{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SANUBS7C5YK5TWDBP2TMDHBUP4","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":"e57ce43a16c4a1cbe693f4cfdd3bea80d19e71e477466a4eb52bbe16ed280f0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-04T17:28:41Z","title_canon_sha256":"42a92fcec6abee5315f55e970391a91e2564885bd66ecb50592cdc4d9124b2aa"},"schema_version":"1.0","source":{"id":"2608.03964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03964","created_at":"2026-08-05T01:37:35Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03964v1","created_at":"2026-08-05T01:37:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03964","created_at":"2026-08-05T01:37:35Z"},{"alias_kind":"pith_short_12","alias_value":"SANUBS7C5YK5","created_at":"2026-08-05T01:37:35Z"},{"alias_kind":"pith_short_16","alias_value":"SANUBS7C5YK5TWDB","created_at":"2026-08-05T01:37:35Z"},{"alias_kind":"pith_short_8","alias_value":"SANUBS7C","created_at":"2026-08-05T01:37:35Z"}],"graph_snapshots":[{"event_id":"sha256:c4dd47b10dcc7c77a8eb4448cf9c348e635b2a7d481d59b824b32c0b5412e872","target":"graph","created_at":"2026-08-05T01:37:35Z","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/2608.03964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Juan Liu, Ming Li, Peijun Yang, Zhan Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-04T17:28:41Z","title":"Identity-Faithful Audio-Visual Target Speaker Extraction with QIANGDA and VOXBLINK2-AVSE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03964","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:ee8bfa6e8bbee0cc7c6bffee24572b6c69737f15cb4d7675a88be81a1ff90cf5","target":"record","created_at":"2026-08-05T01:37:35Z","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":"e57ce43a16c4a1cbe693f4cfdd3bea80d19e71e477466a4eb52bbe16ed280f0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-04T17:28:41Z","title_canon_sha256":"42a92fcec6abee5315f55e970391a91e2564885bd66ecb50592cdc4d9124b2aa"},"schema_version":"1.0","source":{"id":"2608.03964","kind":"arxiv","version":1}},"canonical_sha256":"901b40cbe2ee15d9d8617ea6c19c347f325563bbe0fc30be832be1d277bb4ead","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"901b40cbe2ee15d9d8617ea6c19c347f325563bbe0fc30be832be1d277bb4ead","first_computed_at":"2026-08-05T01:37:35.855966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:37:35.855966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aD8uozaIxC14mmRVx4EUKIT+wIan3bDq8W9uAu81NY97+IuSzWSLIRtzt/owegUvhYFgsFN6Lja5bJvumCf7DQ==","signature_status":"signed_v1","signed_at":"2026-08-05T01:37:35.857360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee8bfa6e8bbee0cc7c6bffee24572b6c69737f15cb4d7675a88be81a1ff90cf5","sha256:c4dd47b10dcc7c77a8eb4448cf9c348e635b2a7d481d59b824b32c0b5412e872"],"state_sha256":"fb2e9cc8ac7bec4aef31846a1efb8af106f8f261e6ea2ece9fd988d6c1589d6e"}