{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KCF5NZISDCW73UVLOH2ZI2G3SA","short_pith_number":"pith:KCF5NZIS","canonical_record":{"source":{"id":"2412.03230","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:28:52Z","cross_cats_sorted":[],"title_canon_sha256":"acebf4a9a2f556e05d8dd747cac8a644d8e9b3c6aa48e8677d1caefa382b6a3a","abstract_canon_sha256":"b35fecf91acdf4dea76eacb707da72977d644a31e34436956814942607aa5100"},"schema_version":"1.0"},"canonical_sha256":"508bd6e51218adfdd2ab71f59468db901953dba8de40e37d5eaacb41490e2aaf","source":{"kind":"arxiv","id":"2412.03230","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03230","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03230v3","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03230","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"KCF5NZISDCW7","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"KCF5NZISDCW73UVL","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"KCF5NZIS","created_at":"2026-07-17T01:21:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KCF5NZISDCW73UVLOH2ZI2G3SA","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03230","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:28:52Z","cross_cats_sorted":[],"title_canon_sha256":"acebf4a9a2f556e05d8dd747cac8a644d8e9b3c6aa48e8677d1caefa382b6a3a","abstract_canon_sha256":"b35fecf91acdf4dea76eacb707da72977d644a31e34436956814942607aa5100"},"schema_version":"1.0"},"canonical_sha256":"508bd6e51218adfdd2ab71f59468db901953dba8de40e37d5eaacb41490e2aaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:40.345110Z","signature_b64":"BH6ddeUfwCC4pDXcHULJZ+/BI6jwk70Y5PMVpbYxRckCHPvBtLvDEykCkMoGmyfrdiE+pvheSFavEehoRIARAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"508bd6e51218adfdd2ab71f59468db901953dba8de40e37d5eaacb41490e2aaf","last_reissued_at":"2026-07-17T01:21:40.344122Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:40.344122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03230","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-17T01:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4k1sIJVPxWRfz9S5XmwfgiIr0xfoHIaY2QoFRdCXmCuUeXUiydDkvSafxHOsGE+YBKr0lH+7gDMOwqZI6tgmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:21:03.121199Z"},"content_sha256":"5f99c46bd9b7df36cf72b67de89018340152ca7fb0db021b53efd15fb6c7b7f8","schema_version":"1.0","event_id":"sha256:5f99c46bd9b7df36cf72b67de89018340152ca7fb0db021b53efd15fb6c7b7f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KCF5NZISDCW73UVLOH2ZI2G3SA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bojun Zhang, Junhong Liang","submitted_at":"2024-12-04T11:28:52Z","abstract_excerpt":"Chinese ASR correction is challenging because errors are often \\emph{phonetic} (many characters share similar Pinyin) while the correction model must also obey a \\emph{length constraint} under noisy N-best hypotheses. Existing approaches either exploit Pinyin only at the prompt/feature level without integrating it into model representations or rely on generative decoding that can drift in length. We propose \\textbf{PERL}, a \\textbf{constrained rephrasing pipeline} for Chinese N-best ASR correction that (i) predicts the target length and enforces it via mask budgeting, and (ii) fuses \\emph{sema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03230","kind":"arxiv","version":3},"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/2412.03230/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":"2026-07-17T01:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14dPZ3m7NFg6SRUgNdhZnmf2PtHWvdiQMs6ckldTrfhupf23oKU+Is7Y2hyIxEGfAUjE90fte/eLOk9dCrpTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:21:03.121669Z"},"content_sha256":"ce98e147babd80b88a7ff47dc46885e9c325b5046edc68db364d3bab33f02dbf","schema_version":"1.0","event_id":"sha256:ce98e147babd80b88a7ff47dc46885e9c325b5046edc68db364d3bab33f02dbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KCF5NZISDCW73UVLOH2ZI2G3SA/bundle.json","state_url":"https://pith.science/pith/KCF5NZISDCW73UVLOH2ZI2G3SA