{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LWONAZWJGCE5LAOOV6OHNBWZ2J","short_pith_number":"pith:LWONAZWJ","schema_version":"1.0","canonical_sha256":"5d9cd066c93089d581ceaf9c7686d9d26f3d1190618a103f2538889b07b9c1c8","source":{"kind":"arxiv","id":"2607.00250","version":1},"attestation_state":"computed","paper":{"title":"LV-ROVER: Multi-Stream Tesseract Voting for Maltese Paragraph OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Adam Darmanin","submitted_at":"2026-06-30T22:58:41Z","abstract_excerpt":"Maltese has decent text corpora and pretrained language models, but, like many languages outside the handful with large OCR benchmarks, only a single known real labelled PDF corpus for OCR training, 57 page, far below what paragraph-level training needs: low-resource for OCR specifically. With no real corpus to train on at scale, we built a synthetic training pipeline and a 5-stream Tesseract LV-ROVER ensemble, and report results on a 422-paragraph benchmark against a fine-tuned-Tesseract baseline of character error rate (CER) 0.0234. Ensemble recognition alone improves CER by 44 percent, to 0"},"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":"2607.00250","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T22:58:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"829a7ed4de5fc8abb2b12469546f545f6bb1af1b09aef2a63ba5b09d392bd04d","abstract_canon_sha256":"345d56a4eb4b3913a2cfe30a195523991b33f27ad3277ace3a8e787b6b00d99e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:41.094078Z","signature_b64":"60cpYmrZWv39jC56WCSfE42C38z1NJaszUAzs17i79z4qflqkCsCE0OKSGlEwe3l/TAOu6MbTSPjduloiyYiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9cd066c93089d581ceaf9c7686d9d26f3d1190618a103f2538889b07b9c1c8","last_reissued_at":"2026-07-02T00:18:41.093234Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:41.093234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LV-ROVER: Multi-Stream Tesseract Voting for Maltese Paragraph OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Adam Darmanin","submitted_at":"2026-06-30T22:58:41Z","abstract_excerpt":"Maltese has decent text corpora and pretrained language models, but, like many languages outside the handful with large OCR benchmarks, only a single known real labelled PDF corpus for OCR training, 57 page, far below what paragraph-level training needs: low-resource for OCR specifically. With no real corpus to train on at scale, we built a synthetic training pipeline and a 5-stream Tesseract LV-ROVER ensemble, and report results on a 422-paragraph benchmark against a fine-tuned-Tesseract baseline of character error rate (CER) 0.0234. Ensemble recognition alone improves CER by 44 percent, to 0"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00250","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/2607.00250/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":"2607.00250","created_at":"2026-07-02T00:18:41.093380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00250v1","created_at":"2026-07-02T00:18:41.093380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00250","created_at":"2026-07-02T00:18:41.093380+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWONAZWJGCE5","created_at":"2026-07-02T00:18:41.093380+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWONAZWJGCE5LAOO","created_at":"2026-07-02T00:18:41.093380+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWONAZWJ","created_at":"2026-07-02T00:18:41.093380+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/LWONAZWJGCE5LAOOV6OHNBWZ2J","json":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J.json","graph_json":"https://pith.science/api/pith-number/LWONAZWJGCE5LAOOV6OHNBWZ2J/graph.json","events_json":"https://pith.science/api/pith-number/LWONAZWJGCE5LAOOV6OHNBWZ2J/events.json","paper":"https://pith.science/paper/LWONAZWJ"},"agent_actions":{"view_html":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J","download_json":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J.json","view_paper":"https://pith.science/paper/LWONAZWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00250&json=true","fetch_graph":"https://pith.science/api/pith-number/LWONAZWJGCE5LAOOV6OHNBWZ2J/graph.json","fetch_events":"https://pith.science/api/pith-number/LWONAZWJGCE5LAOOV6OHNBWZ2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/action/storage_attestation","attest_author":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/action/author_attestation","sign_citation":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/action/citation_signature","submit_replication":"https://pith.science/pith/LWONAZWJGCE5LAOOV6OHNBWZ2J/action/replication_record"}},"created_at":"2026-07-02T00:18:41.093380+00:00","updated_at":"2026-07-02T00:18:41.093380+00:00"}