{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005847221,0.00007611819,0.00009146797,0.00004772145,0.0001616665,0.0001137827,0.00139452,0.00001804712,0.00001394513],"category_scores_gemma":[0.0003583112,0.00004258151,0.000009572495,0.0005016442,0.00003592991,0.0004881631,0.0006743176,0.0002059285,0.00001000898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007628565,"about_ca_system_score_gemma":0.00006670478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000166996,"about_ca_topic_score_gemma":0.00002869106,"domain_scores_codex":[0.9991782,0.0001030194,0.0001408205,0.0002992245,0.000167191,0.0001115515],"domain_scores_gemma":[0.9981599,0.0004713012,0.00009697113,0.001195332,0.00006202132,0.00001447407],"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":[0.00002274221,0.00007858613,0.09634952,0.00006120076,0.0000505946,0.000004118553,0.0004968513,0.004445307,0.001532735,0.148753,0.004597767,0.7436076],"study_design_scores_gemma":[0.0002564279,0.000057637,0.02074763,0.00003706571,0.00001073352,0.00000438179,0.00005126078,0.9276636,0.0002438837,0.0002646572,0.0505663,0.00009639945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006301733,0.00006457366,0.9699128,0.003679642,0.00003217816,0.00008581377,0.000005537786,0.0001474962,0.0197702],"genre_scores_gemma":[0.9413292,0.00001036797,0.05596431,0.0004009076,0.00001422226,0.000005496288,0.00006406087,0.000004479215,0.002206978],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9350274,"threshold_uncertainty_score":0.2591388,"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."}}