{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004510154,0.001636168,0.001567787,0.001617162,0.0006603728,0.001682371,0.003336867,0.00201025,0.006212225],"category_scores_gemma":[0.02165757,0.0006234976,0.001562765,0.001001391,0.002511011,0.003329859,0.003460586,0.003165257,0.0007075327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001211021,"about_ca_system_score_gemma":0.0009022043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001819471,"about_ca_topic_score_gemma":0.00127948,"domain_scores_codex":[0.9964256,0.001485895,0.0001926499,0.0006423232,0.0009888017,0.0002648436],"domain_scores_gemma":[0.9803715,0.01495693,0.0005699637,0.001769071,0.001942573,0.0003898148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004375829,0.0001396078,0.002357607,0.0003886331,0.0001931759,0.0006246918,0.000266161,0.5736135,0.009804692,0.2335852,0.004280556,0.1743086],"study_design_scores_gemma":[0.000007791919,0.00004795865,0.000115752,0.00001361354,0.00001556121,0.00004251783,0.00001195302,0.9246346,0.001168313,0.07337458,0.0005600516,0.000007264058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007829461,0.0001682777,0.9893932,0.0003298055,0.00003801511,0.00003906892,0.00006350729,0.000383705,0.001754977],"genre_scores_gemma":[0.7444153,0.0003460619,0.2448062,0.0003871583,0.0003090591,0.0002867272,0.0005670571,0.0005277622,0.008354605],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006212225,"threshold_uncertainty_score":0.02385223,"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."}}