{"id":"W4385966270","doi":"10.5281/zenodo.8256422","title":"A Probabilistic Framework for Mutation Testing in Deep Neural Networks - Models archive Part 4","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","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; Deep neural networks; Computational biology; Machine learning; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006108938,0.000120033,0.0001237639,0.0001773803,0.001892426,0.0007568746,0.001450498,0.00003190602,0.0003973744],"category_scores_gemma":[0.0008372518,0.0001332758,0.00003495185,0.001067007,0.00006093106,0.0004324542,0.001450488,0.0003781858,0.00005281556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001236653,"about_ca_system_score_gemma":0.000007921675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008939082,"about_ca_topic_score_gemma":6.099022e-7,"domain_scores_codex":[0.9982697,0.0002721545,0.0002694456,0.0004904959,0.0002873949,0.0004108494],"domain_scores_gemma":[0.9990026,0.000157475,0.0001308957,0.0003676811,0.0002386285,0.0001027603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004793359,0.0001665648,0.000005922948,0.00008547768,0.00001062516,0.00003145745,0.002678198,0.3550235,0.00003037234,0.3905928,0.002762762,0.2485644],"study_design_scores_gemma":[0.0002237326,0.0002814184,0.0001019085,0.00001960199,0.000003260194,0.00008687768,0.0001250118,0.8580657,0.000003308149,0.1288769,0.01207315,0.0001392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00129474,0.00004357928,0.992885,0.0005771723,0.0001100743,0.0005652568,0.00004208626,0.0004140892,0.004068029],"genre_scores_gemma":[0.9611835,0.000003828234,0.03783827,0.0002234958,0.0000879582,0.000001446045,0.0002858274,0.0003453941,0.00003022165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9598888,"threshold_uncertainty_score":0.999407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04788279144490647,"score_gpt":0.2440446908250057,"score_spread":0.1961618993800993,"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."}}