{"id":"W4283065923","doi":"","title":"A testing approach for dependable Machine Learning systems","year":2022,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Computer science; System testing; Reliability engineering; Machine learning; Artificial intelligence; Software engineering; Engineering","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01246021,0.000486722,0.0005988475,0.0003273982,0.001490515,0.00127249,0.004330549,0.0002725379,0.00004085555],"category_scores_gemma":[0.006741334,0.0005530912,0.0002588216,0.0008152091,0.000105233,0.0003234945,0.007333559,0.002064223,0.000007903514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003072768,"about_ca_system_score_gemma":0.0004708067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002823718,"about_ca_topic_score_gemma":0.00005758019,"domain_scores_codex":[0.9883088,0.008045717,0.0007222611,0.001534638,0.0007444319,0.0006441213],"domain_scores_gemma":[0.9902314,0.004211724,0.001074539,0.002637908,0.001648635,0.000195805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001678004,0.0005233985,0.006292527,0.0009917277,0.000169279,0.00001673148,0.008317372,0.6961752,0.0006735939,0.2455558,0.0003573105,0.04091034],"study_design_scores_gemma":[0.0004713209,8.986435e-7,0.0001817967,0.0004043238,0.0000344147,0.00002802845,0.0001222729,0.9840912,0.0003708378,0.001367542,0.01239486,0.0005324586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001577791,0.001373905,0.9545255,0.001145066,0.000594918,0.001014164,0.00003519315,0.000936144,0.03879727],"genre_scores_gemma":[0.2826293,0.00002966956,0.7078596,0.00003286601,0.00005878543,0.00052112,0.0005951854,0.00008747205,0.008185938],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2879161,"threshold_uncertainty_score":0.9998094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0259846505532992,"score_gpt":0.2442579682207164,"score_spread":0.2182733176674172,"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."}}