{"id":"W4393689244","doi":"10.5281/zenodo.6577005","title":"A Probabilistic Framework for Mutation Testing in Deep Neural Networks - Models archive Part 2","year":2022,"lang":"en","type":"dataset","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; Artificial neural network; Mutation; Computer science; Artificial intelligence; Deep neural networks; 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":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007412002,0.0002763574,0.0002812401,0.0003613215,0.001714951,0.001594924,0.00309258,0.0001391467,0.00384573],"category_scores_gemma":[0.001993773,0.0003024678,0.00006774824,0.0012658,0.0001050166,0.0004967183,0.002488892,0.0009201096,0.0001301868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001967524,"about_ca_system_score_gemma":0.00001793734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003353176,"about_ca_topic_score_gemma":0.000003258547,"domain_scores_codex":[0.9971607,0.000402818,0.000477581,0.0008966997,0.0004513074,0.0006108377],"domain_scores_gemma":[0.998008,0.0002896579,0.0003288878,0.0008328439,0.0003771841,0.0001634634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003768306,0.0001656937,1.751172e-7,0.0003560363,0.00002070078,0.00006187239,0.000434392,0.05828615,0.00000105139,0.02419827,0.8496408,0.06679711],"study_design_scores_gemma":[0.0001915854,0.0002756955,0.000007378615,0.00007404118,0.00001144503,0.000085504,0.00003314153,0.4513614,3.124671e-7,0.03550887,0.5122035,0.0002471532],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.000006664992,0.00007378056,0.7679942,0.000250343,0.000224206,0.0009135476,0.2295435,0.0003551516,0.0006385618],"genre_scores_gemma":[0.002342665,0.00005234468,0.01757399,0.0002948743,0.0002629776,0.000002803346,0.9786984,0.0007476424,0.00002430689],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.7504202,"threshold_uncertainty_score":0.9999427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04808160967153502,"score_gpt":0.255099248751793,"score_spread":0.207017639080258,"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."}}