{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LR4IEMHJWGZIMRV3CHQFPLSCCF","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":"63e98ff648efab1775fb084e240d7cb48e3e2735adfd0c0c44a651ec0c121173","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T02:48:49Z","title_canon_sha256":"47e37d3edcd166f2fbe73dd4d6dfccca31ed711eb15dd4b4a48dcc0dac8d6368"},"schema_version":"1.0","source":{"id":"2110.03151","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03151","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03151v2","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03151","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"LR4IEMHJWGZI","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"pith_short_16","alias_value":"LR4IEMHJWGZIMRV3","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"pith_short_8","alias_value":"LR4IEMHJ","created_at":"2026-07-05T03:50:36Z"}],"graph_snapshots":[{"event_id":"sha256:1fb6c4ee9248d787a376f6ba1d6f90ba08c6d4444ee78cf050069cce9d2b7a0f","target":"graph","created_at":"2026-07-05T03:50:36Z","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/2110.03151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents Transcribe-to-Diarize, a new approach for neural speaker diarization that uses an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR). The E2E SA-ASR is a joint model that was recently proposed for speaker counting, multi-talker speech recognition, and speaker identification from monaural audio that contains overlapping speech. Although the E2E SA-ASR model originally does not estimate any time-related information, we show that the start and end times of each word can be estimated with sufficient accuracy from the internal state of the E2E SA-ASR by ad","authors_text":"Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Zhong Meng, Zhuo Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T02:48:49Z","title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03151","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":"sha256:47bbdeaf76640311c0ef76c2c131602672dd2fd703d3ded57205260ceb2341fa","target":"record","created_at":"2026-07-05T03:50:36Z","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":"63e98ff648efab1775fb084e240d7cb48e3e2735adfd0c0c44a651ec0c121173","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T02:48:49Z","title_canon_sha256":"47e37d3edcd166f2fbe73dd4d6dfccca31ed711eb15dd4b4a48dcc0dac8d6368"},"schema_version":"1.0","source":{"id":"2110.03151","kind":"arxiv","version":2}},"canonical_sha256":"5c788230e9b1b28646bb11e057ae42114cc9c303846b4416bb6566f0b081d69f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c788230e9b1b28646bb11e057ae42114cc9c303846b4416bb6566f0b081d69f","first_computed_at":"2026-07-05T03:50:36.747901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:50:36.747901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zkjWVuc+IXdTebd4z7+zQvlTOxhfbAKBM8H96kDl6shnqI/CZLdXCxOV33IeQ4nfvT6Rteq2VSBT4IxZxmV4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:50:36.748479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03151","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47bbdeaf76640311c0ef76c2c131602672dd2fd703d3ded57205260ceb2341fa","sha256:1fb6c4ee9248d787a376f6ba1d6f90ba08c6d4444ee78cf050069cce9d2b7a0f"],"state_sha256":"749df6c880c0d9836208d3c879a5f8e2d0c0f05b92f4f370af0fa0a0ef896518"}