{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EIB6FD5ER6ZGWQ2AGRLJXWFYDS","short_pith_number":"pith:EIB6FD5E","schema_version":"1.0","canonical_sha256":"2203e28fa48fb26b434034569bd8b81ca41ac3cee898f1db9f7ab5a8de213e5d","source":{"kind":"arxiv","id":"2202.00470","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.00470","created_at":"2026-07-05T03:53:22.316222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00470v1","created_at":"2026-07-05T03:53:22.316222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00470","created_at":"2026-07-05T03:53:22.316222+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIB6FD5ER6ZG","created_at":"2026-07-05T03:53:22.316222+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIB6FD5ER6ZGWQ2A","created_at":"2026-07-05T03:53:22.316222+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIB6FD5E","created_at":"2026-07-05T03:53:22.316222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS","json":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS.json","graph_json":"https://pith.science/api/pith-number/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/graph.json","events_json":"https://pith.science/api/pith-number/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/events.json","paper":"https://pith.science/paper/EIB6FD5E"},"agent_actions":{"view_html":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS","download_json":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS.json","view_paper":"https://pith.science/paper/EIB6FD5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00470&json=true","fetch_graph":"https://pith.science/api/pith-number/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/graph.json","fetch_events":"https://pith.science/api/pith-number/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/action/storage_attestation","attest_author":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/action/author_attestation","sign_citation":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/action/citation_signature","submit_replication":"https://pith.science/pith/EIB6FD5ER6ZGWQ2AGRLJXWFYDS/action/replication_record"}},"created_at":"2026-07-05T03:53:22.316222+00:00","updated_at":"2026-07-05T03:53:22.316222+00:00"}