{"id":"W2169464732","doi":"10.1109/cec.2006.1688330","title":"The Y-Test: Fairly Comparing Experimental Setups with Unequal Effort","year":2006,"lang":"en","type":"article","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Statistic; Set (abstract data type); Test statistic; Computation; Work (physics); Test (biology); Statistical hypothesis testing; Point (geometry); Algorithm; Mathematics; Statistics; Engineering","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":[0.159871,0.002112947,0.00350762,0.004140526,0.001983411,0.004399749,0.00472463,0.004848738,0.003468841],"category_scores_gemma":[0.4553856,0.001016996,0.002933879,0.003917132,0.009752255,0.0100831,0.006869121,0.004747083,0.0008360735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002721274,"about_ca_system_score_gemma":0.002041115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001021171,"about_ca_topic_score_gemma":0.000646878,"domain_scores_codex":[0.7998534,0.1565881,0.00748823,0.01705157,0.01740887,0.001609763],"domain_scores_gemma":[0.4665758,0.4251068,0.02275502,0.07594806,0.007718169,0.001896055],"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":[0.01926144,0.001492549,0.08066658,0.003312142,0.01570717,0.0006444102,0.00291926,0.1105881,0.02061515,0.2061242,0.0167707,0.5218984],"study_design_scores_gemma":[0.002887503,0.009450549,0.05307102,0.0006965717,0.001838976,0.000841159,0.00153952,0.2944124,0.03371134,0.5821404,0.01864046,0.0007700194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1021409,0.000863561,0.883175,0.0019226,0.0008493187,0.001516774,0.0011575,0.001628918,0.006745455],"genre_scores_gemma":[0.6434669,0.0004097032,0.3417214,0.00207361,0.0005330241,0.007562038,0.001412883,0.001317917,0.001502538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.159871,"threshold_uncertainty_score":0.8454886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009359679556369516,"score_gpt":0.2277095103723361,"score_spread":0.2183498308159666,"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."}}