{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BKPCKBDID6VCALO2AMX3MSDCRR","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":"398790c9482bb72c3733d8a2c975ab268964ee6974dbcd3b508e32f8a23957d8","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T07:26:44Z","title_canon_sha256":"e876bb7ee0a3dbb4cf8b24d9809e95f6b8731bc791f17d47ba5afd24f6e8fd4d"},"schema_version":"1.0","source":{"id":"2506.12059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12059","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12059v1","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12059","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"pith_short_12","alias_value":"BKPCKBDID6VC","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"pith_short_16","alias_value":"BKPCKBDID6VCALO2","created_at":"2026-07-05T11:21:16Z"},{"alias_kind":"pith_short_8","alias_value":"BKPCKBDI","created_at":"2026-07-05T11:21:16Z"}],"graph_snapshots":[{"event_id":"sha256:90c44647295129dcfeeeb60ca4e6cb99c6eace12c46f8f908d1df4aca77183af","target":"graph","created_at":"2026-07-05T11:21:16Z","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/2506.12059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing separately, limiting performance in complex scenarios. We propose a unified framework that combines multi-talker overlapping speech recognition and contextual biasing into a single task. Our ASR method integrates pretrained speech encoders and large language models (LLMs), using optimized finetuning strategies. We also introduce a two-stage filtering algorit","authors_text":"Jiajun He, Koichi Miyazaki, Naoki Sawada, Tomoki Toda","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T07:26:44Z","title":"CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12059","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":"sha256:06cbd365db92c505b21c046389b1c0b12a930bce5a3605f08d4c840eec5b461e","target":"record","created_at":"2026-07-05T11:21:16Z","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":"398790c9482bb72c3733d8a2c975ab268964ee6974dbcd3b508e32f8a23957d8","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T07:26:44Z","title_canon_sha256":"e876bb7ee0a3dbb4cf8b24d9809e95f6b8731bc791f17d47ba5afd24f6e8fd4d"},"schema_version":"1.0","source":{"id":"2506.12059","kind":"arxiv","version":1}},"canonical_sha256":"0a9e2504681faa202dda032fb648628c6cc516b79d518efe11c980a45e491568","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a9e2504681faa202dda032fb648628c6cc516b79d518efe11c980a45e491568","first_computed_at":"2026-07-05T11:21:16.454237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:16.454237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2RxQzUdrL2zS4xJMePcib10TG/gOZ0FIrvRqApE/V2e4LU3+5dxX1xNtqPpDi1h/B5pyJp8nYv0cD70rCt5aAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:16.454660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06cbd365db92c505b21c046389b1c0b12a930bce5a3605f08d4c840eec5b461e","sha256:90c44647295129dcfeeeb60ca4e6cb99c6eace12c46f8f908d1df4aca77183af"],"state_sha256":"bc062c9353eb6c8798ca318f88bcaca7c0832ed17221477f1132b84424bcc709"}