{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:WZ2GAAFXJIG5DA2L7ZI5ODODZX","short_pith_number":"pith:WZ2GAAFX","canonical_record":{"source":{"id":"1201.2605","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2012-01-12T16:09:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f056ea248695dede5746f572429758739d73e80416ec6056127d07bf44a2f2ba","abstract_canon_sha256":"daecc6d2b4a3ef5ba44f74a430742995dc4bb26e0c8017eb0cf71bff8921c274"},"schema_version":"1.0"},"canonical_sha256":"b6746000b74a0dd1834bfe51d70dc3cde9a56f14a9f2acd7a8265f76d0e2fdc4","source":{"kind":"arxiv","id":"1201.2605","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1201.2605","created_at":"2026-05-18T02:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"1201.2605v2","created_at":"2026-05-18T02:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.2605","created_at":"2026-05-18T02:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"WZ2GAAFXJIG5","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WZ2GAAFXJIG5DA2L","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WZ2GAAFX","created_at":"2026-05-18T12:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:WZ2GAAFXJIG5DA2L7ZI5ODODZX","target":"record","payload":{"canonical_record":{"source":{"id":"1201.2605","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2012-01-12T16:09:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f056ea248695dede5746f572429758739d73e80416ec6056127d07bf44a2f2ba","abstract_canon_sha256":"daecc6d2b4a3ef5ba44f74a430742995dc4bb26e0c8017eb0cf71bff8921c274"},"schema_version":"1.0"},"canonical_sha256":"b6746000b74a0dd1834bfe51d70dc3cde9a56f14a9f2acd7a8265f76d0e2fdc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:39:54.450071Z","signature_b64":"/8m8P+DeoufRYRTmjVgQizu6KnJo/GJE8bfBZBSzCogkzPcnQpHsyy1dKVNkc8WoPjoIp6Bvtamg6dlaObHNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6746000b74a0dd1834bfe51d70dc3cde9a56f14a9f2acd7a8265f76d0e2fdc4","last_reissued_at":"2026-05-18T02:39:54.449528Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:39:54.449528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1201.2605","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8YwYCrLb1rDmvLixPWhttyr0xqSqNlNXLENXsgQ3UxVRGkS3XpVzDFeFF2lxaq4zkrcKgjBoPYjjqoZQSUyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:00:15.288833Z"},"content_sha256":"4486cec3f6c313947ee5eceaebe02e60c8cc0600619540b17616beda31ef7c46","schema_version":"1.0","event_id":"sha256:4486cec3f6c313947ee5eceaebe02e60c8cc0600619540b17616beda31ef7c46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:WZ2GAAFXJIG5DA2L7ZI5ODODZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Autonomous Cleaning of Corrupted Scanned Documents - A Generative Modeling Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"J\\\"org L\\\"ucke, Zhenwen Dai","submitted_at":"2012-01-12T16:09:10Z","abstract_excerpt":"We study the task of cleaning scanned text documents that are strongly corrupted by dirt such as manual line strokes, spilled ink etc. We aim at autonomously removing dirt from a single letter-size page based only on the information the page contains. Our approach, therefore, has to learn character representations without supervision and requires a mechanism to distinguish learned representations from irregular patterns. To learn character representations, we use a probabilistic generative model parameterizing pattern features, feature variances, the features' planar arrangements, and pattern "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.2605","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1g2OCPKEYWHFSvKBNQQYqKAUCh6wupsJUbgdXRcwZkbyEdNmZWe4i9uwbH3KzAampmtb1iJdtW+xQZ/XVjyqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:00:15.289354Z"},"content_sha256":"61541444303dc8417cb194635c99ea3f772c6080c800de3300b1109da8a96d25","schema_version":"1.0","event_id":"sha256:61541444303dc8417cb194635c99ea3f772c6080c800de3300b1109da8a96d25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZ2GAAFXJIG5DA2L7ZI5ODODZX/bundle.json","state_url":"https://pith.science/pith/WZ2GAAFXJIG5DA2L7ZI5ODODZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZ2GAAFXJIG5DA2L7ZI5ODODZX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T00:00:15Z","links":{"resolver":"https://pith.science/pith/WZ2GAAFXJIG5DA2L7ZI5ODODZX","bundle":"https://pith.science/pith/WZ2GAAFXJIG5DA2L7ZI5ODODZX/bundle.json","state":"https://pith.science/pith/WZ2GAAFXJIG5DA2L7ZI5ODODZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZ2GAAFXJIG5DA2L7ZI5ODODZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:WZ2GAAFXJIG5DA2L7ZI5ODODZX","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":"daecc6d2b4a3ef5ba44f74a430742995dc4bb26e0c8017eb0cf71bff8921c274","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2012-01-12T16:09:10Z","title_canon_sha256":"f056ea248695dede5746f572429758739d73e80416ec6056127d07bf44a2f2ba"},"schema_version":"1.0","source":{"id":"1201.2605","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1201.2605","created_at":"2026-05-18T02:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"1201.2605v2","created_at":"2026-05-18T02:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.2605","created_at":"2026-05-18T02:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"WZ2GAAFXJIG5","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"WZ2GAAFXJIG5DA2L","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"WZ2GAAFX","created_at":"2026-05-18T12:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:61541444303dc8417cb194635c99ea3f772c6080c800de3300b1109da8a96d25","target":"graph","created_at":"2026-05-18T02:39:54Z","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"},"paper":{"abstract_excerpt":"We study the task of cleaning scanned text documents that are strongly corrupted by dirt such as manual line strokes, spilled ink etc. We aim at autonomously removing dirt from a single letter-size page based only on the information the page contains. Our approach, therefore, has to learn character representations without supervision and requires a mechanism to distinguish learned representations from irregular patterns. To learn character representations, we use a probabilistic generative model parameterizing pattern features, feature variances, the features' planar arrangements, and pattern ","authors_text":"J\\\"org L\\\"ucke, Zhenwen Dai","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2012-01-12T16:09:10Z","title":"Autonomous Cleaning of Corrupted Scanned Documents - A Generative Modeling Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.2605","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":"sha256:4486cec3f6c313947ee5eceaebe02e60c8cc0600619540b17616beda31ef7c46","target":"record","created_at":"2026-05-18T02:39:54Z","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":"daecc6d2b4a3ef5ba44f74a430742995dc4bb26e0c8017eb0cf71bff8921c274","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2012-01-12T16:09:10Z","title_canon_sha256":"f056ea248695dede5746f572429758739d73e80416ec6056127d07bf44a2f2ba"},"schema_version":"1.0","source":{"id":"1201.2605","kind":"arxiv","version":2}},"canonical_sha256":"b6746000b74a0dd1834bfe51d70dc3cde9a56f14a9f2acd7a8265f76d0e2fdc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6746000b74a0dd1834bfe51d70dc3cde9a56f14a9f2acd7a8265f76d0e2fdc4","first_computed_at":"2026-05-18T02:39:54.449528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:39:54.449528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/8m8P+DeoufRYRTmjVgQizu6KnJo/GJE8bfBZBSzCogkzPcnQpHsyy1dKVNkc8WoPjoIp6Bvtamg6dlaObHNBg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:39:54.450071Z","signed_message":"canonical_sha256_bytes"},"source_id":"1201.2605","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4486cec3f6c313947ee5eceaebe02e60c8cc0600619540b17616beda31ef7c46","sha256:61541444303dc8417cb194635c99ea3f772c6080c800de3300b1109da8a96d25"],"state_sha256":"e0c84f16e448d45fcd97c48f6e793dea90a96d9d36b971adde929ab6e52039b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t11bZdzYVgzwG3+rAZf65JAuOYohEfrfh2zwH6KAI82H2mdc1SvhXIXi+L0VkSKlzrWdhMRcw4zhjqW/QJ3YCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:00:15.293553Z","bundle_sha256":"4177bc97f125720f93a04ddb5fb5fc665de7e5edc34a553b9648125ce73fdea5"}}