{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GMJZGA3Q56KCO5ACN7LSYV54XN","short_pith_number":"pith:GMJZGA3Q","canonical_record":{"source":{"id":"2210.17168","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T09:29:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b76cd50fe8e5576f03dfb1cdde58f447b6b5c0cc26499a5304306a8a1f492bea","abstract_canon_sha256":"fd78a4f98697f4eb684e6748fa11bc3098db8e678b3c32bbc628ce7d5b34cf8e"},"schema_version":"1.0"},"canonical_sha256":"3313930370ef942774026fd72c57bcbb54a266db3d459504427ac790e72597e9","source":{"kind":"arxiv","id":"2210.17168","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.17168","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2210.17168v4","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17168","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"GMJZGA3Q56KC","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"GMJZGA3Q56KCO5AC","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"GMJZGA3Q","created_at":"2026-07-05T05:13:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GMJZGA3Q56KCO5ACN7LSYV54XN","target":"record","payload":{"canonical_record":{"source":{"id":"2210.17168","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T09:29:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b76cd50fe8e5576f03dfb1cdde58f447b6b5c0cc26499a5304306a8a1f492bea","abstract_canon_sha256":"fd78a4f98697f4eb684e6748fa11bc3098db8e678b3c32bbc628ce7d5b34cf8e"},"schema_version":"1.0"},"canonical_sha256":"3313930370ef942774026fd72c57bcbb54a266db3d459504427ac790e72597e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:39.858108Z","signature_b64":"OTsfEZ0q5J6tj+vnIiDUTFacoyY/BxtqXRROKnScY+/TBnX7cJG53qYWxT0H3Is/8TkHSekd+JJVlkgAQEg/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3313930370ef942774026fd72c57bcbb54a266db3d459504427ac790e72597e9","last_reissued_at":"2026-07-05T05:13:39.857651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:39.857651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.17168","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/OYNuVjPWicotw0RwbhKxtlwMi9djsmZs8fW+7HFkeitABfiVn7rCXBkfU319Ly3BnMFB/8OzKGSrpX7BemtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:49:43.866359Z"},"content_sha256":"723ff71323224ca8fa4881a82da75cd624230180d2bd4fec3abda82ed585b00c","schema_version":"1.0","event_id":"sha256:723ff71323224ca8fa4881a82da75cd624230180d2bd4fec3abda82ed585b00c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GMJZGA3Q56KCO5ACN7LSYV54XN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hang Yan, Xiaotian Zhang, Xipeng Qiu, Yu Sun","submitted_at":"2022-10-31T09:29:21Z","abstract_excerpt":"Due to the ambiguity of homophones, Chinese Spell Checking (CSC) has widespread applications. Existing systems typically utilize BERT for text encoding. However, CSC requires the model to account for both phonetic and graphemic information. To adapt BERT to the CSC task, we propose a token-level self-distillation contrastive learning method. We employ BERT to encode both the corrupted and corresponding correct sentence. Then, we use contrastive learning loss to regularize corrupted tokens' hidden states to be closer to counterparts in the correct sentence. On three CSC datasets, we confirmed o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17168","kind":"arxiv","version":4},"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/2210.17168/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":"2026-07-05T05:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wNJ647OhFQcpL/uWtJ6FkVAUMl6FQ5n20FHoGPDkDXdc7pFVxbCYYD4bE1DULbsv9Z3uGFiyygeEHp+GWtzvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:49:43.866895Z"},"content_sha256":"2d67b9d20044d7666c7d2d48d477f63fddd3b5247e0d9dc230ce64ef035f5502","schema_version":"1.0","event_id":"sha256:2d67b9d20044d7666c7d2d48d477f63fddd3b5247e0d9dc230ce64ef035f5502"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GMJZGA3Q56KCO5ACN7LSYV54XN/bundle.json","state_url":"https://pith.science/pith/GMJZGA3Q56KCO5ACN7LSYV54XN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