{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NTPNFXFW4XJKDTBDN46VQBZAHQ","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":"d68f80c15112d20b1a3aee2fa08f95e8116defce65ec819a038f875ec0ef0e69","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-25T01:00:41Z","title_canon_sha256":"4ab934f8f0b116ff00f49f789f5bbfd2624bef69383d4c4cd75407ea51cab429"},"schema_version":"1.0","source":{"id":"2601.17640","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.17640","created_at":"2026-08-11T02:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2601.17640v2","created_at":"2026-08-11T02:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17640","created_at":"2026-08-11T02:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"NTPNFXFW4XJK","created_at":"2026-08-11T02:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"NTPNFXFW4XJKDTBD","created_at":"2026-08-11T02:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"NTPNFXFW","created_at":"2026-08-11T02:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:68138004e73a26c5f437b33e690d832329bfe93c2309ce78d37b24d0dc5068c7","target":"graph","created_at":"2026-08-11T02:18:46Z","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/2601.17640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate transcription and speaker role diarization of child-adult spoken interactions are crucial for developmental and clinical research. However, manual annotation is time-consuming and challenging to scale. Existing automated systems typically rely on cascaded speaker diarization and automatic speech recognition pipelines, which can lead to error propagation. This paper presents a unified end-to-end framework that extends the Whisper encoder-decoder architecture to jointly model ASR and child-adult speaker role diarization. The proposed approach integrates: (i) a serialized output training","authors_text":"Anfeng Xu, Catherine Lord, Shrikanth Narayanan, Somer Bishop, Tiantian Feng","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-25T01:00:41Z","title":"End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17640","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":"sha256:85a9470d01855e3a04b034ba1571d2cf5380f14fe5e7ce90fdba7caebcbef3e7","target":"record","created_at":"2026-08-11T02:18:46Z","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":"d68f80c15112d20b1a3aee2fa08f95e8116defce65ec819a038f875ec0ef0e69","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-25T01:00:41Z","title_canon_sha256":"4ab934f8f0b116ff00f49f789f5bbfd2624bef69383d4c4cd75407ea51cab429"},"schema_version":"1.0","source":{"id":"2601.17640","kind":"arxiv","version":2}},"canonical_sha256":"6cded2dcb6e5d2a1cc236f3d5807203c03cde0b7e0ef2bf2401365c9564d05f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cded2dcb6e5d2a1cc236f3d5807203c03cde0b7e0ef2bf2401365c9564d05f6","first_computed_at":"2026-08-11T02:18:46.882133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:18:46.882133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GhJHtbYju3J8jYjwJKEp/Ptz2/uuEhPd8wRbBZHGGvTPZ5MtsqcuOHeSApJBczfDeSo4tp1YGCVHnKmRXhA/Dw==","signature_status":"signed_v1","signed_at":"2026-08-11T02:18:46.883796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.17640","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85a9470d01855e3a04b034ba1571d2cf5380f14fe5e7ce90fdba7caebcbef3e7","sha256:68138004e73a26c5f437b33e690d832329bfe93c2309ce78d37b24d0dc5068c7"],"state_sha256":"18d3cdfcfc195d562ead3177630fe306546e1f6b45d3c2c041224b025a5f8317"}