{"id":"W2075791583","doi":"10.2166/wst.2013.246","title":"Benchmark simulation models, quo vadis?","year":2013,"lang":"en","type":"article","venue":"Water Science & Technology","topic":"Wastewater Treatment and Nitrogen Removal","field":"Environmental Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Benchmarking; Computer science; Benchmark (surveying); Context (archaeology); Transparency (behavior); Data science; Process (computing); Task (project management); Usability; Status quo; Risk analysis (engineering); Process management; Management science; Systems engineering; Engineering; Human–computer interaction; Business","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":[0.01991258,0.001067982,0.001338471,0.001384159,0.0008187742,0.006780648,0.003769974,0.002445708,0.01230417],"category_scores_gemma":[0.07986252,0.0005812166,0.0009272237,0.002230437,0.001694895,0.00904424,0.004049506,0.002515193,0.002815672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002713937,"about_ca_system_score_gemma":0.003999877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005557117,"about_ca_topic_score_gemma":0.005659399,"domain_scores_codex":[0.9856493,0.009568908,0.0008249505,0.000885792,0.00262052,0.0004504291],"domain_scores_gemma":[0.9761405,0.01256949,0.001788703,0.005774572,0.002992691,0.0007340842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003370263,0.0002310858,0.005487456,0.0008543482,0.0003070929,0.0000986954,0.0006581212,0.1355528,0.001019108,0.6624461,0.05469424,0.1383139],"study_design_scores_gemma":[0.0001320116,0.0002057391,0.0009525216,0.0007936298,0.00007171653,0.00007019988,0.0007471128,0.3682052,0.001705564,0.4826627,0.1443589,0.00009479556],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.02604274,0.005188267,0.8124725,0.05394602,0.004093749,0.0003487276,0.003198344,0.009703818,0.08500587],"genre_scores_gemma":[0.5804806,0.004679782,0.3822919,0.006743697,0.001212708,0.001108692,0.004232008,0.003762662,0.01548798],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.01991258,"threshold_uncertainty_score":0.1053091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009987009864080715,"score_gpt":0.2111846139197233,"score_spread":0.2011976040556426,"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."}}