{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PD4FOO7P764MDDYPMTI2YPTLLO","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":"4ed2cc2df1aaac656f34599d512df8a1d9abb9a477f4e2d322910e7c77399531","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T15:53:13Z","title_canon_sha256":"01e3dc2a3256406f08ab3a0dae73254ab7f82818aba16f86fb943aef08724bf0"},"schema_version":"1.0","source":{"id":"2401.07787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07787","created_at":"2026-07-05T07:34:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07787v1","created_at":"2026-07-05T07:34:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07787","created_at":"2026-07-05T07:34:02Z"},{"alias_kind":"pith_short_12","alias_value":"PD4FOO7P764M","created_at":"2026-07-05T07:34:02Z"},{"alias_kind":"pith_short_16","alias_value":"PD4FOO7P764MDDYP","created_at":"2026-07-05T07:34:02Z"},{"alias_kind":"pith_short_8","alias_value":"PD4FOO7P","created_at":"2026-07-05T07:34:02Z"}],"graph_snapshots":[{"event_id":"sha256:38774ec0ff9cd5c31b0531a77b0ae5f6de766ac98d97b35509c683505fff138a","target":"graph","created_at":"2026-07-05T07:34:02Z","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/2401.07787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses a major challenge to historical research on the 19th century. Large quantities of sources have become digitally available for the first time, while extraction techniques are lagging behind. Therefore, we researched machine learning (ML) models to recognise and extract complex data structures in a high-value historical primary source, the Schematismus. It records every single person in the Habsburg civil service above a certain hierarchical level between 1702 and 1918 and documents the genesis of the central administration over two centuries. Its complex and intricate struc","authors_text":"David Fleischhacker, Roman Kern, Wolfgang Goederle","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T15:53:13Z","title":"Improving OCR Quality in 19th Century Historical Documents Using a Combined Machine Learning Based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07787","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":"sha256:8e46c0ca95737d97414624e559318c20d86a61e6ed292f5104da0e553d689327","target":"record","created_at":"2026-07-05T07:34:02Z","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":"4ed2cc2df1aaac656f34599d512df8a1d9abb9a477f4e2d322910e7c77399531","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T15:53:13Z","title_canon_sha256":"01e3dc2a3256406f08ab3a0dae73254ab7f82818aba16f86fb943aef08724bf0"},"schema_version":"1.0","source":{"id":"2401.07787","kind":"arxiv","version":1}},"canonical_sha256":"78f8573befffb8c18f0f64d1ac3e6b5ba7c4bb56219205d630106b61ba801c00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78f8573befffb8c18f0f64d1ac3e6b5ba7c4bb56219205d630106b61ba801c00","first_computed_at":"2026-07-05T07:34:02.960345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:02.960345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LkDALWZFo+lKWLfNGmet7dMVRbYMJu/yXrZPRtDwMwuuCix8HMg05hhi6Vbr/7XekSyWwJ0+3NUwTEK3FCoTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:02.960781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e46c0ca95737d97414624e559318c20d86a61e6ed292f5104da0e553d689327","sha256:38774ec0ff9cd5c31b0531a77b0ae5f6de766ac98d97b35509c683505fff138a"],"state_sha256":"b7110043c5fc5dbce1a563084e7b8de68dec2e01b426d5cb626783aa8f4d3928"}