{"id":"W4416109760","doi":"10.1093/comjnl/bxaf124","title":"CV content recognition using YOLOv8 and Tesseract-OCR deep learning","year":2025,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Preprocessor; Consistency (knowledge bases); Sorting; Variety (cybernetics); Deep learning; Hyperparameter; Analytics; Precision and recall; Component (thermodynamics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006645885,0.001269201,0.0008675903,0.004115173,0.000399823,0.001390938,0.001639508,0.001075311,0.006908273],"category_scores_gemma":[0.002143545,0.0002829897,0.0009534995,0.001827023,0.0003140404,0.00123109,0.001042723,0.001036751,0.00721228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008867832,"about_ca_system_score_gemma":0.0008747627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01184011,"about_ca_topic_score_gemma":0.01222917,"domain_scores_codex":[0.9992926,0.0000549402,0.00005203822,0.0002680531,0.0002226193,0.00010961],"domain_scores_gemma":[0.9991772,0.0001494066,0.00008575952,0.0001567481,0.0003757243,0.00005524013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002986169,0.0001886371,0.00221372,0.0002132143,0.00005592623,0.0001069027,0.00005169647,0.00934876,0.02899612,0.0004756273,0.01442819,0.9436225],"study_design_scores_gemma":[0.00005459574,0.0002519018,0.008821333,0.0001067512,0.00009441048,0.0002057514,0.0001738925,0.8986917,0.07440101,0.001081031,0.0160458,0.0000719707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3078713,0.004077146,0.5633147,0.0006838195,0.00132962,0.00110777,0.0113156,0.08923151,0.02106866],"genre_scores_gemma":[0.5163596,0.001165289,0.4352836,0.0003695506,0.0002216533,0.0005203247,0.02066848,0.0009845734,0.0244269],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01184011,"threshold_uncertainty_score":0.0235424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06729306244984125,"score_gpt":0.276650143117134,"score_spread":0.2093570806672927,"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."}}