{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004022295,0.00009309092,0.0001080092,0.0001475782,0.0005209768,0.0006248247,0.0005694479,0.00004270021,0.000007698448],"category_scores_gemma":[0.00004067122,0.00006330805,0.00004086788,0.0002381881,0.0000628835,0.0004523409,0.00032779,0.0003972688,0.00001117962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004225445,"about_ca_system_score_gemma":0.00003030395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000338956,"about_ca_topic_score_gemma":5.650838e-7,"domain_scores_codex":[0.9992183,0.0001129207,0.0002149415,0.0001589413,0.0001254244,0.0001694406],"domain_scores_gemma":[0.9993472,0.0001495346,0.0001545522,0.000199676,0.0001153394,0.00003377111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000519518,0.00002076209,0.001105798,0.000004868774,0.00003093556,0.000006187068,0.0003474786,0.0002106069,0.001291914,0.009431734,0.0004165993,0.9871279],"study_design_scores_gemma":[0.00104485,0.0001680421,0.0254674,0.0002332875,0.00004087526,0.00073135,0.0005808101,0.8363416,0.003230596,0.1233328,0.00849969,0.0003286637],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1191509,0.0006195778,0.8717293,0.007574519,0.0005190886,0.0000661232,1.032022e-7,0.000150513,0.000189973],"genre_scores_gemma":[0.9030192,0.0003091179,0.09552859,0.0008183647,0.000135297,0.000003084682,6.688492e-7,0.000005068252,0.0001806325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9867992,"threshold_uncertainty_score":0.6025199,"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."}}