{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007031186,0.00007620853,0.00005679782,0.00001410964,0.0004803314,0.0001339505,0.000439238,0.00001449753,0.000006122025],"category_scores_gemma":[0.000001020042,0.00004537317,0.00002223093,0.0001783817,0.00006502716,0.0002171401,0.0001082958,0.00005477205,0.0000501798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000276785,"about_ca_system_score_gemma":0.00002770976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002004918,"about_ca_topic_score_gemma":0.00007021424,"domain_scores_codex":[0.9993404,0.000006585715,0.0001157497,0.0001860955,0.0001723413,0.0001788444],"domain_scores_gemma":[0.9995183,0.00007964145,0.00003204136,0.0003093674,0.00002585756,0.00003479234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002037654,0.0001995072,0.01046604,9.334095e-7,0.000006031381,0.000003374218,0.00009062644,0.001156327,0.0008175786,0.9820373,0.004403322,0.0008169439],"study_design_scores_gemma":[0.0008542414,0.0002951491,0.1093604,0.00001134199,0.000005646053,0.00007542015,0.0003455326,0.8279507,0.01749101,0.01222256,0.03091731,0.0004707224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1866438,0.0002320931,0.7651038,0.001959699,0.00009093247,0.0002622298,0.000001630814,0.0003777597,0.04532803],"genre_scores_gemma":[0.9658369,9.225277e-7,0.03264519,0.00005292413,0.00006321594,0.00004335801,0.000002765978,0.000003965808,0.001350754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9698147,"threshold_uncertainty_score":0.3694369,"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."}}