{"id":"W4394055305","doi":"10.5281/zenodo.6561381","title":"A Probabilistic Framework for Mutation Testing in Deep Neural Networks - Models archive Part 1","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; Machine learning; Genetics; Biology","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":[0.005321392,0.001892074,0.001278977,0.002104688,0.0006941778,0.002074452,0.004577765,0.002439612,0.01132154],"category_scores_gemma":[0.0196672,0.001067935,0.002013116,0.002620622,0.0009097965,0.002015291,0.002698957,0.004366945,0.006964264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002239298,"about_ca_system_score_gemma":0.003510598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02269218,"about_ca_topic_score_gemma":0.0512613,"domain_scores_codex":[0.9969822,0.001217003,0.0002331866,0.0005918276,0.0007792655,0.0001965303],"domain_scores_gemma":[0.9947184,0.002643327,0.000239374,0.001446794,0.0008095602,0.0001424648],"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":[0.0004883001,0.0003910495,0.005322881,0.000815801,0.0003426259,0.0001541901,0.00009137915,0.3293348,0.001343622,0.04539656,0.4897523,0.1265665],"study_design_scores_gemma":[0.0003527146,0.00008390946,0.001836302,0.0001351933,0.0000503372,0.0001734104,0.00002515376,0.8430557,0.001465998,0.08872803,0.06403514,0.00005811407],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.01575601,0.003134889,0.6431901,0.002789646,0.0004233378,0.0006469201,0.294418,0.03141955,0.008221537],"genre_scores_gemma":[0.1247539,0.001319933,0.3680805,0.001498673,0.0002564966,0.00248433,0.4897309,0.003933411,0.0079418],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.02269218,"threshold_uncertainty_score":0.04512018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02092767895809806,"score_gpt":0.2468258120546542,"score_spread":0.2258981330965562,"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."}}