{"id":"W4393787782","doi":"10.5281/zenodo.6561382","title":"A Probabilistic Framework for Mutation Testing in Deep Neural Networks - Models archive Part 1","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; Computer science; Artificial neural network; Mutation; Deep neural networks; Artificial intelligence; Computational biology; 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":[0.0007445919,0.0002764307,0.0002811827,0.000361519,0.001714847,0.001592046,0.003094013,0.0001391461,0.003907031],"category_scores_gemma":[0.002014041,0.0003025503,0.00006775918,0.001266621,0.0001050178,0.0004964345,0.002489184,0.0009202863,0.0001313573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001967054,"about_ca_system_score_gemma":0.00001800424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003325233,"about_ca_topic_score_gemma":0.000003242538,"domain_scores_codex":[0.99716,0.0004029317,0.0004774022,0.00089726,0.0004514013,0.0006110251],"domain_scores_gemma":[0.9980028,0.0002931266,0.0003285132,0.0008342025,0.0003778955,0.0001634878],"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":[0.00003773614,0.0001652178,1.793252e-7,0.000352255,0.00002063553,0.00006030361,0.0004327216,0.05787859,0.000001079367,0.02377875,0.8521373,0.06513518],"study_design_scores_gemma":[0.0001912331,0.0002767216,0.000007508144,0.0000751012,0.00001152407,0.00008567563,0.00003355561,0.454534,3.153115e-7,0.0354238,0.5091121,0.0002485431],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.000006661242,0.00007236019,0.7661479,0.0002498714,0.00022174,0.000909242,0.2314164,0.0003530243,0.0006228007],"genre_scores_gemma":[0.002377372,0.00005127402,0.01791838,0.0002951769,0.0002600493,0.000002852064,0.9783213,0.0007493183,0.00002426614],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.7482295,"threshold_uncertainty_score":0.9999427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04948459791673763,"score_gpt":0.2555494789308763,"score_spread":0.2060648810141387,"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."}}