{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PKU6P56FX775MRKTGZEZKOJLQQ","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":"4a644c02226aa732f8e30331cbbbcd6d130346ca31033e7d945d762a8ce6a7f7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-11T12:40:07Z","title_canon_sha256":"0790bf920deac84ddc0b9d6c87fb5ea3eeda7aca5599907d2760cadeb022fd9d"},"schema_version":"1.0","source":{"id":"2601.06896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06896","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06896v2","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06896","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"PKU6P56FX775","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"PKU6P56FX775MRKT","created_at":"2026-07-14T01:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"PKU6P56F","created_at":"2026-07-14T01:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:e52fc7e41fd0157e79f72dcd9e94906c9f9db472a1c519fc960d072903572d54","target":"graph","created_at":"2026-07-14T01:22:03Z","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/2601.06896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present TagSpeech, a unified LLM-based framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization. The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via Serialized Output Training (SOT) to learn turn-taking dynamics; and (2) an interleaved time anchor mechanism that not only supports fine-grained timestamp prediction but also acts as a synchronization signal between semantic understanding and speaker tracking. Compared to previous works that primarily focus on speaker-attributed ASR or implicit diarization, Ta","authors_text":"Mingyue Huo, Yiwen Shao, Yuheng Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-11T12:40:07Z","title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06896","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:d367b9fc123bf63cd8fdd05197fded560bb16bd490330beb51ac0a3b6e3a00bb","target":"record","created_at":"2026-07-14T01:22:03Z","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":"4a644c02226aa732f8e30331cbbbcd6d130346ca31033e7d945d762a8ce6a7f7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-11T12:40:07Z","title_canon_sha256":"0790bf920deac84ddc0b9d6c87fb5ea3eeda7aca5599907d2760cadeb022fd9d"},"schema_version":"1.0","source":{"id":"2601.06896","kind":"arxiv","version":2}},"canonical_sha256":"7aa9e7f7c5bfffd64553364995392b843d862b189f4808a81cfd3a17a5e4ef38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7aa9e7f7c5bfffd64553364995392b843d862b189f4808a81cfd3a17a5e4ef38","first_computed_at":"2026-07-14T01:22:03.160431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:03.160431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8MPKleGUrnKN5OE0YQHMPga9XboxecxnhSQ3vlh9Z6A7fy5U8JOK5MP/ebZ/HP/RG8NUvmJOyirg5hL2b+t1Cg==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:03.161398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.06896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d367b9fc123bf63cd8fdd05197fded560bb16bd490330beb51ac0a3b6e3a00bb","sha256:e52fc7e41fd0157e79f72dcd9e94906c9f9db472a1c519fc960d072903572d54"],"state_sha256":"507a52291409d27a4ce05379c3f18c8f018c7c1c432fb842c11ab516f6b37aee"}