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KCF5NZISDCW73UVLOH2ZI2G3SA/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":"2026-08-18T08:21:03Z","links":{"resolver":"https://pith.science/pith/KCF5NZISDCW73UVLOH2ZI2G3SA","bundle":"https://pith.science/pith/KCF5NZISDCW73UVLOH2ZI2G3SA/bundle.json","state":"https://pith.science/pith/KCF5NZISDCW73UVLOH2ZI2G3SA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KCF5NZISDCW73UVLOH2ZI2G3SA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KCF5NZISDCW73UVLOH2ZI2G3SA","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":"b35fecf91acdf4dea76eacb707da72977d644a31e34436956814942607aa5100","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:28:52Z","title_canon_sha256":"acebf4a9a2f556e05d8dd747cac8a644d8e9b3c6aa48e8677d1caefa382b6a3a"},"schema_version":"1.0","source":{"id":"2412.03230","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03230","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03230v3","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03230","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"KCF5NZISDCW7","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"KCF5NZISDCW73UVL","created_at":"2026-07-17T01:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"KCF5NZIS","created_at":"2026-07-17T01:21:40Z"}],"graph_snapshots":[{"event_id":"sha256:ce98e147babd80b88a7ff47dc46885e9c325b5046edc68db364d3bab33f02dbf","target":"graph","created_at":"2026-07-17T01:21:40Z","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/2412.03230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chinese ASR correction is challenging because errors are often \\emph{phonetic} (many characters share similar Pinyin) while the correction model must also obey a \\emph{length constraint} under noisy N-best hypotheses. Existing approaches either exploit Pinyin only at the prompt/feature level without integrating it into model representations or rely on generative decoding that can drift in length. We propose \\textbf{PERL}, a \\textbf{constrained rephrasing pipeline} for Chinese N-best ASR correction that (i) predicts the target length and enforces it via mask budgeting, and (ii) fuses \\emph{sema","authors_text":"Bojun Zhang, Junhong Liang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:28:52Z","title":"PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03230","kind":"arxiv","version":3},"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":"sha256:5f99c46bd9b7df36cf72b67de89018340152ca7fb0db021b53efd15fb6c7b7f8","target":"record","created_at":"2026-07-17T01:21:40Z","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":"b35fecf91acdf4dea76eacb707da72977d644a31e34436956814942607aa5100","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:28:52Z","title_canon_sha256":"acebf4a9a2f556e05d8dd747cac8a644d8e9b3c6aa48e8677d1caefa382b6a3a"},"schema_version":"1.0","source":{"id":"2412.03230","kind":"arxiv","version":3}},"canonical_sha256":"508bd6e51218adfdd2ab71f59468db901953dba8de40e37d5eaacb41490e2aaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"508bd6e51218adfdd2ab71f59468db901953dba8de40e37d5eaacb41490e2aaf","first_computed_at":"2026-07-17T01:21:40.344122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:40.344122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BH6ddeUfwCC4pDXcHULJZ+/BI6jwk70Y5PMVpbYxRckCHPvBtLvDEykCkMoGmyfrdiE+pvheSFavEehoRIARAw==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:40.345110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03230","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f99c46bd9b7df36cf72b67de89018340152ca7fb0db021b53efd15fb6c7b7f8","sha256:ce98e147babd80b88a7ff47dc46885e9c325b5046edc68db364d3bab33f02dbf"],"state_sha256":"3d2cd419db8e3b23015149c7c2d712500b417caa775cf43384661964ab820c6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qyk68QlPh+f4OdydRQshrD914/86OI3SeK74/RSif5K7vNMZp5nygNWljTfUnGg9z3Q+cavgvCnTIBAWcaRFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:21:03.124782Z","bundle_sha256":"f497d4d44800d87e6ebba9e291ab9a9273bc7e22530c01e3d44596a50731e901"}}