{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000176411,0.0001536963,0.0001213032,0.0002839258,0.0003302207,0.00008198621,0.0006964359,0.00010791,0.001845299],"category_scores_gemma":[0.000008166077,0.00009877628,0.0000350463,0.0008361288,0.001159404,0.00115367,0.0005299274,0.0001005983,0.004331039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001739805,"about_ca_system_score_gemma":0.00000988712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000246573,"about_ca_topic_score_gemma":0.00001642504,"domain_scores_codex":[0.9983212,0.00001169865,0.0001730482,0.0005049394,0.0003396598,0.0006494359],"domain_scores_gemma":[0.9993974,0.000006740011,0.00003279635,0.0004426368,0.00002064858,0.00009978637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000642975,0.0001430241,0.02362848,0.000002565156,0.00000750125,0.00001458264,0.0008984908,0.04702073,0.9080753,0.0009880433,0.0003437242,0.01887111],"study_design_scores_gemma":[0.0003818665,0.0001776058,0.00280907,0.00000550372,0.00001394455,0.00003250839,0.0001884611,0.1793796,0.7279531,0.08566353,0.003008549,0.0003862864],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908829,0.00001414989,0.001407182,0.001107326,0.0001125501,0.0002755108,6.327176e-7,0.0002068753,0.005992898],"genre_scores_gemma":[0.9919032,0.000002265449,0.007007959,0.00008749131,0.00001305963,0.00004256309,0.000003591777,0.000008929709,0.0009308927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1801223,"threshold_uncertainty_score":0.9990671,"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."}}