{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L6ICTGDZXQQGZF6MYLEZ232JYS","short_pith_number":"pith:L6ICTGDZ","schema_version":"1.0","canonical_sha256":"5f90299879bc206c97ccc2c99d6f49c4834e4cb124ffca0795512783c09313ba","source":{"kind":"arxiv","id":"2410.24034","version":1},"attestation_state":"computed","paper":{"title":"Handwriting Recognition in Historical Documents with Multimodal LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lucian Li","submitted_at":"2024-10-31T15:32:14Z","abstract_excerpt":"There is an immense quantity of historical and cultural documentation that exists only as handwritten manuscripts. At the same time, performing OCR across scripts and different handwriting styles has proven to be an enormously difficult problem relative to the process of digitizing print. While recent Transformer based models have achieved relatively strong performance, they rely heavily on manually transcribed training data and have difficulty generalizing across writers. Multimodal LLM, such as GPT-4v and Gemini, have demonstrated effectiveness in performing OCR and computer vision tasks wit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.24034","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T15:32:14Z","cross_cats_sorted":[],"title_canon_sha256":"256ae980a3211b9e614aad71484eebef59bdff5a32ea7eb0a231e27000d8c606","abstract_canon_sha256":"5a0e98876eccb3c95e8d8d19340b504c98414c9c6ea33ae61e82e34fe5802cde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:18.302879Z","signature_b64":"0fBHWvyppZv8u1bG44CjI2mNFw0+pWSChRPPd6cFAEZ6qfDEiBaqiZ4JwB3MpWjdvZ+dsT6pp5x+NfklSYwGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f90299879bc206c97ccc2c99d6f49c4834e4cb124ffca0795512783c09313ba","last_reissued_at":"2026-07-05T09:29:18.302469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:18.302469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Handwriting Recognition in Historical Documents with Multimodal LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lucian Li","submitted_at":"2024-10-31T15:32:14Z","abstract_excerpt":"There is an immense quantity of historical and cultural documentation that exists only as handwritten manuscripts. At the same time, performing OCR across scripts and different handwriting styles has proven to be an enormously difficult problem relative to the process of digitizing print. While recent Transformer based models have achieved relatively strong performance, they rely heavily on manually transcribed training data and have difficulty generalizing across writers. Multimodal LLM, such as GPT-4v and Gemini, have demonstrated effectiveness in performing OCR and computer vision tasks wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24034","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.24034/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.24034","created_at":"2026-07-05T09:29:18.302528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24034v1","created_at":"2026-07-05T09:29:18.302528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24034","created_at":"2026-07-05T09:29:18.302528+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6ICTGDZXQQG","created_at":"2026-07-05T09:29:18.302528+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6ICTGDZXQQGZF6M","created_at":"2026-07-05T09:29:18.302528+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6ICTGDZ","created_at":"2026-07-05T09:29:18.302528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23543","citing_title":"Position Paper: Metadata Enrichment Model: Integrating Neural Networks and Semantic Knowledge Graphs for Cultural Heritage Applications","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS","json":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS.json","graph_json":"https://pith.science/api/pith-number/L6ICTGDZXQQGZF6MYLEZ232JYS/graph.json","events_json":"https://pith.science/api/pith-number/L6ICTGDZXQQGZF6MYLEZ232JYS/events.json","paper":"https://pith.science/paper/L6ICTGDZ"},"agent_actions":{"view_html":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS","download_json":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS.json","view_paper":"https://pith.science/paper/L6ICTGDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24034&json=true","fetch_graph":"https://pith.science/api/pith-number/L6ICTGDZXQQGZF6MYLEZ232JYS/graph.json","fetch_events":"https://pith.science/api/pith-number/L6ICTGDZXQQGZF6MYLEZ232JYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS/action/storage_attestation","attest_author":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS/action/author_attestation","sign_citation":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS/action/citation_signature","submit_replication":"https://pith.science/pith/L6ICTGDZXQQGZF6MYLEZ232JYS/action/replication_record"}},"created_at":"2026-07-05T09:29:18.302528+00:00","updated_at":"2026-07-05T09:29:18.302528+00:00"}