{"id":"W2132705868","doi":"10.5194/gmd-5-1009-2012","title":"Assessing climate model software quality: a defect density analysis of three models","year":2012,"lang":"en","type":"article","venue":"Geoscientific model development","topic":"Software Engineering Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Executable; Context (archaeology); Software; Climate model; Computer science; Software quality; Quality (philosophy); Trustworthiness; Climate change; Software development; Geography; Geology; Programming language; Computer security","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":[0.00475558,0.0003129111,0.0005795849,0.001142023,0.0004089583,0.0004097579,0.001317659,0.0001271351,0.00000743878],"category_scores_gemma":[0.0003335007,0.0003068841,0.0003080292,0.002727503,0.00009339437,0.001952052,0.001326803,0.000233984,0.00002483318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003131352,"about_ca_system_score_gemma":0.0005594626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005089609,"about_ca_topic_score_gemma":0.00006560243,"domain_scores_codex":[0.9953759,0.00008856756,0.0007799095,0.0008804987,0.001625589,0.001249588],"domain_scores_gemma":[0.9971824,0.0003437412,0.0002266888,0.00144817,0.0004282087,0.0003707566],"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":[0.000004214497,0.0001713934,0.03503288,0.00008953395,0.0003027689,0.000001577888,0.002433339,0.9433739,0.0004851542,0.006214437,0.00006440184,0.01182642],"study_design_scores_gemma":[0.0001308715,0.000003226666,0.04698272,0.00002709029,0.00009077383,0.000001596614,0.00001533707,0.9497729,0.0008923357,0.001722671,0.00001044196,0.000350063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4160161,0.00008907837,0.5832379,0.00001171291,0.0002156807,0.0001367804,0.00001293648,0.0002279847,0.00005177496],"genre_scores_gemma":[0.5747291,0.000003298312,0.4250733,0.00002270013,0.000006305318,0.00003049064,0.00002538762,0.0000141228,0.00009534519],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.158713,"threshold_uncertainty_score":0.9999383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1135921490724538,"score_gpt":0.3292275387615579,"score_spread":0.215635389689104,"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."}}