GMJZGA3Q56KCO5ACN7LSYV54XN/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":"2026-08-06T05:49:43Z","links":{"resolver":"https://pith.science/pith/GMJZGA3Q56KCO5ACN7LSYV54XN","bundle":"https://pith.science/pith/GMJZGA3Q56KCO5ACN7LSYV54XN/bundle.json","state":"https://pith.science/pith/GMJZGA3Q56KCO5ACN7LSYV54XN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GMJZGA3Q56KCO5ACN7LSYV54XN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GMJZGA3Q56KCO5ACN7LSYV54XN","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":"fd78a4f98697f4eb684e6748fa11bc3098db8e678b3c32bbc628ce7d5b34cf8e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T09:29:21Z","title_canon_sha256":"b76cd50fe8e5576f03dfb1cdde58f447b6b5c0cc26499a5304306a8a1f492bea"},"schema_version":"1.0","source":{"id":"2210.17168","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.17168","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2210.17168v4","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17168","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"GMJZGA3Q56KC","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"GMJZGA3Q56KCO5AC","created_at":"2026-07-05T05:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"GMJZGA3Q","created_at":"2026-07-05T05:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:2d67b9d20044d7666c7d2d48d477f63fddd3b5247e0d9dc230ce64ef035f5502","target":"graph","created_at":"2026-07-05T05:13:39Z","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/2210.17168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the ambiguity of homophones, Chinese Spell Checking (CSC) has widespread applications. Existing systems typically utilize BERT for text encoding. However, CSC requires the model to account for both phonetic and graphemic information. To adapt BERT to the CSC task, we propose a token-level self-distillation contrastive learning method. We employ BERT to encode both the corrupted and corresponding correct sentence. Then, we use contrastive learning loss to regularize corrupted tokens' hidden states to be closer to counterparts in the correct sentence. On three CSC datasets, we confirmed o","authors_text":"Hang Yan, Xiaotian Zhang, Xipeng Qiu, Yu Sun","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T09:29:21Z","title":"SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17168","kind":"arxiv","version":4},"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":"sha256:723ff71323224ca8fa4881a82da75cd624230180d2bd4fec3abda82ed585b00c","target":"record","created_at":"2026-07-05T05:13:39Z","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":"fd78a4f98697f4eb684e6748fa11bc3098db8e678b3c32bbc628ce7d5b34cf8e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T09:29:21Z","title_canon_sha256":"b76cd50fe8e5576f03dfb1cdde58f447b6b5c0cc26499a5304306a8a1f492bea"},"schema_version":"1.0","source":{"id":"2210.17168","kind":"arxiv","version":4}},"canonical_sha256":"3313930370ef942774026fd72c57bcbb54a266db3d459504427ac790e72597e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3313930370ef942774026fd72c57bcbb54a266db3d459504427ac790e72597e9","first_computed_at":"2026-07-05T05:13:39.857651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:39.857651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OTsfEZ0q5J6tj+vnIiDUTFacoyY/BxtqXRROKnScY+/TBnX7cJG53qYWxT0H3Is/8TkHSekd+JJVlkgAQEg/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:39.858108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.17168","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:723ff71323224ca8fa4881a82da75cd624230180d2bd4fec3abda82ed585b00c","sha256:2d67b9d20044d7666c7d2d48d477f63fddd3b5247e0d9dc230ce64ef035f5502"],"state_sha256":"b5dc9ad179a9f5c098b352392dda5888263e586fce39143b43dab1a843d649cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PNyS1C0/EOmyfL+UfU6LI054nPiNbKirdlVZn2kwW2aoCfeb9RHV6e0ICe/wlj3tvRmOwilu9hfthhAlFWjWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:49:43.870687Z","bundle_sha256":"d877d4dbf74ee0e543426f23ca2cc1d60672dbc7d8c08ff60f0bd3d552ca7d9a"}}