{"id":"W3185468338","doi":"10.48550/arxiv.2107.13491","title":"Models of Computational Profiles to Study the Likelihood of DNN Metamorphic Test Cases","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Metamorphic rock; Test (biology); Maximum likelihood; Computer science; Artificial intelligence; Econometrics; Geology; Machine learning; Statistics; Geochemistry; Paleontology; Mathematics","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":[0.000540322,0.0002762391,0.0005009196,0.0002529379,0.0001510194,0.00006453292,0.002290549,0.0001146584,0.00002139107],"category_scores_gemma":[0.000343878,0.0002565214,0.0002075385,0.0009823847,0.0001178935,0.0003053483,0.004108579,0.0005299872,0.000004210018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007966766,"about_ca_system_score_gemma":0.0004326862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004746338,"about_ca_topic_score_gemma":0.00005387406,"domain_scores_codex":[0.9978726,0.0004186819,0.0003580152,0.0008539323,0.0002612816,0.0002354821],"domain_scores_gemma":[0.9965706,0.001114167,0.0004929898,0.001175174,0.0005527976,0.00009429643],"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":[0.00001416297,0.0003871164,0.005724287,0.00005054118,0.0002076955,0.0002107783,0.001624114,0.9733763,0.00002238631,0.01803393,0.0000125198,0.0003361123],"study_design_scores_gemma":[0.0004051556,0.0001879348,0.006528778,0.00009563775,0.0001846798,0.000009215672,0.001300061,0.9665239,0.0001826192,0.02430516,0.000002518218,0.0002743084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4588814,0.00003496614,0.5402941,0.00008223297,0.0001435075,0.0003874112,0.00001307374,0.00004237229,0.0001209509],"genre_scores_gemma":[0.9811657,0.000006997145,0.01866613,0.00003535662,0.00003460643,0.000002514092,0.00001007412,0.00001611789,0.00006251175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5222843,"threshold_uncertainty_score":0.9999887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09383745150203482,"score_gpt":0.2270443138388205,"score_spread":0.1332068623367857,"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."}}