{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3YAY5J2SGEHFO7QSZWKIP4QTNL","short_pith_number":"pith:3YAY5J2S","canonical_record":{"source":{"id":"2305.17721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T13:19:12Z","cross_cats_sorted":[],"title_canon_sha256":"232b347e6e8dbec943dc9a5fc8c89ae41897a51ce61d3d9c250ae0d1ceaf891f","abstract_canon_sha256":"e013af93bdae3a2a36f215705485cbb0d3d56c9abe5e09f7fdf2715432b4bdf4"},"schema_version":"1.0"},"canonical_sha256":"de018ea752310e577e12cd9487f2136afb2f7d73fa73e9af2c64d1b56933dc9d","source":{"kind":"arxiv","id":"2305.17721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17721","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17721v1","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17721","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"3YAY5J2SGEHF","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"3YAY5J2SGEHFO7QS","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"3YAY5J2S","created_at":"2026-07-05T06:14:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3YAY5J2SGEHFO7QSZWKIP4QTNL","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T13:19:12Z","cross_cats_sorted":[],"title_canon_sha256":"232b347e6e8dbec943dc9a5fc8c89ae41897a51ce61d3d9c250ae0d1ceaf891f","abstract_canon_sha256":"e013af93bdae3a2a36f215705485cbb0d3d56c9abe5e09f7fdf2715432b4bdf4"},"schema_version":"1.0"},"canonical_sha256":"de018ea752310e577e12cd9487f2136afb2f7d73fa73e9af2c64d1b56933dc9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:47.790530Z","signature_b64":"SWn7SLWZJQhFQnZPnK3anPU9J2PTUTfZPes3x25CfhODGCXhJQzzmHvo6jJGPegWWQnlxZ0wmlMe/VzAAbXvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de018ea752310e577e12cd9487f2136afb2f7d73fa73e9af2c64d1b56933dc9d","last_reissued_at":"2026-07-05T06:14:47.790065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:47.790065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17721","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":"2026-07-05T06:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/1IJAOOcfSqKyzo0ys8gDWmHrjQaR36RJ17FeGGlQBc2vBupV7JCu/v/E7is23XWN/+C0vt0DAZrzaq3qI9SDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:31:33.009383Z"},"content_sha256":"cf333e96484a6e14b18e9d25d00ecc3720aa02e20139852240527366882d7ab2","schema_version":"1.0","event_id":"sha256:cf333e96484a6e14b18e9d25d00ecc3720aa02e20139852240527366882d7ab2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3YAY5J2SGEHFO7QSZWKIP4QTNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Masked Language Modeling for Chinese Spelling Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Hongqiu Wu, Shaohua Zhang, Yuchen Zhang","submitted_at":"2023-05-28T13:19:12Z","abstract_excerpt":"In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model while under-fit the language model, resulting in poor generalization to out-of-distribution error patterns. Given that BERT is the backbone of most CSC models, this phenomenon has a significant negative impact. To address this issue, we are releasing a multi-domain benchmark LEMON, with higher quality and diversity than existing benchmarks, to allow a comprehens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17721","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/2305.17721/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":"2026-07-05T06:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqlejaIY3LSCcD+CE2PKhQOXSftZVucm6Sp3T+UtWuoryheEbogcvVqwCUCzVanMZgTMepOjpS4YyA83qfnsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:31:33.009886Z"},"content_sha256":"e8d2b2a8188b3c7a33b0b2b2ff3e2543be69a95418081b5e2ec66e125cd93f06","schema_version":"1.0","event_id":"sha256:e8d2b2a8188b3c7a33b0b2b2ff3e2543be69a95418081b5e2ec66e125cd93f06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YAY5J2SGEHFO7QSZWKIP4QTNL/bundle.json","state_url":"https://pith.science/pith/3YAY5J2SGEHFO7QSZWKIP4QTNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YAY5J2SGEHFO7QSZWKIP4QTNL/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":"2026-08-12T09:31:33Z","links":{"resolver":"https://pith.science/pith/3YAY5J2SGEHFO7QSZWKIP4QTNL","bundle":"https://pith.science/pith/3YAY5J2SGEHFO7QSZWKIP4QTNL/bundle.json","state":"https://pith.science/pith/3YAY5J2SGEHFO7QSZWKIP4QTNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YAY5J2SGEHFO7QSZWKIP4QTNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3YAY5J2SGEHFO7QSZWKIP4QTNL","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":"e013af93bdae3a2a36f215705485cbb0d3d56c9abe5e09f7fdf2715432b4bdf4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T13:19:12Z","title_canon_sha256":"232b347e6e8dbec943dc9a5fc8c89ae41897a51ce61d3d9c250ae0d1ceaf891f"},"schema_version":"1.0","source":{"id":"2305.17721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17721","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17721v1","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17721","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"3YAY5J2SGEHF","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"3YAY5J2SGEHFO7QS","created_at":"2026-07-05T06:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"3YAY5J2S","created_at":"2026-07-05T06:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:e8d2b2a8188b3c7a33b0b2b2ff3e2543be69a95418081b5e2ec66e125cd93f06","target":"graph","created_at":"2026-07-05T06:14:47Z","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/2305.17721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model while under-fit the language model, resulting in poor generalization to out-of-distribution error patterns. Given that BERT is the backbone of most CSC models, this phenomenon has a significant negative impact. To address this issue, we are releasing a multi-domain benchmark LEMON, with higher quality and diversity than existing benchmarks, to allow a comprehens","authors_text":"Hai Zhao, Hongqiu Wu, Shaohua Zhang, Yuchen Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T13:19:12Z","title":"Rethinking Masked Language Modeling for Chinese Spelling Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17721","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:cf333e96484a6e14b18e9d25d00ecc3720aa02e20139852240527366882d7ab2","target":"record","created_at":"2026-07-05T06:14:47Z","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":"e013af93bdae3a2a36f215705485cbb0d3d56c9abe5e09f7fdf2715432b4bdf4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T13:19:12Z","title_canon_sha256":"232b347e6e8dbec943dc9a5fc8c89ae41897a51ce61d3d9c250ae0d1ceaf891f"},"schema_version":"1.0","source":{"id":"2305.17721","kind":"arxiv","version":1}},"canonical_sha256":"de018ea752310e577e12cd9487f2136afb2f7d73fa73e9af2c64d1b56933dc9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de018ea752310e577e12cd9487f2136afb2f7d73fa73e9af2c64d1b56933dc9d","first_computed_at":"2026-07-05T06:14:47.790065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:47.790065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWn7SLWZJQhFQnZPnK3anPU9J2PTUTfZPes3x25CfhODGCXhJQzzmHvo6jJGPegWWQnlxZ0wmlMe/VzAAbXvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:47.790530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf333e96484a6e14b18e9d25d00ecc3720aa02e20139852240527366882d7ab2","sha256:e8d2b2a8188b3c7a33b0b2b2ff3e2543be69a95418081b5e2ec66e125cd93f06"],"state_sha256":"faa4ebc30c20b0ca44738f064f4cd62893a21bebd1b06b9bc3647becedd7687a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBhqN3BJj3jTfpm1JFgNJ/Ual62qlLC9BIF8I6Jy+N0FR/gr5zSpXyF6HKNWQQTH1/9UP9eg7KfLoB108IUtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T09:31:33.015309Z","bundle_sha256":"493a52961b1477801b5d2771ff8718e46fac47f17a35c809fb2fb1ab5172bbdc"}}