{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UYJGP6NRDITNODASGJGQ7OCKA7","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":"1c55f4b9960f94dc8525d24581eee1448284bf2b0258b8578789456deca21262","cross_cats_sorted":["cs.AI","cs.DL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T04:21:34Z","title_canon_sha256":"a3521a16b6cf3036967f7beee0fb67a370c7edbfb231edadca65f7753186f5c5"},"schema_version":"1.0","source":{"id":"2504.00414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00414","created_at":"2026-07-05T10:42:25Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00414v1","created_at":"2026-07-05T10:42:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00414","created_at":"2026-07-05T10:42:25Z"},{"alias_kind":"pith_short_12","alias_value":"UYJGP6NRDITN","created_at":"2026-07-05T10:42:25Z"},{"alias_kind":"pith_short_16","alias_value":"UYJGP6NRDITNODAS","created_at":"2026-07-05T10:42:25Z"},{"alias_kind":"pith_short_8","alias_value":"UYJGP6NR","created_at":"2026-07-05T10:42:25Z"}],"graph_snapshots":[{"event_id":"sha256:2a9d5b33124af94aec4b5047235ff75710b6517eed90a553fe8709ded6aab922","target":"graph","created_at":"2026-07-05T10:42:25Z","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/2504.00414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore how multimodal Large Language Models (mLLMs) can help researchers transcribe historical documents, extract relevant historical information, and construct datasets from historical sources. Specifically, we investigate the capabilities of mLLMs in performing (1) Optical Character Recognition (OCR), (2) OCR Post-Correction, and (3) Named Entity Recognition (NER) tasks on a set of city directories published in German between 1754 and 1870. First, we benchmark the off-the-shelf transcription accuracy of both mLLMs and conventional OCR models. We find that the best-performing mLLM model s","authors_text":"Gavin Greif, Niclas Griesshaber, Robin Greif","cross_cats":["cs.AI","cs.DL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T04:21:34Z","title":"Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00414","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":"sha256:64f4a8dd94d3a8fcd5f0c323c835906ffe0455fc1883b8c66465b43aa9d5191c","target":"record","created_at":"2026-07-05T10:42:25Z","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":"1c55f4b9960f94dc8525d24581eee1448284bf2b0258b8578789456deca21262","cross_cats_sorted":["cs.AI","cs.DL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T04:21:34Z","title_canon_sha256":"a3521a16b6cf3036967f7beee0fb67a370c7edbfb231edadca65f7753186f5c5"},"schema_version":"1.0","source":{"id":"2504.00414","kind":"arxiv","version":1}},"canonical_sha256":"a61267f9b11a26d70c12324d0fb84a07c388a4ef1dc28825f175518dc342cd94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a61267f9b11a26d70c12324d0fb84a07c388a4ef1dc28825f175518dc342cd94","first_computed_at":"2026-07-05T10:42:25.935574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:25.935574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qp5edBMzxCUmPdgmqxDky42kXyZ41rE1t+0MOGznwyhY40uC/SFNtSoSCigyolsE8xWJGwz7O03kT1Y9dKdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:25.936063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64f4a8dd94d3a8fcd5f0c323c835906ffe0455fc1883b8c66465b43aa9d5191c","sha256:2a9d5b33124af94aec4b5047235ff75710b6517eed90a553fe8709ded6aab922"],"state_sha256":"a72173ed3d4a3ef58f5fab20ff936283e2fbbc15bb4c965961cff1e9d46cb2dc"}