{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TZQMRINH7NJZLHHAARLEYFQAFM","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":"be079054c7912d79740c7eedb13c589b5af0f37bc831c215fb95b3c555fb7f5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T11:38:20Z","title_canon_sha256":"e366c40ea4baefe8a563415157afbc1c3e502671786ba62f363e3eeafd4b9a4e"},"schema_version":"1.0","source":{"id":"2507.06761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06761","created_at":"2026-07-05T11:34:22Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06761v1","created_at":"2026-07-05T11:34:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06761","created_at":"2026-07-05T11:34:22Z"},{"alias_kind":"pith_short_12","alias_value":"TZQMRINH7NJZ","created_at":"2026-07-05T11:34:22Z"},{"alias_kind":"pith_short_16","alias_value":"TZQMRINH7NJZLHHA","created_at":"2026-07-05T11:34:22Z"},{"alias_kind":"pith_short_8","alias_value":"TZQMRINH","created_at":"2026-07-05T11:34:22Z"}],"graph_snapshots":[{"event_id":"sha256:6ef1cfb234ce139d51e0e80de57932efb4501a373dd1f53b79567a4d3d788c88","target":"graph","created_at":"2026-07-05T11:34:22Z","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/2507.06761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Manchu, a critically endangered language essential for understanding early modern Eastern Eurasian history, lacks effective OCR systems that can handle real-world historical documents. This study develops high-performing OCR systems by fine-tuning three open-source vision-language models (LLaMA-3.2-11B, Qwen2.5-VL-7B, Qwen2.5-VL-3B) on 60,000 synthetic Manchu word images using parameter-efficient training. LLaMA-3.2-11B achieved exceptional performance with 98.3\\% word accuracy and 0.0024 character error rate on synthetic data, while crucially maintaining 93.1\\% accuracy on real-world handwrit","authors_text":"Donghyeok Choi, Yan Hon Michael Chung","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T11:38:20Z","title":"Finetuning Vision-Language Models as OCR Systems for Low-Resource Languages: A Case Study of Manchu"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06761","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:f4ec9c02750a3918c8be43a1e3547f9b733ecc8882abae1d08848374712dbecb","target":"record","created_at":"2026-07-05T11:34:22Z","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":"be079054c7912d79740c7eedb13c589b5af0f37bc831c215fb95b3c555fb7f5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T11:38:20Z","title_canon_sha256":"e366c40ea4baefe8a563415157afbc1c3e502671786ba62f363e3eeafd4b9a4e"},"schema_version":"1.0","source":{"id":"2507.06761","kind":"arxiv","version":1}},"canonical_sha256":"9e60c8a1a7fb53959ce004564c16002b09b58f11d13155555ac796b201e17770","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e60c8a1a7fb53959ce004564c16002b09b58f11d13155555ac796b201e17770","first_computed_at":"2026-07-05T11:34:22.778424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:22.778424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jeO5Qvzv/NJS0b2Qy3eBlGedLRUL0PwsGTGqKi61o5R8TEOA6UY7R7r06JNJgcdbjIORq9wOnmFQFilzPc3NAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:22.778920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4ec9c02750a3918c8be43a1e3547f9b733ecc8882abae1d08848374712dbecb","sha256:6ef1cfb234ce139d51e0e80de57932efb4501a373dd1f53b79567a4d3d788c88"],"state_sha256":"84925f67c5ddb1a7c9c0ebd836342e0d71bdbbd6ab18451220e277f5869db5c4"}