{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WFROJZIGTYWHNDWFWKJFLQVJSW","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":"8364ea58fc0ced079b439356b697f0c5c7033989935b55652f7e438b17be49fe","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-23T02:54:52Z","title_canon_sha256":"b887a5bccc360d5021f4a3de1699c6122c24c2795c00339f9f2ff8de694aec4a"},"schema_version":"1.0","source":{"id":"2505.17410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17410","created_at":"2026-07-05T11:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17410v1","created_at":"2026-07-05T11:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17410","created_at":"2026-07-05T11:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"WFROJZIGTYWH","created_at":"2026-07-05T11:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"WFROJZIGTYWHNDWF","created_at":"2026-07-05T11:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"WFROJZIG","created_at":"2026-07-05T11:08:25Z"}],"graph_snapshots":[{"event_id":"sha256:8fee7e4c017460fd20a090ef0e30b08450992f34b7c8731c59a80aa2a2373e2b","target":"graph","created_at":"2026-07-05T11:08:25Z","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/2505.17410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative error correction (GER) with large language models (LLMs) has emerged as an effective post-processing approach to improve automatic speech recognition (ASR) performance. However, it often struggles with rare or domain-specific words due to limited training data. Furthermore, existing LLM-based GER approaches primarily rely on textual information, neglecting phonetic cues, which leads to over-correction. To address these issues, we propose a novel LLM-based GER approach that targets rare words and incorporates phonetic information. First, we generate synthetic data to contain rare wor","authors_text":"Hiroaki Kokubo, Masaaki Yamamoto, Natsuo Yamashita, Yohei Kawaguchi","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-23T02:54:52Z","title":"LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17410","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:eeae6f8cf1ec1105572c9fd005518a21fdba79c1247257e311c14f245abf7c97","target":"record","created_at":"2026-07-05T11:08:25Z","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":"8364ea58fc0ced079b439356b697f0c5c7033989935b55652f7e438b17be49fe","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-23T02:54:52Z","title_canon_sha256":"b887a5bccc360d5021f4a3de1699c6122c24c2795c00339f9f2ff8de694aec4a"},"schema_version":"1.0","source":{"id":"2505.17410","kind":"arxiv","version":1}},"canonical_sha256":"b162e4e5069e2c768ec5b29255c2a9958937636d1071d8cf78b4ff8fc4a2b956","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b162e4e5069e2c768ec5b29255c2a9958937636d1071d8cf78b4ff8fc4a2b956","first_computed_at":"2026-07-05T11:08:25.731417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:25.731417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5gP1zUreqIIgXfoDxV7DUVeCbWd+Vt56nkTfynNExwthr4mLtsoUUZEO+4sD5jzry6vaXCWQ3HHp4W5qwYASBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:25.731896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeae6f8cf1ec1105572c9fd005518a21fdba79c1247257e311c14f245abf7c97","sha256:8fee7e4c017460fd20a090ef0e30b08450992f34b7c8731c59a80aa2a2373e2b"],"state_sha256":"3a18de26983749c451e48ea6d1f5d82caf787bfad0368748e55decb07dde1287"}