{"id":"W2031783991","doi":"10.2478/v10229-011-0010-8","title":"Testing for Equivalence: A Methodology for Computational Cognitive Modelling","year":2010,"lang":"en","type":"article","venue":"Journal of Artificial General Intelligence","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of Waterloo","funders":"","keywords":"Equivalence (formal languages); Computer science; Similarity (geometry); Range (aeronautics); Set (abstract data type); Econometrics; Artificial intelligence; Algorithm; Machine learning; Mathematics; 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":[0.002054268,0.0001590183,0.0002997893,0.0001716813,0.0002236936,0.0001706358,0.00070238,0.0001169006,0.000006377285],"category_scores_gemma":[0.001384536,0.0001436607,0.0001908122,0.0002709405,0.0001058368,0.0003938694,0.00006722576,0.0003587944,0.000004278708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001829631,"about_ca_system_score_gemma":0.0003403353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001103947,"about_ca_topic_score_gemma":0.000005097882,"domain_scores_codex":[0.9982151,0.0000826669,0.0008037445,0.0002922478,0.0002601332,0.0003461517],"domain_scores_gemma":[0.9945962,0.002506481,0.0005093144,0.0001358223,0.002105548,0.0001466181],"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":[0.0001560257,0.00008704786,0.00002603733,0.00002376724,0.00003554629,0.000004833541,0.0005405986,0.4861206,0.04854133,0.209724,0.0000762981,0.2546639],"study_design_scores_gemma":[0.00005995135,0.0003710126,0.000008511133,0.00003062235,0.00001663238,0.00006703304,0.00004111999,0.653714,0.02516402,0.3203656,0.00004598282,0.0001155101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06899821,0.00006038103,0.9289634,0.0003754482,0.001320205,0.000207791,0.00001035587,0.00002710775,0.00003705222],"genre_scores_gemma":[0.4278918,0.000002030324,0.571396,0.0001618815,0.0005106646,0.00001112333,0.000001177004,0.000007569084,0.00001769921],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3588936,"threshold_uncertainty_score":0.5858315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3112390030106687,"score_gpt":0.4095147432123687,"score_spread":0.09827574020169999,"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."}}