{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JNK2Z255FIX262QHBL3BL454WO","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":"0f79b93ac32bdb3f37a744936989603b687512b34a9244dd5d833049d201d9c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T14:19:50Z","title_canon_sha256":"64e95cfe82b131da18b19c20b228b7c79ce77495648defa9c06f6374556bdf73"},"schema_version":"1.0","source":{"id":"2303.09339","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09339","created_at":"2026-07-05T05:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09339v2","created_at":"2026-07-05T05:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09339","created_at":"2026-07-05T05:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"JNK2Z255FIX2","created_at":"2026-07-05T05:52:28Z"},{"alias_kind":"pith_short_16","alias_value":"JNK2Z255FIX262QH","created_at":"2026-07-05T05:52:28Z"},{"alias_kind":"pith_short_8","alias_value":"JNK2Z255","created_at":"2026-07-05T05:52:28Z"}],"graph_snapshots":[{"event_id":"sha256:798aec4fe001423085a82f131c0874e6c749b39abb5cc174b64854200e1cf9ca","target":"graph","created_at":"2026-07-05T05:52:28Z","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/2303.09339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Groleau, Jonathan Boarman, Kok Wei Chee, Samay Maini, Stefan Larson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T14:19:50Z","title":"ShabbyPages: A Reproducible Document Denoising and Binarization Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09339","kind":"arxiv","version":2},"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:e70e2b50dbcb112607030d0e226d881780241488527a39c6db03e96881faacff","target":"record","created_at":"2026-07-05T05:52:28Z","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":"0f79b93ac32bdb3f37a744936989603b687512b34a9244dd5d833049d201d9c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T14:19:50Z","title_canon_sha256":"64e95cfe82b131da18b19c20b228b7c79ce77495648defa9c06f6374556bdf73"},"schema_version":"1.0","source":{"id":"2303.09339","kind":"arxiv","version":2}},"canonical_sha256":"4b55acebbd2a2faf6a070af615f3bcb39aeb7bf6aadb97cc11b7a22ae867616a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b55acebbd2a2faf6a070af615f3bcb39aeb7bf6aadb97cc11b7a22ae867616a","first_computed_at":"2026-07-05T05:52:28.846014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:28.846014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1MV4FY3qZSJpH4qeZ24q5Ev3DchT2WfdHcQLeIOpLZiR/9XAlQe/UGSFe3oLh2ibloa1eNqp0cjdMHe8lg9+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:28.846471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09339","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e70e2b50dbcb112607030d0e226d881780241488527a39c6db03e96881faacff","sha256:798aec4fe001423085a82f131c0874e6c749b39abb5cc174b64854200e1cf9ca"],"state_sha256":"e067f312cf572d5537c6a27a6fb0cf067e5aad55916aee726f33be309ddc380e"}