{"id":"W4393580462","doi":"10.5281/zenodo.6577004","title":"A Probabilistic Framework for Mutation Testing in Deep Neural Networks - Models archive Part 2","year":2022,"lang":"en","type":"dataset","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Probabilistic logic; Mutation; Artificial neural network; Computer science; Artificial intelligence; Genetics; Biology; Gene","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"],"consensus_categories":[],"category_scores_codex":[0.000836894,0.0006668358,0.0007096531,0.0006976775,0.0004449587,0.000711438,0.002720003,0.0005424279,0.00009650388],"category_scores_gemma":[0.001192381,0.0007093713,0.0002087462,0.001579645,0.00009313982,0.0007108655,0.001025754,0.001757689,0.000002112058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004908957,"about_ca_system_score_gemma":0.0005034317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003688594,"about_ca_topic_score_gemma":0.003970836,"domain_scores_codex":[0.9957147,0.0002607183,0.0009589006,0.001279426,0.0005372855,0.001248955],"domain_scores_gemma":[0.9958711,0.001308125,0.0007433317,0.001625896,0.0001571978,0.00029434],"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":[0.00007693728,0.0003950573,0.00008316827,0.0005091468,0.00004591009,0.0003214405,0.0002260433,0.6302072,0.000001656418,0.101538,0.2347641,0.03183139],"study_design_scores_gemma":[0.0002125203,0.0002528741,0.00009615554,0.0001543224,0.00003534255,0.0001170699,0.00001623548,0.7600818,0.000001934022,0.2298521,0.008614052,0.000565679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001247008,0.0006428655,0.8070576,0.0006993595,0.0003320505,0.001653865,0.1892289,0.0003563671,0.00001652363],"genre_scores_gemma":[0.003861599,0.0001359543,0.6300025,0.002547607,0.0003868399,0.008909303,0.3540279,0.0001059693,0.00002238296],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2261501,"threshold_uncertainty_score":0.9995357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02035522874740122,"score_gpt":0.2464136732920858,"score_spread":0.2260584445446845,"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."}}