{"id":"W4413319364","doi":"10.1109/aitest66680.2025.00019","title":"CODEX: Testing Machine Learning with the Coverage of Data Explorer Tool","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Systems Engineering Research Center; U.S. Department of Defense","keywords":"Computer science; Artificial intelligence","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":[0.0068032,0.00250013,0.0008299095,0.003507798,0.0006297166,0.002593007,0.00392241,0.002098594,0.01364722],"category_scores_gemma":[0.05326802,0.0009949185,0.001412319,0.001958563,0.001475851,0.003420054,0.003927063,0.002705435,0.005950646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009817993,"about_ca_system_score_gemma":0.002388094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004198663,"about_ca_topic_score_gemma":0.003903661,"domain_scores_codex":[0.9927294,0.002241473,0.0007582195,0.001140231,0.002764558,0.0003660361],"domain_scores_gemma":[0.9610243,0.03096859,0.001243355,0.003709912,0.002596266,0.0004575948],"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":[0.002224285,0.001220565,0.03686565,0.003633302,0.0005739034,0.001879574,0.001554146,0.07627746,0.01147558,0.04629199,0.3960078,0.4219958],"study_design_scores_gemma":[0.001171343,0.001119766,0.0131423,0.001329318,0.0001405833,0.001359115,0.0004628763,0.698332,0.04311261,0.06910358,0.1704318,0.0002946579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.0675895,0.001699866,0.340889,0.001935596,0.0005913648,0.0008790864,0.01905476,0.5465537,0.02080718],"genre_scores_gemma":[0.3712304,0.0009350816,0.4836344,0.002335904,0.0001995149,0.003067696,0.058053,0.0719353,0.008608659],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01364722,"threshold_uncertainty_score":0.04565454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05548895724841843,"score_gpt":0.2860890169030726,"score_spread":0.2306000596546542,"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."}}