{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QNPQYZTPIEUTSH4HWJBZMIT3DR","short_pith_number":"pith:QNPQYZTP","canonical_record":{"source":{"id":"1910.14080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-30T18:47:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3df75aea5c2938124e2eb924af6bc4f1f15a13a2962906748b6f0df1f5614538","abstract_canon_sha256":"584cfb5f8c76c2a2e6544c319c663879023dd8745d8d76ae76d93cdf796af83f"},"schema_version":"1.0"},"canonical_sha256":"835f0c666f4129391f87b24396227b1c76687024f502cc7dcfdac80188e464c0","source":{"kind":"arxiv","id":"1910.14080","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.14080","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"arxiv_version","alias_value":"1910.14080v2","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14080","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"pith_short_12","alias_value":"QNPQYZTPIEUT","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"pith_short_16","alias_value":"QNPQYZTPIEUTSH4H","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"pith_short_8","alias_value":"QNPQYZTP","created_at":"2026-07-05T07:52:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QNPQYZTPIEUTSH4HWJBZMIT3DR","target":"record","payload":{"canonical_record":{"source":{"id":"1910.14080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-30T18:47:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3df75aea5c2938124e2eb924af6bc4f1f15a13a2962906748b6f0df1f5614538","abstract_canon_sha256":"584cfb5f8c76c2a2e6544c319c663879023dd8745d8d76ae76d93cdf796af83f"},"schema_version":"1.0"},"canonical_sha256":"835f0c666f4129391f87b24396227b1c76687024f502cc7dcfdac80188e464c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:05.684674Z","signature_b64":"L2DkmDCvp1tK1sQXNG8dgi+veGGRPRhTiexeeSMBPD1qdw50xjE++2AbOfgl3NKUouIoyhxpSTeUWf+zydFZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"835f0c666f4129391f87b24396227b1c76687024f502cc7dcfdac80188e464c0","last_reissued_at":"2026-07-05T07:52:05.684123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:05.684123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.14080","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:52:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4lyo3uNgPgV4eD0PW5VBP2RDBZ7ohsUsIs6tOtHKaIn8XpNmBE7PRZonhkW6zDmDwCLv6X+SIbUpVGdy1ls/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:22:33.884214Z"},"content_sha256":"067f4cd72d196b095d77c32acb5fa6a283fafbfc2b00c0b77052ff9732659b27","schema_version":"1.0","event_id":"sha256:067f4cd72d196b095d77c32acb5fa6a283fafbfc2b00c0b77052ff9732659b27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QNPQYZTPIEUTSH4HWJBZMIT3DR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Text Denoising with Masked Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haoming Jiang, Yifu Sun","submitted_at":"2019-10-30T18:47:37Z","abstract_excerpt":"Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual text denoising algorithm based on the ready-to-use masked language model. The proposed algorithm does not require retraining of the model and can be integrated into any NLP system without additional training on paired cleaning training data. We evaluate our method under synthetic noise and natural noise and show that the proposed algorithm can use context infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14080","kind":"arxiv","version":2},"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/1910.14080/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":"2026-07-05T07:52:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RpetfNiYjHFx0wShdEpM5qg79tgFBlNZb1/CZU0ZSnfGMbbSO5bKvNoZflrKHzKHECZg3jpAsuzRXgQ3PoIjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:22:33.884707Z"},"content_sha256":"856e2014bf594b3c635b5edcf117bff23eaba3c55423235588c86c4087f47d27","schema_version":"1.0","event_id":"sha256:856e2014bf594b3c635b5edcf117bff23eaba3c55423235588c86c4087f47d27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNPQYZTPIEUTSH4HWJBZMIT3DR/bundle.json","state_url":"https://pith.science/pith/QNPQYZTPIEUTSH4HWJBZMIT3DR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNPQYZTPIEUTSH4HWJBZMIT3DR/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":"2026-08-09T17:22:33Z","links":{"resolver":"https://pith.science/pith/QNPQYZTPIEUTSH4HWJBZMIT3DR","bundle":"https://pith.science/pith/QNPQYZTPIEUTSH4HWJBZMIT3DR/bundle.json","state":"https://pith.science/pith/QNPQYZTPIEUTSH4HWJBZMIT3DR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNPQYZTPIEUTSH4HWJBZMIT3DR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QNPQYZTPIEUTSH4HWJBZMIT3DR","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":"584cfb5f8c76c2a2e6544c319c663879023dd8745d8d76ae76d93cdf796af83f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-30T18:47:37Z","title_canon_sha256":"3df75aea5c2938124e2eb924af6bc4f1f15a13a2962906748b6f0df1f5614538"},"schema_version":"1.0","source":{"id":"1910.14080","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.14080","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"arxiv_version","alias_value":"1910.14080v2","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14080","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"pith_short_12","alias_value":"QNPQYZTPIEUT","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"pith_short_16","alias_value":"QNPQYZTPIEUTSH4H","created_at":"2026-07-05T07:52:05Z"},{"alias_kind":"pith_short_8","alias_value":"QNPQYZTP","created_at":"2026-07-05T07:52:05Z"}],"graph_snapshots":[{"event_id":"sha256:856e2014bf594b3c635b5edcf117bff23eaba3c55423235588c86c4087f47d27","target":"graph","created_at":"2026-07-05T07:52:05Z","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/1910.14080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual text denoising algorithm based on the ready-to-use masked language model. The proposed algorithm does not require retraining of the model and can be integrated into any NLP system without additional training on paired cleaning training data. We evaluate our method under synthetic noise and natural noise and show that the proposed algorithm can use context infor","authors_text":"Haoming Jiang, Yifu Sun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-30T18:47:37Z","title":"Contextual Text Denoising with Masked Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14080","kind":"arxiv","version":2},"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":"sha256:067f4cd72d196b095d77c32acb5fa6a283fafbfc2b00c0b77052ff9732659b27","target":"record","created_at":"2026-07-05T07:52:05Z","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":"584cfb5f8c76c2a2e6544c319c663879023dd8745d8d76ae76d93cdf796af83f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-30T18:47:37Z","title_canon_sha256":"3df75aea5c2938124e2eb924af6bc4f1f15a13a2962906748b6f0df1f5614538"},"schema_version":"1.0","source":{"id":"1910.14080","kind":"arxiv","version":2}},"canonical_sha256":"835f0c666f4129391f87b24396227b1c76687024f502cc7dcfdac80188e464c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"835f0c666f4129391f87b24396227b1c76687024f502cc7dcfdac80188e464c0","first_computed_at":"2026-07-05T07:52:05.684123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:05.684123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L2DkmDCvp1tK1sQXNG8dgi+veGGRPRhTiexeeSMBPD1qdw50xjE++2AbOfgl3NKUouIoyhxpSTeUWf+zydFZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:05.684674Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.14080","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:067f4cd72d196b095d77c32acb5fa6a283fafbfc2b00c0b77052ff9732659b27","sha256:856e2014bf594b3c635b5edcf117bff23eaba3c55423235588c86c4087f47d27"],"state_sha256":"1f9f1bf01d8183e8e8ace56f727f9af1de75f7e05c6a47ce3b2ab69ac3b76a96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Pg0SyRiL/g7t2IvvqBTeknC9Bj0Wj1Aer5711YRvsEOfs2637qu7amhc1KBvBnfAFMsDe06OnuyTOWR0EA7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:22:33.888397Z","bundle_sha256":"d4328f38672e2fde092d8dfe04463492052e996b36c1712fb2bda3fdc44ec5cc"}}