{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SOFR2DF4JU3SYB3I2ZJCI7LMJ6","short_pith_number":"pith:SOFR2DF4","schema_version":"1.0","canonical_sha256":"938b1d0cbc4d372c0768d652247d6c4f817e2d68709263e7eb5e8c23d9bc25b3","source":{"kind":"arxiv","id":"2607.08143","version":1},"attestation_state":"computed","paper":{"title":"ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andrianos Michail, Emanuela Boros, Florian Wagner, Juri Opitz, Maud Ehrmann, Simon Clematide","submitted_at":"2026-07-09T06:26:13Z","abstract_excerpt":"We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents. OCR post-correction remains a long-standing challenge in digital heritage: large-scale collections of digitized documents are affected by legacy OCR errors, while re-digitization at scale remains impractical. Large language models (LLMs) offers a major opportunity to revisit this challenge, yet their effectiveness across languages, document types, and noise conditions - and their tendency to hallucinate - remains insufficiently understood. HIPE-OCRepair-2026 pursues t"},"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":"2607.08143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T06:26:13Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"ea322e871d8ff9d8ad376944e132a6f072b7acdfd7d706b0ea47ec8a34481915","abstract_canon_sha256":"7bc4f94409188ca150d2100cd9d7a1876a26bc33d42b8b5fcaadbfb4bd9d86c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:27.759002Z","signature_b64":"v4r2zNTjV5xU9c4D1s7yCLvadICMcYYxBP7qaitoJp+FtozNOSQcbtWhGIWLL7/ths0zhVMmBLrWaEFFOeMwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"938b1d0cbc4d372c0768d652247d6c4f817e2d68709263e7eb5e8c23d9bc25b3","last_reissued_at":"2026-07-10T01:19:27.758601Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:27.758601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Andrianos Michail, Emanuela Boros, Florian Wagner, Juri Opitz, Maud Ehrmann, Simon Clematide","submitted_at":"2026-07-09T06:26:13Z","abstract_excerpt":"We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents. OCR post-correction remains a long-standing challenge in digital heritage: large-scale collections of digitized documents are affected by legacy OCR errors, while re-digitization at scale remains impractical. Large language models (LLMs) offers a major opportunity to revisit this challenge, yet their effectiveness across languages, document types, and noise conditions - and their tendency to hallucinate - remains insufficiently understood. HIPE-OCRepair-2026 pursues t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08143","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/2607.08143/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":"2607.08143","created_at":"2026-07-10T01:19:27.758658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08143v1","created_at":"2026-07-10T01:19:27.758658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08143","created_at":"2026-07-10T01:19:27.758658+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOFR2DF4JU3S","created_at":"2026-07-10T01:19:27.758658+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOFR2DF4JU3SYB3I","created_at":"2026-07-10T01:19:27.758658+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOFR2DF4","created_at":"2026-07-10T01:19:27.758658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6","json":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6.json","graph_json":"https://pith.science/api/pith-number/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/graph.json","events_json":"https://pith.science/api/pith-number/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/events.json","paper":"https://pith.science/paper/SOFR2DF4"},"agent_actions":{"view_html":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6","download_json":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6.json","view_paper":"https://pith.science/paper/SOFR2DF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08143&json=true","fetch_graph":"https://pith.science/api/pith-number/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/action/storage_attestation","attest_author":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/action/author_attestation","sign_citation":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/action/citation_signature","submit_replication":"https://pith.science/pith/SOFR2DF4JU3SYB3I2ZJCI7LMJ6/action/replication_record"}},"created_at":"2026-07-10T01:19:27.758658+00:00","updated_at":"2026-07-10T01:19:27.758658+00:00"}