{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FC2MMLTJ2GAMMPAUMANPGMS4JS","short_pith_number":"pith:FC2MMLTJ","schema_version":"1.0","canonical_sha256":"28b4c62e69d180c63c14601af3325c4cb4ef0b936b629268263ca104dfcbc3fd","source":{"kind":"arxiv","id":"2508.14557","version":1},"attestation_state":"computed","paper":{"title":"Improving OCR using internal document redundancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aitor Artola, Antoine Tadros, Boshra Rajaei, Camilo Mari\\~no, Diego Belzarena, Gregory Randall, Ignacio Ram\\'irez, Jean-Michel Morel, Marina Gardella, Natalia Bottaioli, Roy He, Seginus Mowlavi","submitted_at":"2025-08-20T09:21:43Z","abstract_excerpt":"Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data. This is particularly evident for printed documents, where intra-domain data variability is typically low, but inter-domain data variability is high. In that context, current OCR methods do not fully exploit each document's redundancy. We propose an unsupervised method by leveraging the redundancy of character shapes within a document to correct imperfect out"},"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":"2508.14557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-20T09:21:43Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"17b0fe6b8d4314da796d1fc8fc045070a1449d5731a9f83e3b377f7ba914f06d","abstract_canon_sha256":"200d49f2aeac45cc868ae7e541825b4086f1412471e269d7fe65c773d9f40bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:34.200055Z","signature_b64":"3d0r9tFnonWdE2BCDpe2R3gWHAE39VXSIR/gHmuimYYVclf8nRLOElX/dU07NPpGt5TvwOIPv8RysOyhO68mDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b4c62e69d180c63c14601af3325c4cb4ef0b936b629268263ca104dfcbc3fd","last_reissued_at":"2026-07-05T11:56:34.199588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:34.199588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving OCR using internal document redundancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aitor Artola, Antoine Tadros, Boshra Rajaei, Camilo Mari\\~no, Diego Belzarena, Gregory Randall, Ignacio Ram\\'irez, Jean-Michel Morel, Marina Gardella, Natalia Bottaioli, Roy He, Seginus Mowlavi","submitted_at":"2025-08-20T09:21:43Z","abstract_excerpt":"Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data. This is particularly evident for printed documents, where intra-domain data variability is typically low, but inter-domain data variability is high. In that context, current OCR methods do not fully exploit each document's redundancy. We propose an unsupervised method by leveraging the redundancy of character shapes within a document to correct imperfect out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14557","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/2508.14557/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":"2508.14557","created_at":"2026-07-05T11:56:34.199645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14557v1","created_at":"2026-07-05T11:56:34.199645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14557","created_at":"2026-07-05T11:56:34.199645+00:00"},{"alias_kind":"pith_short_12","alias_value":"FC2MMLTJ2GAM","created_at":"2026-07-05T11:56:34.199645+00:00"},{"alias_kind":"pith_short_16","alias_value":"FC2MMLTJ2GAMMPAU","created_at":"2026-07-05T11:56:34.199645+00:00"},{"alias_kind":"pith_short_8","alias_value":"FC2MMLTJ","created_at":"2026-07-05T11:56:34.199645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17159","citing_title":"MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS","json":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS.json","graph_json":"https://pith.science/api/pith-number/FC2MMLTJ2GAMMPAUMANPGMS4JS/graph.json","events_json":"https://pith.science/api/pith-number/FC2MMLTJ2GAMMPAUMANPGMS4JS/events.json","paper":"https://pith.science/paper/FC2MMLTJ"},"agent_actions":{"view_html":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS","download_json":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS.json","view_paper":"https://pith.science/paper/FC2MMLTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14557&json=true","fetch_graph":"https://pith.science/api/pith-number/FC2MMLTJ2GAMMPAUMANPGMS4JS/graph.json","fetch_events":"https://pith.science/api/pith-number/FC2MMLTJ2GAMMPAUMANPGMS4JS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS/action/storage_attestation","attest_author":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS/action/author_attestation","sign_citation":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS/action/citation_signature","submit_replication":"https://pith.science/pith/FC2MMLTJ2GAMMPAUMANPGMS4JS/action/replication_record"}},"created_at":"2026-07-05T11:56:34.199645+00:00","updated_at":"2026-07-05T11:56:34.199645+00:00"}