{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009625287,0.0001051954,0.0002628511,0.0001612295,0.0000636762,0.00002909017,0.00004514073,0.00007805948,1.149483e-7],"category_scores_gemma":[0.0001202246,0.00008470973,0.00004242537,0.0002289507,0.00003966613,0.0004456796,0.0000124462,0.0001148171,5.154568e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006930297,"about_ca_system_score_gemma":0.00001146171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004016033,"about_ca_topic_score_gemma":0.000001096272,"domain_scores_codex":[0.9990716,0.00006478046,0.0005516101,0.00008278499,0.0001092699,0.0001199536],"domain_scores_gemma":[0.9988117,0.0005747913,0.0003828731,0.00005063801,0.0001592141,0.00002083977],"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":[0.0001057392,0.00002491525,0.02175664,0.000718754,0.00001359304,1.636438e-7,0.0002838727,0.8496856,0.1045081,0.00002254569,9.846621e-8,0.02287994],"study_design_scores_gemma":[0.0005977987,0.0003842807,0.05269689,0.002775818,0.00003360557,0.000005937387,0.00003565643,0.9000458,0.04309275,0.0002539135,0.000002556414,0.0000749676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9670732,0.0003606039,0.03198422,0.000004574881,0.0001552365,0.0003792953,5.218488e-7,0.00002038196,0.0000219561],"genre_scores_gemma":[0.9904679,0.00004564318,0.009436641,0.000001015048,0.000035529,0.000003784791,7.987992e-7,0.000008480976,1.789541e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06141538,"threshold_uncertainty_score":0.3454363,"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."}}