{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QQOGV3BU4T4TZTDJUOMXP32LP3","short_pith_number":"pith:QQOGV3BU","schema_version":"1.0","canonical_sha256":"841c6aec34e4f93ccc69a39977ef4b7edbf1205564b441e0b62092461cf401c6","source":{"kind":"arxiv","id":"2205.08257","version":1},"attestation_state":"computed","paper":{"title":"Detection Masking for Improved OCR on Noisy Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Rotman, Inbar Shapira, Ophir Azulai, Udi Barzelay, Yevgeny Burshtein","submitted_at":"2022-05-17T11:59:18Z","abstract_excerpt":"Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical documents. Existing technologies perform well for clean documents, but when the document is visually degraded, or when there are non-textual elements, OCR quality can be greatly impacted, specifically due to erroneous detections. In this paper we present an improved detection network with a masking system to improve the quality of OCR performed on documents. By filtering non-textual elements from the image we can util"},"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":"2205.08257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T11:59:18Z","cross_cats_sorted":[],"title_canon_sha256":"a1af9c8c33c5ce837248d843a01661c9bec96a6f5edfee23b4c75db6d6af6ad8","abstract_canon_sha256":"359da19ebad9dc81b2d886a8feead3921d49d28b8c8ea779f7988b9f0870b366"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:00.991739Z","signature_b64":"/o/NW8nW5nzQBJutd9rNkYfNXKCshkBPIYrJiJWy43gFvaLdn1CluZ3Av4rkpOelfSMmGDeTyQE7SqEoozD0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"841c6aec34e4f93ccc69a39977ef4b7edbf1205564b441e0b62092461cf401c6","last_reissued_at":"2026-07-05T04:24:00.991284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:00.991284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detection Masking for Improved OCR on Noisy Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Rotman, Inbar Shapira, Ophir Azulai, Udi Barzelay, Yevgeny Burshtein","submitted_at":"2022-05-17T11:59:18Z","abstract_excerpt":"Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical documents. Existing technologies perform well for clean documents, but when the document is visually degraded, or when there are non-textual elements, OCR quality can be greatly impacted, specifically due to erroneous detections. In this paper we present an improved detection network with a masking system to improve the quality of OCR performed on documents. By filtering non-textual elements from the image we can util"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08257","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/2205.08257/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":"2205.08257","created_at":"2026-07-05T04:24:00.991353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.08257v1","created_at":"2026-07-05T04:24:00.991353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08257","created_at":"2026-07-05T04:24:00.991353+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQOGV3BU4T4T","created_at":"2026-07-05T04:24:00.991353+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQOGV3BU4T4TZTDJ","created_at":"2026-07-05T04:24:00.991353+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQOGV3BU","created_at":"2026-07-05T04:24:00.991353+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/QQOGV3BU4T4TZTDJUOMXP32LP3","json":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3.json","graph_json":"https://pith.science/api/pith-number/QQOGV3BU4T4TZTDJUOMXP32LP3/graph.json","events_json":"https://pith.science/api/pith-number/QQOGV3BU4T4TZTDJUOMXP32LP3/events.json","paper":"https://pith.science/paper/QQOGV3BU"},"agent_actions":{"view_html":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3","download_json":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3.json","view_paper":"https://pith.science/paper/QQOGV3BU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.08257&json=true","fetch_graph":"https://pith.science/api/pith-number/QQOGV3BU4T4TZTDJUOMXP32LP3/graph.json","fetch_events":"https://pith.science/api/pith-number/QQOGV3BU4T4TZTDJUOMXP32LP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3/action/storage_attestation","attest_author":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3/action/author_attestation","sign_citation":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3/action/citation_signature","submit_replication":"https://pith.science/pith/QQOGV3BU4T4TZTDJUOMXP32LP3/action/replication_record"}},"created_at":"2026-07-05T04:24:00.991353+00:00","updated_at":"2026-07-05T04:24:00.991353+00:00"}