{"id":"W2076520128","doi":"10.1080/19401490802559409","title":"A demonstration of the effectiveness of inter-program comparative testing for diagnosing and repairing solution and coding errors in building simulation programs","year":2009,"lang":"en","type":"article","venue":"Journal of Building Performance Simulation","topic":"Fuel Cells and Related Materials","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Coding (social sciences); Computer science; Construct (python library); Reliability engineering; Computer engineering; Engineering; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01403956,0.0009589658,0.0004821917,0.001468082,0.0008433918,0.001045102,0.001811156,0.001015521,0.002380066],"category_scores_gemma":[0.07265306,0.0004317138,0.0005564979,0.0009295643,0.001116537,0.001960434,0.001540013,0.00120073,0.0002797894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133099,"about_ca_system_score_gemma":0.001503141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002982413,"about_ca_topic_score_gemma":0.002504309,"domain_scores_codex":[0.9884064,0.007462718,0.000706406,0.0008052985,0.002193006,0.0004261876],"domain_scores_gemma":[0.8942901,0.07800484,0.003084947,0.01354382,0.01056941,0.0005068457],"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":[0.002848778,0.004384184,0.05143994,0.0009897151,0.0003858643,0.0007053582,0.006548168,0.3527874,0.06485882,0.05149053,0.003917179,0.459644],"study_design_scores_gemma":[0.0003655057,0.005750215,0.01476573,0.0002552917,0.0001693343,0.0005614422,0.002003058,0.7620422,0.1952409,0.01110485,0.007544267,0.0001971778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4164521,0.0001291856,0.567884,0.00033083,0.00009635527,0.0005306024,0.0002726032,0.002853303,0.01145101],"genre_scores_gemma":[0.8159288,0.00004217372,0.18256,0.00004453383,0.00000757594,0.0002699516,0.0001665345,0.0002464164,0.0007340935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01403956,"threshold_uncertainty_score":0.07424921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03150123061377279,"score_gpt":0.3029270747721755,"score_spread":0.2714258441584027,"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."}}