{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01859023,0.0006749748,0.0006612408,0.009184581,0.001535921,0.004269205,0.001486831,0.001079112,0.004325232],"category_scores_gemma":[0.1965079,0.0004364459,0.0007014053,0.007114204,0.001869421,0.004760361,0.002537566,0.0007766977,0.001792094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003150924,"about_ca_system_score_gemma":0.001641529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01860771,"about_ca_topic_score_gemma":0.0227629,"domain_scores_codex":[0.9724907,0.009783558,0.003899871,0.002075547,0.01118665,0.0005636322],"domain_scores_gemma":[0.8378826,0.1087786,0.01040707,0.009756234,0.03161903,0.001556442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004373966,0.000523911,0.1174242,0.001754529,0.0003578003,0.0004225736,0.02997682,0.002612978,0.01178195,0.003091438,0.009627917,0.8180519],"study_design_scores_gemma":[0.0008772556,0.006874566,0.7500826,0.001545327,0.001247196,0.001842803,0.05262589,0.02074828,0.06324843,0.00497699,0.09517586,0.0007547736],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9407227,0.00447164,0.01294666,0.001036646,0.0002958017,0.001276665,0.001287889,0.001899382,0.03606253],"genre_scores_gemma":[0.9473624,0.00240959,0.04037245,0.0004992881,0.0001446964,0.0004766556,0.001492474,0.0008043672,0.006438154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9957308,"threshold_uncertainty_score":0.09831572,"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."}}