{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008409349,0.0006670224,0.0007095002,0.0006980797,0.00044493,0.0007100819,0.002721333,0.0005424252,0.00009813393],"category_scores_gemma":[0.001205185,0.0007095754,0.0002087817,0.001580725,0.00009314096,0.0007104371,0.001025881,0.001758045,0.000002132103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000490772,"about_ca_system_score_gemma":0.000505412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003656286,"about_ca_topic_score_gemma":0.003950336,"domain_scores_codex":[0.9957137,0.0002607956,0.0009585203,0.001280267,0.0005374026,0.001249357],"domain_scores_gemma":[0.9958523,0.001324647,0.0007424411,0.001628698,0.0001575112,0.0002943873],"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":[0.00007739224,0.0003956011,0.00008565527,0.0005056685,0.0000459597,0.0003142307,0.0002261214,0.6289508,0.000001710488,0.1001714,0.2381126,0.03111299],"study_design_scores_gemma":[0.0002112725,0.0002528672,0.00009755152,0.0001560373,0.0000354599,0.0001168557,0.00001638479,0.7613572,0.000001944912,0.2288506,0.008336908,0.0005667945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001250827,0.0006321245,0.80474,0.0007005209,0.0003293992,0.00165166,0.1915623,0.0003554107,0.00001615228],"genre_scores_gemma":[0.00389067,0.0001319612,0.6333848,0.002530029,0.000379248,0.00899959,0.3505562,0.000105373,0.0000221652],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2297756,"threshold_uncertainty_score":0.9995356,"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."}}