{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JNK2Z255FIX262QHBL3BL454WO","short_pith_number":"pith:JNK2Z255","schema_version":"1.0","canonical_sha256":"4b55acebbd2a2faf6a070af615f3bcb39aeb7bf6aadb97cc11b7a22ae867616a","source":{"kind":"arxiv","id":"2303.09339","version":2},"attestation_state":"computed","paper":{"title":"ShabbyPages: A Reproducible Document Denoising and Binarization Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Groleau, Jonathan Boarman, Kok Wei Chee, Samay Maini, Stefan Larson","submitted_at":"2023-03-16T14:19:50Z","abstract_excerpt":"Document denoising and binarization are fundamental problems in the document processing space, but current datasets are often too small and lack sufficient complexity to effectively train and benchmark modern data-driven machine learning models. To fill this gap, we introduce ShabbyPages, a new document image dataset designed for training and benchmarking document denoisers and binarizers. ShabbyPages contains over 6,000 clean \"born digital\" images with synthetically-noised counterparts (\"shabby pages\") that were augmented using the Augraphy document augmentation tool to appear as if they have"},"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":"2303.09339","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T14:19:50Z","cross_cats_sorted":[],"title_canon_sha256":"64e95cfe82b131da18b19c20b228b7c79ce77495648defa9c06f6374556bdf73","abstract_canon_sha256":"0f79b93ac32bdb3f37a744936989603b687512b34a9244dd5d833049d201d9c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:28.846471Z","signature_b64":"1MV4FY3qZSJpH4qeZ24q5Ev3DchT2WfdHcQLeIOpLZiR/9XAlQe/UGSFe3oLh2ibloa1eNqp0cjdMHe8lg9+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b55acebbd2a2faf6a070af615f3bcb39aeb7bf6aadb97cc11b7a22ae867616a","last_reissued_at":"2026-07-05T05:52:28.846014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:28.846014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShabbyPages: A Reproducible Document Denoising and Binarization Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Groleau, Jonathan Boarman, Kok Wei Chee, Samay Maini, Stefan Larson","submitted_at":"2023-03-16T14:19:50Z","abstract_excerpt":"Document denoising and binarization are fundamental problems in the document processing space, but current datasets are often too small and lack sufficient complexity to effectively train and benchmark modern data-driven machine learning models. To fill this gap, we introduce ShabbyPages, a new document image dataset designed for training and benchmarking document denoisers and binarizers. ShabbyPages contains over 6,000 clean \"born digital\" images with synthetically-noised counterparts (\"shabby pages\") that were augmented using the Augraphy document augmentation tool to appear as if they have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09339","kind":"arxiv","version":2},"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/2303.09339/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":"2303.09339","created_at":"2026-07-05T05:52:28.846066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09339v2","created_at":"2026-07-05T05:52:28.846066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09339","created_at":"2026-07-05T05:52:28.846066+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNK2Z255FIX2","created_at":"2026-07-05T05:52:28.846066+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNK2Z255FIX262QH","created_at":"2026-07-05T05:52:28.846066+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNK2Z255","created_at":"2026-07-05T05:52:28.846066+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/JNK2Z255FIX262QHBL3BL454WO","json":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO.json","graph_json":"https://pith.science/api/pith-number/JNK2Z255FIX262QHBL3BL454WO/graph.json","events_json":"https://pith.science/api/pith-number/JNK2Z255FIX262QHBL3BL454WO/events.json","paper":"https://pith.science/paper/JNK2Z255"},"agent_actions":{"view_html":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO","download_json":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO.json","view_paper":"https://pith.science/paper/JNK2Z255","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09339&json=true","fetch_graph":"https://pith.science/api/pith-number/JNK2Z255FIX262QHBL3BL454WO/graph.json","fetch_events":"https://pith.science/api/pith-number/JNK2Z255FIX262QHBL3BL454WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO/action/storage_attestation","attest_author":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO/action/author_attestation","sign_citation":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO/action/citation_signature","submit_replication":"https://pith.science/pith/JNK2Z255FIX262QHBL3BL454WO/action/replication_record"}},"created_at":"2026-07-05T05:52:28.846066+00:00","updated_at":"2026-07-05T05:52:28.846066+00:00"}