{"id":"W2068919549","doi":"10.1016/j.jocs.2010.12.002","title":"Examining random and designed tests to detect code mistakes in scientific software","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Science","topic":"Software Engineering Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Royal Military College of Canada","funders":"","keywords":"Computer science; Mistake; Code (set theory); Test (biology); Software; Code coverage; Software bug; Programming language; Reliability engineering; Engineering","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":[0.003863998,0.00009137307,0.0001547687,0.0009029296,0.0002348637,0.0007517593,0.001208973,0.00002727941,0.000004297488],"category_scores_gemma":[0.006504796,0.00007988101,0.0000234401,0.00198817,0.0003216596,0.0009371275,0.0001171711,0.0002892118,0.000005642393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006896375,"about_ca_system_score_gemma":0.0007540367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003384264,"about_ca_topic_score_gemma":0.00001381896,"domain_scores_codex":[0.9979625,0.00003912951,0.0003296702,0.0003004755,0.001059667,0.0003085544],"domain_scores_gemma":[0.9964742,0.002274415,0.0001187421,0.0001855531,0.0006505406,0.0002965452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.000100037,0.0001228069,0.1045364,0.00004178666,0.00001415626,0.0002246077,0.004618755,0.3783693,0.2781487,0.002461869,0.0005028808,0.2308588],"study_design_scores_gemma":[0.00130679,0.0002625239,0.9265121,0.0001012257,0.000002226084,0.0005141432,0.00003505947,0.05852729,0.004714506,0.007476657,0.0003128074,0.0002346356],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5413347,0.00002927493,0.4580367,0.0001715586,0.0003428257,0.00005805632,4.634526e-7,0.00001735874,0.000009107466],"genre_scores_gemma":[0.637332,2.285905e-7,0.362595,0.00003226833,0.00002725554,0.000001455366,6.857795e-8,0.000003020394,0.000008718481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8219758,"threshold_uncertainty_score":0.7787318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02964945215008588,"score_gpt":0.2961040621995382,"score_spread":0.2664546100494523,"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."}}