{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WFBJU6FZBU3BHAQLTI4IF577G2","short_pith_number":"pith:WFBJU6FZ","canonical_record":{"source":{"id":"1608.02153","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-06T20:51:53Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"deffc7c3059621d1ffd2011b3900ada4f6a5a2bc580d80923206223e4fb6214d","abstract_canon_sha256":"b9770366d101260c9246fb8516acdfd3ebc763f9e33e82856589dda43b30fd52"},"schema_version":"1.0"},"canonical_sha256":"b1429a78b90d3613820b9a3882f7ff369130104df20f6246677fb34f294c81b3","source":{"kind":"arxiv","id":"1608.02153","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.02153","created_at":"2026-05-18T00:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"1608.02153v2","created_at":"2026-05-18T00:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02153","created_at":"2026-05-18T00:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"WFBJU6FZBU3B","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WFBJU6FZBU3BHAQL","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WFBJU6FZ","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WFBJU6FZBU3BHAQLTI4IF577G2","target":"record","payload":{"canonical_record":{"source":{"id":"1608.02153","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-06T20:51:53Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"deffc7c3059621d1ffd2011b3900ada4f6a5a2bc580d80923206223e4fb6214d","abstract_canon_sha256":"b9770366d101260c9246fb8516acdfd3ebc763f9e33e82856589dda43b30fd52"},"schema_version":"1.0"},"canonical_sha256":"b1429a78b90d3613820b9a3882f7ff369130104df20f6246677fb34f294c81b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:49.217618Z","signature_b64":"rhMxKBtIZIRIHpgUZfY/3KqY94rJ1zmCIqM7DPXES5Yd34PEht6+TOIZdfQJJByMkQSiczx8fR9Fh305w+RKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1429a78b90d3613820b9a3882f7ff369130104df20f6246677fb34f294c81b3","last_reissued_at":"2026-05-18T00:46:49.216881Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:49.216881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.02153","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":"2026-05-18T00:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMsVe71NY6w6E5wqwVbUOKzUM2un8Z0IIFjUd5DBCscCxgMwifJfZPnojUib6selUDp/zKMjNNoY/yTWvXsdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:46:31.853377Z"},"content_sha256":"d804b9878a0316d50b0f6f61b9a2637f91de322d77a4c5ff2a1304014bc103ed","schema_version":"1.0","event_id":"sha256:d804b9878a0316d50b0f6f61b9a2637f91de322d77a4c5ff2a1304014bc103ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WFBJU6FZBU3BHAQLTI4IF577G2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"A. L\\\"udeling, U. Springmann","submitted_at":"2016-08-06T20:51:53Z","abstract_excerpt":"This article describes the results of a case study that applies Neural Network-based Optical Character Recognition (OCR) to scanned images of books printed between 1487 and 1870 by training the OCR engine OCRopus [@breuel2013high] on the RIDGES herbal text corpus [@OdebrechtEtAlSubmitted]. Training specific OCR models was possible because the necessary *ground truth* is available as error-corrected diplomatic transcriptions. The OCR results have been evaluated for accuracy against the ground truth of unseen test sets. Character and word accuracies (percentage of correctly recognized items) for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02153","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":"2026-05-18T00:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbnzfQgnlXJf/b26H4kYj6JOcyJ1T3vgYC4JBG4xwoJRmLvDrPBvdj2ELfOMtFnkHHPepGfVUw3VplIHbEWFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:46:31.853734Z"},"content_sha256":"a475d4d8c34e386103d2ff89d4187ae3fd423fb15f7c346d9369914c610ae93b","schema_version":"1.0","event_id":"sha256:a475d4d8c34e386103d2ff89d4187ae3fd423fb15f7c346d9369914c610ae93b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/bundle.json","state_url":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WFBJU6FZBU3BHAQLTI4IF577G2/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":"2026-07-01T08:46:31Z","links":{"resolver":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2","bundle":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/bundle.json","state":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WFBJU6FZBU3BHAQLTI4IF577G2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WFBJU6FZBU3BHAQLTI4IF577G2","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":"b9770366d101260c9246fb8516acdfd3ebc763f9e33e82856589dda43b30fd52","cross_cats_sorted":["cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-06T20:51:53Z","title_canon_sha256":"deffc7c3059621d1ffd2011b3900ada4f6a5a2bc580d80923206223e4fb6214d"},"schema_version":"1.0","source":{"id":"1608.02153","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.02153","created_at":"2026-05-18T00:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"1608.02153v2","created_at":"2026-05-18T00:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02153","created_at":"2026-05-18T00:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"WFBJU6FZBU3B","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WFBJU6FZBU3BHAQL","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WFBJU6FZ","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:a475d4d8c34e386103d2ff89d4187ae3fd423fb15f7c346d9369914c610ae93b","target":"graph","created_at":"2026-05-18T00:46:49Z","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":"This article describes the results of a case study that applies Neural Network-based Optical Character Recognition (OCR) to scanned images of books printed between 1487 and 1870 by training the OCR engine OCRopus [@breuel2013high] on the RIDGES herbal text corpus [@OdebrechtEtAlSubmitted]. Training specific OCR models was possible because the necessary *ground truth* is available as error-corrected diplomatic transcriptions. The OCR results have been evaluated for accuracy against the ground truth of unseen test sets. Character and word accuracies (percentage of correctly recognized items) for","authors_text":"A. L\\\"udeling, U. Springmann","cross_cats":["cs.DL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-06T20:51:53Z","title":"OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02153","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:d804b9878a0316d50b0f6f61b9a2637f91de322d77a4c5ff2a1304014bc103ed","target":"record","created_at":"2026-05-18T00:46:49Z","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":"b9770366d101260c9246fb8516acdfd3ebc763f9e33e82856589dda43b30fd52","cross_cats_sorted":["cs.DL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-06T20:51:53Z","title_canon_sha256":"deffc7c3059621d1ffd2011b3900ada4f6a5a2bc580d80923206223e4fb6214d"},"schema_version":"1.0","source":{"id":"1608.02153","kind":"arxiv","version":2}},"canonical_sha256":"b1429a78b90d3613820b9a3882f7ff369130104df20f6246677fb34f294c81b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1429a78b90d3613820b9a3882f7ff369130104df20f6246677fb34f294c81b3","first_computed_at":"2026-05-18T00:46:49.216881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:49.216881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rhMxKBtIZIRIHpgUZfY/3KqY94rJ1zmCIqM7DPXES5Yd34PEht6+TOIZdfQJJByMkQSiczx8fR9Fh305w+RKBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:49.217618Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.02153","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d804b9878a0316d50b0f6f61b9a2637f91de322d77a4c5ff2a1304014bc103ed","sha256:a475d4d8c34e386103d2ff89d4187ae3fd423fb15f7c346d9369914c610ae93b"],"state_sha256":"34be0d78315aea18a3747f3447d85b0846c121d2f8a703ea7d17ef61880780b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/LTZYc0RAH0XVhSFGqUliAjzctYDcvrMh+pZFciiH0POXwOdNSKL0rZDrkuZxKj9SL1LdPI17tZZ5OtWjggDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T08:46:31.855736Z","bundle_sha256":"4a61a0d10d19e20dd7a5c10b26b7d75675aa90a826c17b8fb922f5edfdd7abc9"}}