{"id":"W4381053704","doi":"10.1007/s11432-022-3580-5","title":"Toward actionable testing of deep learning models","year":2023,"lang":"en","type":"article","venue":"Science China Information Sciences","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Data science","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004891634,0.0001297943,0.00015401,0.001109947,0.001560453,0.0006517722,0.002504691,0.00003918443,0.00001310579],"category_scores_gemma":[0.002536053,0.0001111729,0.00004226338,0.01152449,0.0009524185,0.01997036,0.0008162801,0.0002352468,0.0001235673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007266745,"about_ca_system_score_gemma":0.0004334442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001120717,"about_ca_topic_score_gemma":9.698617e-7,"domain_scores_codex":[0.9970212,0.00005295642,0.0004515605,0.0003277798,0.001603972,0.000542508],"domain_scores_gemma":[0.9985837,0.0002414371,0.0004286008,0.0002811083,0.0003560795,0.0001091174],"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":[7.449977e-7,0.000003351229,0.001134548,0.00001316396,9.12272e-7,4.085043e-7,0.004739725,0.8652992,0.0003496234,0.06065422,0.00001281061,0.06779126],"study_design_scores_gemma":[0.00009098709,0.0000663198,0.007408767,0.0000186545,0.000001118981,0.000009937036,0.001283999,0.9741567,0.0009773987,0.01564597,0.0002040312,0.000136148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07256457,0.00000840443,0.8781176,0.00051451,0.0006176108,0.0001278726,5.255825e-7,0.0005421493,0.04750679],"genre_scores_gemma":[0.9166262,0.000005522831,0.08323345,0.00005497837,0.00002354056,0.000007489868,0.00000121373,0.000002455742,0.00004516894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8440616,"threshold_uncertainty_score":0.9997394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06458478689624302,"score_gpt":0.3011856642803998,"score_spread":0.2366008773841567,"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."}}