{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4YACVMJ5XTCPR7YHAPHRLFE2HH","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":"056313e2b74ad10a74551ee043f2cfa1272adcf053535989be2bfc4a654cd0ad","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-24T13:19:56Z","title_canon_sha256":"5063c5d1f60701c5d59d348bcd0aef58cd64e4ee3ce7c6ee1a223b607aab7e57"},"schema_version":"1.0","source":{"id":"2501.14477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14477","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14477v2","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14477","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"4YACVMJ5XTCP","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"4YACVMJ5XTCPR7YH","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"4YACVMJ5","created_at":"2026-07-05T11:06:54Z"}],"graph_snapshots":[{"event_id":"sha256:9b8d33af53ee5229bfe542f08876295a9a4e0426f25786bd94deb37b827511cc","target":"graph","created_at":"2026-07-05T11:06:54Z","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/2501.14477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typically predicting a time-frequency spectrogram mask for the target speech. However, imperfections in these masks often result in over-/under-suppression of target/non-target speech, degrading perceptual quality. Generative methods, by contrast, re-synthesize target speech based on the mixture and target speaker cues, achieving superior perceptual quality. Nevertheless, these methods often overlook speech intelligibil","authors_text":"Hao Ma, Ju Liu, Rujin Chen, Xiao-Lei Zhang, Xuelong Li","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-24T13:19:56Z","title":"Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14477","kind":"arxiv","version":2},"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":"sha256:5a6a560f63dfe43ab95c8338dde1b07c5f06e79bd511164af13b76d0cf9d6a93","target":"record","created_at":"2026-07-05T11:06:54Z","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":"056313e2b74ad10a74551ee043f2cfa1272adcf053535989be2bfc4a654cd0ad","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-24T13:19:56Z","title_canon_sha256":"5063c5d1f60701c5d59d348bcd0aef58cd64e4ee3ce7c6ee1a223b607aab7e57"},"schema_version":"1.0","source":{"id":"2501.14477","kind":"arxiv","version":2}},"canonical_sha256":"e6002ab13dbcc4f8ff0703cf15949a39f45b1d4d9c890f3b8449d31d7cbfd0aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6002ab13dbcc4f8ff0703cf15949a39f45b1d4d9c890f3b8449d31d7cbfd0aa","first_computed_at":"2026-07-05T11:06:54.787332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:54.787332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1rb7SU46NbdwU6zsNmVgDaE8FH4VavbHjkG3CIE5M3kFgdCChObw3OJPM/DAEHcRlqVZqGdY9/4v+MT5ywmuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:54.787869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a6a560f63dfe43ab95c8338dde1b07c5f06e79bd511164af13b76d0cf9d6a93","sha256:9b8d33af53ee5229bfe542f08876295a9a4e0426f25786bd94deb37b827511cc"],"state_sha256":"43aa91afcd4ca7c2fb8608e2393a61e7e5a753ebd480a0901dc60bf16ca416e8"}