{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VLBORAL4JWW35ICB3UEQVSQL4M","short_pith_number":"pith:VLBORAL4","canonical_record":{"source":{"id":"2507.09510","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-13T06:35:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"252b7023b1b70137b4d9969030475dfdcaa901157b2807135bcebe8abba34b3c","abstract_canon_sha256":"378d18344e27bccb63b1ca4a26a49af51bb18c5313fd586189bfae55e661d61e"},"schema_version":"1.0"},"canonical_sha256":"aac2e8817c4dadbea041dd090aca0be32a5ad3f1fa232c3477bc94f49d2ef24b","source":{"kind":"arxiv","id":"2507.09510","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09510","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09510v3","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09510","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_12","alias_value":"VLBORAL4JWW3","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_16","alias_value":"VLBORAL4JWW35ICB","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_8","alias_value":"VLBORAL4","created_at":"2026-07-05T11:51:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VLBORAL4JWW35ICB3UEQVSQL4M","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09510","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-13T06:35:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"252b7023b1b70137b4d9969030475dfdcaa901157b2807135bcebe8abba34b3c","abstract_canon_sha256":"378d18344e27bccb63b1ca4a26a49af51bb18c5313fd586189bfae55e661d61e"},"schema_version":"1.0"},"canonical_sha256":"aac2e8817c4dadbea041dd090aca0be32a5ad3f1fa232c3477bc94f49d2ef24b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:31.984629Z","signature_b64":"OXp6UwNW4WaIhlet74CAfVWwEF0inCEIh8c9wHMC+5cq+3b+mE5khedC3oxLT7VUZDS9SHf4UlJRxzvZsSqWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac2e8817c4dadbea041dd090aca0be32a5ad3f1fa232c3477bc94f49d2ef24b","last_reissued_at":"2026-07-05T11:51:31.984121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:31.984121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09510","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ay1fojDP0SUXUIZkLeSNpEqTnus7ruehn2whlHaxvbGpKF8murB4WThfSQBVbrJl1GW/gcmIDhlOU1PZjfTsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:21:14.413936Z"},"content_sha256":"070f93edcf183a06f75180e17d5e2a3dd07b3b64c697bf9d465a86d7c5255bd4","schema_version":"1.0","event_id":"sha256:070f93edcf183a06f75180e17d5e2a3dd07b3b64c697bf9d465a86d7c5255bd4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VLBORAL4JWW35ICB3UEQVSQL4M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Target Speaker Extraction with Explicit Speaker Consistency Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anbin QI, Shu Wu, Xiang Xie, Yanzhang Xie","submitted_at":"2025-07-13T06:35:13Z","abstract_excerpt":"Target Speaker Extraction (TSE) uses a reference cue to extract the target speech from a mixture. In TSE systems relying on audio cues, the speaker embedding from the enrolled speech is crucial to performance. However, these embeddings may suffer from speaker identity confusion. Unlike previous studies that focus on improving speaker embedding extraction, we improve TSE performance from the perspective of speaker consistency. In this paper, we propose a speaker consistency-aware target speaker extraction method that incorporates a centroid-based speaker consistency loss. This approach enhances"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09510","kind":"arxiv","version":3},"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/2507.09510/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MoJ+CC8JQzkp90KjDpg8dt4BAetOJWPWRtjakGiFCl5ZzDT4ijtoXdd8/CQ4WK+LecwitY2Dxo3wEExxYuleAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:21:14.414467Z"},"content_sha256":"92f56c98f7cc20d942fa2e729d1b093e28c834ba86d13db142068f109cdde796","schema_version":"1.0","event_id":"sha256:92f56c98f7cc20d942fa2e729d1b093e28c834ba86d13db142068f109cdde796"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLBORAL4JWW35ICB3UEQVSQL4M/bundle.json","state_url":"https://pith.science/pith/VLBORAL4JWW35ICB3UEQVSQL4M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLBORAL4JWW35ICB3UEQVSQL4M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T04:21:14Z","links":{"resolver":"https://pith.science/pith/VLBORAL4JWW35ICB3UEQVSQL4M","bundle":"https://pith.science/pith/VLBORAL4JWW35ICB3UEQVSQL4M/bundle.json","state":"https://pith.science/pith/VLBORAL4JWW35ICB3UEQVSQL4M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLBORAL4JWW35ICB3UEQVSQL4M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VLBORAL4JWW35ICB3UEQVSQL4M","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":"378d18344e27bccb63b1ca4a26a49af51bb18c5313fd586189bfae55e661d61e","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-13T06:35:13Z","title_canon_sha256":"252b7023b1b70137b4d9969030475dfdcaa901157b2807135bcebe8abba34b3c"},"schema_version":"1.0","source":{"id":"2507.09510","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09510","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09510v3","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09510","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_12","alias_value":"VLBORAL4JWW3","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_16","alias_value":"VLBORAL4JWW35ICB","created_at":"2026-07-05T11:51:31Z"},{"alias_kind":"pith_short_8","alias_value":"VLBORAL4","created_at":"2026-07-05T11:51:31Z"}],"graph_snapshots":[{"event_id":"sha256:92f56c98f7cc20d942fa2e729d1b093e28c834ba86d13db142068f109cdde796","target":"graph","created_at":"2026-07-05T11:51:31Z","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/2507.09510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target Speaker Extraction (TSE) uses a reference cue to extract the target speech from a mixture. In TSE systems relying on audio cues, the speaker embedding from the enrolled speech is crucial to performance. However, these embeddings may suffer from speaker identity confusion. Unlike previous studies that focus on improving speaker embedding extraction, we improve TSE performance from the perspective of speaker consistency. In this paper, we propose a speaker consistency-aware target speaker extraction method that incorporates a centroid-based speaker consistency loss. This approach enhances","authors_text":"Anbin QI, Shu Wu, Xiang Xie, Yanzhang Xie","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-13T06:35:13Z","title":"Enhancing Target Speaker Extraction with Explicit Speaker Consistency Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09510","kind":"arxiv","version":3},"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":"sha256:070f93edcf183a06f75180e17d5e2a3dd07b3b64c697bf9d465a86d7c5255bd4","target":"record","created_at":"2026-07-05T11:51:31Z","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":"378d18344e27bccb63b1ca4a26a49af51bb18c5313fd586189bfae55e661d61e","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-13T06:35:13Z","title_canon_sha256":"252b7023b1b70137b4d9969030475dfdcaa901157b2807135bcebe8abba34b3c"},"schema_version":"1.0","source":{"id":"2507.09510","kind":"arxiv","version":3}},"canonical_sha256":"aac2e8817c4dadbea041dd090aca0be32a5ad3f1fa232c3477bc94f49d2ef24b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aac2e8817c4dadbea041dd090aca0be32a5ad3f1fa232c3477bc94f49d2ef24b","first_computed_at":"2026-07-05T11:51:31.984121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:31.984121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OXp6UwNW4WaIhlet74CAfVWwEF0inCEIh8c9wHMC+5cq+3b+mE5khedC3oxLT7VUZDS9SHf4UlJRxzvZsSqWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:31.984629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09510","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:070f93edcf183a06f75180e17d5e2a3dd07b3b64c697bf9d465a86d7c5255bd4","sha256:92f56c98f7cc20d942fa2e729d1b093e28c834ba86d13db142068f109cdde796"],"state_sha256":"e6cd067b077d001c5bf83538c9a2f3cd846c1bc5320a64f7dd80b5c2c86bae40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E4ClRAQz96tBWDWLxSU0fQM2Z9s15ra5Jcn9J0AibvvkqdOWhO2wHcksVuoi0+oow44a23fzVTlfp+SB2OEkDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:21:14.418694Z","bundle_sha256":"e951d94d280557b8af1552f07181b0ad34261e9ac6469c15bad6e52a270d300f"}}