{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EIB6FD5ER6ZGWQ2AGRLJXWFYDS","short_pith_number":"pith:EIB6FD5E","canonical_record":{"source":{"id":"2202.00470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T21:56:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63eebe23321a1745b57dccefe119764eb9e8c8774c76650b60858380ab61fd09","abstract_canon_sha256":"843c7620957890d833c10ccd37970ecf91c6ed5e2b11e25a8ec2ae302330a78f"},"schema_version":"1.0"},"canonical_sha256":"2203e28fa48fb26b434034569bd8b81ca41ac3cee898f1db9f7ab5a8de213e5d","source":{"kind":"arxiv","id":"2202.00470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00470","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00470v1","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00470","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"EIB6FD5ER6ZG","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"EIB6FD5ER6ZGWQ2A","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"EIB6FD5E","created_at":"2026-07-05T03:53:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EIB6FD5ER6ZGWQ2AGRLJXWFYDS","target":"record","payload":{"canonical_record":{"source":{"id":"2202.00470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T21:56:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63eebe23321a1745b57dccefe119764eb9e8c8774c76650b60858380ab61fd09","abstract_canon_sha256":"843c7620957890d833c10ccd37970ecf91c6ed5e2b11e25a8ec2ae302330a78f"},"schema_version":"1.0"},"canonical_sha256":"2203e28fa48fb26b434034569bd8b81ca41ac3cee898f1db9f7ab5a8de213e5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:22.316576Z","signature_b64":"Mu4mZXJWs/Oj7xP1rXX+92pk9EsGGaSs1Jhd9NiFaQDDjFUEV1QtcI3a2rVybt2a4CSUebjAhHL01NtFjlwHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2203e28fa48fb26b434034569bd8b81ca41ac3cee898f1db9f7ab5a8de213e5d","last_reissued_at":"2026-07-05T03:53:22.316153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:22.316153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.00470","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":"2026-07-05T03:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gt5X4c4u2axETrea4tA6wZL1BfQymmyt94oKGsl1dy04uXJ3p31Q42jzn1NvoV95xs9XJwclch+6oFmU0WeHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:18.528834Z"},"content_sha256":"591c7ad8fbcb1ac1d4aa83c3d448a85d394dda0b28411bf3b1b04362e68d6a14","schema_version":"1.0","event_id":"sha256:591c7ad8fbcb1ac1d4aa83c3d448a85d394dda0b28411bf3b1b04362e68d6a14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EIB6FD5ER6ZGWQ2AGRLJXWFYDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Assessment of the Impact of OCR Noise on Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Giovanni Colavizza, Konstantin Todorov","submitted_at":"2022-01-26T21:56:14Z","abstract_excerpt":"Neural language models are the backbone of modern-day natural language processing applications. Their use on textual heritage collections which have undergone Optical Character Recognition (OCR) is therefore also increasing. Nevertheless, our understanding of the impact OCR noise could have on language models is still limited. We perform an assessment of the impact OCR noise has on a variety of language models, using data in Dutch, English, French and German. We find that OCR noise poses a significant obstacle to language modelling, with language models increasingly diverging from their noisel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00470","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/2202.00470/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":"2026-07-05T03:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8FVoTE4cp17+w2Uyd2qM85xxbvcOGY4g+R8xQggJC3j3HtdWaNWEoKvp8WnkQqRuCd/IEL2rgsc4yBcUbeoeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:18.529344Z"},"content_sha256":"0196c639783a2627a69af1a3a5255ca8ee5aafdbd44a13163ef4be8674763ed7","schema_version":"1.0","event_id":"sha256:0196c639783a2627a69af1a3a5255ca8ee5aafdbd44a13163ef4be8674763ed7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/bundle.json","state_url":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/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":"2026-08-04T17:30:18Z","links":{"resolver":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS","bundle":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/bundle.json","state":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EIB6FD5ER6ZGWQ2AGRLJXWFYDS","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":"843c7620957890d833c10ccd37970ecf91c6ed5e2b11e25a8ec2ae302330a78f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T21:56:14Z","title_canon_sha256":"63eebe23321a1745b57dccefe119764eb9e8c8774c76650b60858380ab61fd09"},"schema_version":"1.0","source":{"id":"2202.00470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00470","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00470v1","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00470","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"EIB6FD5ER6ZG","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"EIB6FD5ER6ZGWQ2A","created_at":"2026-07-05T03:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"EIB6FD5E","created_at":"2026-07-05T03:53:22Z"}],"graph_snapshots":[{"event_id":"sha256:0196c639783a2627a69af1a3a5255ca8ee5aafdbd44a13163ef4be8674763ed7","target":"graph","created_at":"2026-07-05T03:53:22Z","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/2202.00470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural language models are the backbone of modern-day natural language processing applications. Their use on textual heritage collections which have undergone Optical Character Recognition (OCR) is therefore also increasing. Nevertheless, our understanding of the impact OCR noise could have on language models is still limited. We perform an assessment of the impact OCR noise has on a variety of language models, using data in Dutch, English, French and German. We find that OCR noise poses a significant obstacle to language modelling, with language models increasingly diverging from their noisel","authors_text":"Giovanni Colavizza, Konstantin Todorov","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T21:56:14Z","title":"An Assessment of the Impact of OCR Noise on Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00470","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":"sha256:591c7ad8fbcb1ac1d4aa83c3d448a85d394dda0b28411bf3b1b04362e68d6a14","target":"record","created_at":"2026-07-05T03:53:22Z","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":"843c7620957890d833c10ccd37970ecf91c6ed5e2b11e25a8ec2ae302330a78f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-26T21:56:14Z","title_canon_sha256":"63eebe23321a1745b57dccefe119764eb9e8c8774c76650b60858380ab61fd09"},"schema_version":"1.0","source":{"id":"2202.00470","kind":"arxiv","version":1}},"canonical_sha256":"2203e28fa48fb26b434034569bd8b81ca41ac3cee898f1db9f7ab5a8de213e5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2203e28fa48fb26b434034569bd8b81ca41ac3cee898f1db9f7ab5a8de213e5d","first_computed_at":"2026-07-05T03:53:22.316153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:53:22.316153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mu4mZXJWs/Oj7xP1rXX+92pk9EsGGaSs1Jhd9NiFaQDDjFUEV1QtcI3a2rVybt2a4CSUebjAhHL01NtFjlwHBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:53:22.316576Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:591c7ad8fbcb1ac1d4aa83c3d448a85d394dda0b28411bf3b1b04362e68d6a14","sha256:0196c639783a2627a69af1a3a5255ca8ee5aafdbd44a13163ef4be8674763ed7"],"state_sha256":"baabf23c17a052a99a8cdf6879209476674589c67834547d3c000521e44721dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eP9n+Xdg7KbFQCLTZWStN6rxF3Wa/d5jAi6d78kTL+aozo9YLflR88vKtgZP4nA3jZilRNnMj1NdcuXL3TWfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:30:18.534327Z","bundle_sha256":"99beb83b0f56f8420fd50c6b429dd0fab960d3d9df87a1592ee26df4363872c2"}}