{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DY22ZSHBSSE664EZ4IKCG2PHSI","short_pith_number":"pith:DY22ZSHB","schema_version":"1.0","canonical_sha256":"1e35acc8e19489ef7099e2142369e792040785a92f7251b4a246453091dbf0fc","source":{"kind":"arxiv","id":"2105.07983","version":1},"attestation_state":"computed","paper":{"title":"Unknown-box Approximation to Improve Optical Character Recognition Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Allegra Latimer, Ayantha Randika, Nilanjan Ray, Xiao Xiao","submitted_at":"2021-05-17T16:09:15Z","abstract_excerpt":"Optical character recognition (OCR) is a widely used pattern recognition application in numerous domains. There are several feature-rich, general-purpose OCR solutions available for consumers, which can provide moderate to excellent accuracy levels. However, accuracy can diminish with difficult and uncommon document domains. Preprocessing of document images can be used to minimize the effect of domain shift. In this paper, a novel approach is presented for creating a customized preprocessor for a given OCR engine. Unlike the previous OCR agnostic preprocessing techniques, the proposed approach"},"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":"2105.07983","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-17T16:09:15Z","cross_cats_sorted":[],"title_canon_sha256":"d0f408674146ff0c64c01b0911df86aba859807f2c638a6a2112366011c7b528","abstract_canon_sha256":"055780f7bb093b48e6a33a18e3d32d2f3b4273fdbb343b3edca5c846c4955a24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:46.852106Z","signature_b64":"XAPMtOnKukQXntMe8+XVXnOvJ/wiMOE6t+V2+7iEQgXn9WsNEybyq5aYXM7nMwqWSXg8HWYmo/gQfqsXUIoTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e35acc8e19489ef7099e2142369e792040785a92f7251b4a246453091dbf0fc","last_reissued_at":"2026-07-05T02:40:46.851667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:46.851667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unknown-box Approximation to Improve Optical Character Recognition Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Allegra Latimer, Ayantha Randika, Nilanjan Ray, Xiao Xiao","submitted_at":"2021-05-17T16:09:15Z","abstract_excerpt":"Optical character recognition (OCR) is a widely used pattern recognition application in numerous domains. There are several feature-rich, general-purpose OCR solutions available for consumers, which can provide moderate to excellent accuracy levels. However, accuracy can diminish with difficult and uncommon document domains. Preprocessing of document images can be used to minimize the effect of domain shift. In this paper, a novel approach is presented for creating a customized preprocessor for a given OCR engine. Unlike the previous OCR agnostic preprocessing techniques, the proposed approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07983","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/2105.07983/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":"2105.07983","created_at":"2026-07-05T02:40:46.851731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07983v1","created_at":"2026-07-05T02:40:46.851731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07983","created_at":"2026-07-05T02:40:46.851731+00:00"},{"alias_kind":"pith_short_12","alias_value":"DY22ZSHBSSE6","created_at":"2026-07-05T02:40:46.851731+00:00"},{"alias_kind":"pith_short_16","alias_value":"DY22ZSHBSSE664EZ","created_at":"2026-07-05T02:40:46.851731+00:00"},{"alias_kind":"pith_short_8","alias_value":"DY22ZSHB","created_at":"2026-07-05T02:40:46.851731+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/DY22ZSHBSSE664EZ4IKCG2PHSI","json":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI.json","graph_json":"https://pith.science/api/pith-number/DY22ZSHBSSE664EZ4IKCG2PHSI/graph.json","events_json":"https://pith.science/api/pith-number/DY22ZSHBSSE664EZ4IKCG2PHSI/events.json","paper":"https://pith.science/paper/DY22ZSHB"},"agent_actions":{"view_html":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI","download_json":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI.json","view_paper":"https://pith.science/paper/DY22ZSHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07983&json=true","fetch_graph":"https://pith.science/api/pith-number/DY22ZSHBSSE664EZ4IKCG2PHSI/graph.json","fetch_events":"https://pith.science/api/pith-number/DY22ZSHBSSE664EZ4IKCG2PHSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI/action/storage_attestation","attest_author":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI/action/author_attestation","sign_citation":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI/action/citation_signature","submit_replication":"https://pith.science/pith/DY22ZSHBSSE664EZ4IKCG2PHSI/action/replication_record"}},"created_at":"2026-07-05T02:40:46.851731+00:00","updated_at":"2026-07-05T02:40:46.851731+00:00"}