{"id":"W2964374341","doi":"10.1007/978-3-030-28423-7_9","title":"Mutant Accuracy Testing for Assessing the Implementation of Numerical Algorithms","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Implementation; Computer science; MATLAB; Algorithm; Regression testing; Process (computing); Mutation; Software; Software development; Programming language","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":[0.00435932,0.001201455,0.0008065127,0.002456446,0.0004754145,0.001243669,0.003142649,0.001593877,0.002513995],"category_scores_gemma":[0.0543691,0.0004640849,0.0006818953,0.001527462,0.00121259,0.002341884,0.001110016,0.001414101,0.0005666564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008327041,"about_ca_system_score_gemma":0.001008339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002004528,"about_ca_topic_score_gemma":0.001956158,"domain_scores_codex":[0.9908879,0.004055422,0.0006283991,0.0007611585,0.003332204,0.0003348377],"domain_scores_gemma":[0.9324275,0.05085191,0.002786292,0.007646435,0.005541054,0.0007469074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001489766,0.0008133163,0.04085638,0.0006230272,0.0002570886,0.0003745954,0.000356089,0.3032987,0.04798938,0.03922824,0.00638176,0.5583316],"study_design_scores_gemma":[0.00004519686,0.000435179,0.003945117,0.0000667914,0.00005204985,0.0002633597,0.00005866325,0.9515815,0.02934058,0.0130536,0.001122491,0.00003537427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.174795,0.0007961859,0.8139892,0.0001930767,0.0001422052,0.0001153094,0.0003433359,0.005195756,0.004429978],"genre_scores_gemma":[0.5856254,0.0001460835,0.4115942,0.00005226293,0.00002298557,0.000111839,0.0005404163,0.0005564694,0.001350375],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00435932,"threshold_uncertainty_score":0.02305454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0439389944210681,"score_gpt":0.3484687972418413,"score_spread":0.3045298028207732,"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."}}