{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OMTSAE5TS3NK37UHF7E4BMHM4L","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":"198ff9bce1c4fdc94f1f61a423255968cb8b0fa060d8a037e9b67ec34b8ddb4e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-12-24T06:13:02Z","title_canon_sha256":"053111ff082dac032858bb807a2e75556b19e95013c7bb4dcf354799b133e3dc"},"schema_version":"1.0","source":{"id":"2512.20978","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.20978","created_at":"2026-06-09T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2512.20978v2","created_at":"2026-06-09T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.20978","created_at":"2026-06-09T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"OMTSAE5TS3NK","created_at":"2026-06-09T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"OMTSAE5TS3NK37UH","created_at":"2026-06-09T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"OMTSAE5T","created_at":"2026-06-09T01:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:18ac0db3de1dfaa3f5bd748ca93f10a4bf9a432432a27511e2c0a083e02a6ee9","target":"graph","created_at":"2026-06-09T01:05:12Z","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/2512.20978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech. We propose GenTSE, a two-stage decoder-only generative LM for TSE: Stage-1 predicts coarse semantic tokens, and Stage-2 generates fine acoustic tokens. Separating semantics and acoustics stabilizes decoding and yields more accurate target speech. Both stages use continuous SSL or codec embeddings, offering richer context than discretized-prompt methods. To reduce exposure bias, we employ a Frozen-LM Conditioning training strategy t","authors_text":"Azmat Adnan, Boon Siew Han, Eng Siong Chng, Haoyang Li, Shreyas Gopal, Wei Rao, Xuyi Zhuang, Ye Ni, Yuanjin Zheng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-12-24T06:13:02Z","title":"GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.20978","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:b7aa7d25c73e08762018a103f6d116a7ed99c5fb514adf23b833bbf3479bb0d8","target":"record","created_at":"2026-06-09T01:05:12Z","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":"198ff9bce1c4fdc94f1f61a423255968cb8b0fa060d8a037e9b67ec34b8ddb4e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-12-24T06:13:02Z","title_canon_sha256":"053111ff082dac032858bb807a2e75556b19e95013c7bb4dcf354799b133e3dc"},"schema_version":"1.0","source":{"id":"2512.20978","kind":"arxiv","version":2}},"canonical_sha256":"73272013b396daadfe872fc9c0b0ece2f37ade47cd017e456e3fb8cb180e1d55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73272013b396daadfe872fc9c0b0ece2f37ade47cd017e456e3fb8cb180e1d55","first_computed_at":"2026-06-09T01:05:12.170145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:12.170145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qbw1dimRxw6ekN9ms4IhEs1VqN40E9NTB1McPEtK/l2CAtfbEKtu1mgcOgwwUjCWpxCzAz9aNKkm61Ni3wCdBw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:12.170660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.20978","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7aa7d25c73e08762018a103f6d116a7ed99c5fb514adf23b833bbf3479bb0d8","sha256:18ac0db3de1dfaa3f5bd748ca93f10a4bf9a432432a27511e2c0a083e02a6ee9"],"state_sha256":"75330ef80e47b8e72440ee67c0552e94791520ddeaa2de15e1fd2760ab173e21"}