{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001411521,0.0003287657,0.0004020715,0.0003373457,0.0002649834,0.0004981074,0.002496666,0.000142565,0.000003134797],"category_scores_gemma":[0.0008397264,0.0002409371,0.0001103809,0.0005772704,0.0002904958,0.0005026862,0.0008428934,0.0004114973,0.00000283091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001570782,"about_ca_system_score_gemma":0.0008993324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008401481,"about_ca_topic_score_gemma":0.000003780036,"domain_scores_codex":[0.9973727,0.00003475153,0.0005547466,0.0008982744,0.0006804485,0.0004591109],"domain_scores_gemma":[0.992379,0.005475769,0.0006062942,0.001047668,0.0004347007,0.00005661686],"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":[5.619502e-7,0.000008751511,0.0007838173,0.00003901506,0.000005322283,0.000003423718,0.0003622708,0.001673004,0.0001342673,0.002140921,0.00003052007,0.9948182],"study_design_scores_gemma":[0.0001846037,0.0002368346,0.0009564937,0.0004496429,0.00001157976,0.00006352602,3.805094e-7,0.7377296,0.002588332,0.2571934,0.0001952681,0.0003903717],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001100279,0.0001005001,0.996851,0.0004441252,0.0007903815,0.0006396226,0.000005864983,0.0008540582,0.0002044458],"genre_scores_gemma":[0.2230105,0.000002022132,0.7762967,0.0004535189,0.0001855296,0.0000143392,0.000002915725,0.00002218295,0.00001224241],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9944277,"threshold_uncertainty_score":0.9825129,"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."}}