{"paper":{"title":"Comparing OCR Pipelines for Folkloristic Text Digitization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.DL","authors_text":"Alina L. Machidon, Octavian M. Machidon","submitted_at":"2025-07-25T09:22:41Z","abstract_excerpt":"The digitization of historical folkloristic materials presents unique challenges due to diverse text layouts, varying print and handwriting styles, and linguistic variations. This study explores different optical character recognition (OCR) approaches for Slovene folkloristic and historical text digitization, integrating both traditional methods and large language models (LLMs) to improve text transcription accuracy while maintaining linguistic and structural integrity. We compare single-stage OCR techniques with multi-stage pipelines that incorporate machine learning-driven post-processing fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19092","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/2507.19092/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"}