{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QQOGV3BU4T4TZTDJUOMXP32LP3","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":"359da19ebad9dc81b2d886a8feead3921d49d28b8c8ea779f7988b9f0870b366","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T11:59:18Z","title_canon_sha256":"a1af9c8c33c5ce837248d843a01661c9bec96a6f5edfee23b4c75db6d6af6ad8"},"schema_version":"1.0","source":{"id":"2205.08257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.08257","created_at":"2026-07-05T04:24:00Z"},{"alias_kind":"arxiv_version","alias_value":"2205.08257v1","created_at":"2026-07-05T04:24:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08257","created_at":"2026-07-05T04:24:00Z"},{"alias_kind":"pith_short_12","alias_value":"QQOGV3BU4T4T","created_at":"2026-07-05T04:24:00Z"},{"alias_kind":"pith_short_16","alias_value":"QQOGV3BU4T4TZTDJ","created_at":"2026-07-05T04:24:00Z"},{"alias_kind":"pith_short_8","alias_value":"QQOGV3BU","created_at":"2026-07-05T04:24:00Z"}],"graph_snapshots":[{"event_id":"sha256:5c1ed83f1a4813e70963979d42260b9c93c12e6dee8aa09c0d6ca9d3b5dd62fd","target":"graph","created_at":"2026-07-05T04:24:00Z","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/2205.08257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daniel Rotman, Inbar Shapira, Ophir Azulai, Udi Barzelay, Yevgeny Burshtein","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T11:59:18Z","title":"Detection Masking for Improved OCR on Noisy Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08257","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:e7a5254b77495600bb9741ba96309f0ec3dd68d1f736f7443c178128086e4921","target":"record","created_at":"2026-07-05T04:24:00Z","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":"359da19ebad9dc81b2d886a8feead3921d49d28b8c8ea779f7988b9f0870b366","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T11:59:18Z","title_canon_sha256":"a1af9c8c33c5ce837248d843a01661c9bec96a6f5edfee23b4c75db6d6af6ad8"},"schema_version":"1.0","source":{"id":"2205.08257","kind":"arxiv","version":1}},"canonical_sha256":"841c6aec34e4f93ccc69a39977ef4b7edbf1205564b441e0b62092461cf401c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"841c6aec34e4f93ccc69a39977ef4b7edbf1205564b441e0b62092461cf401c6","first_computed_at":"2026-07-05T04:24:00.991284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:00.991284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/o/NW8nW5nzQBJutd9rNkYfNXKCshkBPIYrJiJWy43gFvaLdn1CluZ3Av4rkpOelfSMmGDeTyQE7SqEoozD0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:00.991739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.08257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7a5254b77495600bb9741ba96309f0ec3dd68d1f736f7443c178128086e4921","sha256:5c1ed83f1a4813e70963979d42260b9c93c12e6dee8aa09c0d6ca9d3b5dd62fd"],"state_sha256":"a9a14bf2beddd0f4519cf78ff30075fdbac09abbf820fc96c95bb3f58e9c78be"}