{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VVBORYNS5M5UI4PB5QNRF7T6MA","short_pith_number":"pith:VVBORYNS","canonical_record":{"source":{"id":"2409.13262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T06:50:56Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31d02251785a5d7ccc0070b0427fa1dd028c4027059518bf630958d086ccbf52","abstract_canon_sha256":"2086e5d93e71b52639153f46714c35b50f61c2e09025c67d43c368fcc088fd69"},"schema_version":"1.0"},"canonical_sha256":"ad42e8e1b2eb3b4471e1ec1b12fe7e601a4ed339964550c272d969849559ce8a","source":{"kind":"arxiv","id":"2409.13262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13262","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13262v1","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13262","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"VVBORYNS5M5U","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"VVBORYNS5M5UI4PB","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"VVBORYNS","created_at":"2026-07-05T09:09:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VVBORYNS5M5UI4PB5QNRF7T6MA","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T06:50:56Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31d02251785a5d7ccc0070b0427fa1dd028c4027059518bf630958d086ccbf52","abstract_canon_sha256":"2086e5d93e71b52639153f46714c35b50f61c2e09025c67d43c368fcc088fd69"},"schema_version":"1.0"},"canonical_sha256":"ad42e8e1b2eb3b4471e1ec1b12fe7e601a4ed339964550c272d969849559ce8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:31.936896Z","signature_b64":"OlXrM1T5/HjJ3vo9ZIurad9Li+K5Bk2hSBHqMbYqv/7JrzhJxOkduncqkkeiLSaXwCjrnQByVNEDhwTI9fORCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad42e8e1b2eb3b4471e1ec1b12fe7e601a4ed339964550c272d969849559ce8a","last_reissued_at":"2026-07-05T09:09:31.936409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:31.936409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13262","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNDYkwdP2QapTZWZUpikWYplI8OJ+CVayu9/MorqOL9xznkeDfHMZA8QjczBoMOIXpklr7kw8VN1YmQV7s4kBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:09:55.183631Z"},"content_sha256":"b5cfbf113b3637de4bddaf58126a39e8daf37db071ffe4d505e531b64c702ed4","schema_version":"1.0","event_id":"sha256:b5cfbf113b3637de4bddaf58126a39e8daf37db071ffe4d505e531b64c702ed4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VVBORYNS5M5UI4PB5QNRF7T6MA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model Should Understand Pinyin for Chinese ASR Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hao Yang, Huan Zhao, Min Zhang, Wei Tang, Xiaofeng Zhao, Xiaosong Qiao, Yuang Li","submitted_at":"2024-09-20T06:50:56Z","abstract_excerpt":"Large language models can enhance automatic speech recognition systems through generative error correction. In this paper, we propose Pinyin-enhanced GEC, which leverages Pinyi, the phonetic representation of Mandarin Chinese, as supplementary information to improve Chinese ASR error correction. Our approach only utilizes synthetic errors for training and employs the one-best hypothesis during inference. Additionally, we introduce a multitask training approach involving conversion tasks between Pinyin and text to align their feature spaces. Experiments on the Aishell-1 and the Common Voice dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13262","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.13262/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkJF0Q220jaSEnPB40NVVtyoKyXVUgMakXah0b+X53gFyfK5ZS+pX6UbOkFScl47krw/2FdRk7cqKhiIICxaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:09:55.184143Z"},"content_sha256":"3149ec6e82e5df9415b0884c02132b6e511e9ef3e021be46ed30db8c37db3753","schema_version":"1.0","event_id":"sha256:3149ec6e82e5df9415b0884c02132b6e511e9ef3e021be46ed30db8c37db3753"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVBORYNS5M5UI4PB5QNRF7T6MA/bundle.json","state_url":"https://pith.science/pith/VVBORYNS5M5UI4PB5QNRF7T6MA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVBORYNS5M5UI4PB5QNRF7T6MA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T15:09:55Z","links":{"resolver":"https://pith.science/pith/VVBORYNS5M5UI4PB5QNRF7T6MA","bundle":"https://pith.science/pith/VVBORYNS5M5UI4PB5QNRF7T6MA/bundle.json","state":"https://pith.science/pith/VVBORYNS5M5UI4PB5QNRF7T6MA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVBORYNS5M5UI4PB5QNRF7T6MA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VVBORYNS5M5UI4PB5QNRF7T6MA","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":"2086e5d93e71b52639153f46714c35b50f61c2e09025c67d43c368fcc088fd69","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T06:50:56Z","title_canon_sha256":"31d02251785a5d7ccc0070b0427fa1dd028c4027059518bf630958d086ccbf52"},"schema_version":"1.0","source":{"id":"2409.13262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13262","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13262v1","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13262","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"VVBORYNS5M5U","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"VVBORYNS5M5UI4PB","created_at":"2026-07-05T09:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"VVBORYNS","created_at":"2026-07-05T09:09:31Z"}],"graph_snapshots":[{"event_id":"sha256:3149ec6e82e5df9415b0884c02132b6e511e9ef3e021be46ed30db8c37db3753","target":"graph","created_at":"2026-07-05T09:09:31Z","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/2409.13262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models can enhance automatic speech recognition systems through generative error correction. In this paper, we propose Pinyin-enhanced GEC, which leverages Pinyi, the phonetic representation of Mandarin Chinese, as supplementary information to improve Chinese ASR error correction. Our approach only utilizes synthetic errors for training and employs the one-best hypothesis during inference. Additionally, we introduce a multitask training approach involving conversion tasks between Pinyin and text to align their feature spaces. Experiments on the Aishell-1 and the Common Voice dat","authors_text":"Hao Yang, Huan Zhao, Min Zhang, Wei Tang, Xiaofeng Zhao, Xiaosong Qiao, Yuang Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T06:50:56Z","title":"Large Language Model Should Understand Pinyin for Chinese ASR Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13262","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:b5cfbf113b3637de4bddaf58126a39e8daf37db071ffe4d505e531b64c702ed4","target":"record","created_at":"2026-07-05T09:09:31Z","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":"2086e5d93e71b52639153f46714c35b50f61c2e09025c67d43c368fcc088fd69","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T06:50:56Z","title_canon_sha256":"31d02251785a5d7ccc0070b0427fa1dd028c4027059518bf630958d086ccbf52"},"schema_version":"1.0","source":{"id":"2409.13262","kind":"arxiv","version":1}},"canonical_sha256":"ad42e8e1b2eb3b4471e1ec1b12fe7e601a4ed339964550c272d969849559ce8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad42e8e1b2eb3b4471e1ec1b12fe7e601a4ed339964550c272d969849559ce8a","first_computed_at":"2026-07-05T09:09:31.936409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:31.936409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OlXrM1T5/HjJ3vo9ZIurad9Li+K5Bk2hSBHqMbYqv/7JrzhJxOkduncqkkeiLSaXwCjrnQByVNEDhwTI9fORCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:31.936896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5cfbf113b3637de4bddaf58126a39e8daf37db071ffe4d505e531b64c702ed4","sha256:3149ec6e82e5df9415b0884c02132b6e511e9ef3e021be46ed30db8c37db3753"],"state_sha256":"df95d928e49257f08446f315624212b36484f0dc95df1a6e3bf8cdeb8fddcc74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rMuhyB02XG4sk4S0abtKbw7aVAY5n9BLQvP4Sf0SLHxzm9zR8zFODt4nKm4W0Gi2S31KVOMk0dTgBCMNBNXhBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:09:55.189898Z","bundle_sha256":"020467ed449c9ac4202571613f48b1cb79d7b71c3d004ebed91aaf3d4d2594cf"}}