{"id":"W3199517873","doi":"","title":"Digitization Decisions: Comparing OCR Software for Librarian and Archivist Use","year":2021,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Digitization; Archivist; Computer science; Software; World Wide Web; Special collections; Information retrieval; Library science; Programming language; Computer vision","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001577675,0.0001849509,0.0003730671,0.0003138001,0.0004927779,0.007546747,0.0006457611,0.00001115481,0.001029655],"category_scores_gemma":[0.0003694959,0.0001665135,0.0001172214,0.0001362506,0.0001818618,0.00492043,0.0007213716,0.0001127244,0.00000646186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000159025,"about_ca_system_score_gemma":0.00006270155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007168507,"about_ca_topic_score_gemma":0.00008699368,"domain_scores_codex":[0.9986259,0.00005617591,0.0004813964,0.0003141319,0.0003057726,0.0002166547],"domain_scores_gemma":[0.9983078,0.000862881,0.0002648,0.0002027892,0.0002039617,0.0001578055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0003344871,0.0009605233,0.09465634,0.0003399049,0.0006369728,0.00008908849,0.002031971,0.0003376998,0.0003809367,0.5081055,0.09970626,0.2924203],"study_design_scores_gemma":[0.0004399172,0.00001158342,0.4966133,0.0005762988,0.00006113724,0.000007412867,0.0001533493,0.0001857032,0.0002585942,0.2895869,0.2118074,0.0002984048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7778748,0.003467685,0.01839428,0.0008349967,0.001228056,0.001250826,0.001305132,0.0001552358,0.1954889],"genre_scores_gemma":[0.9906244,0.001881235,0.001214736,0.0005269345,0.000292414,0.00004898483,0.0003678429,0.0000398403,0.005003667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.401957,"threshold_uncertainty_score":0.9998835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4108773341849517,"score_gpt":0.4719787724928549,"score_spread":0.06110143830790316,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}