{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PHM4PZIW45CI6YUNRJ47L2ARC2","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":"b133a8e33c924a7b37ac4a06b58c805642423fb326ad24fd32561a319c627cae","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:09:41Z","title_canon_sha256":"48e40298b5513fa0213ab1231c40a275d39df0a041ced515c1eb16d94aef7651"},"schema_version":"1.0","source":{"id":"2108.01129","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01129","created_at":"2026-07-05T03:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01129v1","created_at":"2026-07-05T03:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01129","created_at":"2026-07-05T03:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"PHM4PZIW45CI","created_at":"2026-07-05T03:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"PHM4PZIW45CI6YUN","created_at":"2026-07-05T03:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"PHM4PZIW","created_at":"2026-07-05T03:02:59Z"}],"graph_snapshots":[{"event_id":"sha256:4835cc4c25fea46b36680e5963dc58576934416eb043c5cc77dce3b0935401ba","target":"graph","created_at":"2026-07-05T03:02:59Z","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/2108.01129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach. Unlike English where the writing system is closely related to sound, Chinese characters (Hanzi) represent meaning, not sound. We propose factoring audio -> Hanzi into two sub-tasks: (1) audio -> Pinyin and (2) Pinyin -> Hanzi, where Pinyin is a system of phonetic transcription of standard Chinese. Factoring the audio -> Hanzi task in this way achieves 3.9% CER (character error rate) on the Aishell-1 corpus, the best result reported on this dataset so far.","authors_text":"Dongji Gao, Jiahong Yuan, Kenneth Church, Liang Huang, Renjie Zheng, Xingyu Cai","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:09:41Z","title":"Decoupling recognition and transcription in Mandarin ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01129","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":"sha256:8a058594a1b54efb57694f704bfb5239bd912e58b9d9a68bd2e1c103fc16269f","target":"record","created_at":"2026-07-05T03:02:59Z","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":"b133a8e33c924a7b37ac4a06b58c805642423fb326ad24fd32561a319c627cae","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:09:41Z","title_canon_sha256":"48e40298b5513fa0213ab1231c40a275d39df0a041ced515c1eb16d94aef7651"},"schema_version":"1.0","source":{"id":"2108.01129","kind":"arxiv","version":1}},"canonical_sha256":"79d9c7e516e7448f628d8a79f5e81116a928682a8be70faacb542b7978e28d97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79d9c7e516e7448f628d8a79f5e81116a928682a8be70faacb542b7978e28d97","first_computed_at":"2026-07-05T03:02:59.802647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:02:59.802647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yRPN5uivZ58RyVZeL66I+wKQHxrWCNouQ6dWyR5dgilVj+0cM2vUwcqaUSC4k5K8S/MjL9XwUNuCw7MuiebyDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:02:59.803001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.01129","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a058594a1b54efb57694f704bfb5239bd912e58b9d9a68bd2e1c103fc16269f","sha256:4835cc4c25fea46b36680e5963dc58576934416eb043c5cc77dce3b0935401ba"],"state_sha256":"e97ba7cabb46477d50d2e6e82c62d648480bb525d731440fc97e345fae289ce3"}