMDHBUP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4/action/storage_attestation","attest_author":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4/action/author_attestation","sign_citation":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4/action/citation_signature","submit_replication":"https://pith.science/pith/SANUBS7C5YK5TWDBP2TMDHBUP4/action/replication_record"}},"created_at":"2026-08-05T01:37:35.856435+00:00","updated_at":"2026-08-05T01:37:35.856435+00:00"}