{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06170998,0.002896926,0.003971591,0.01004508,0.003322584,0.007907378,0.008364159,0.004433035,0.008918461],"category_scores_gemma":[0.2463413,0.001726647,0.009325691,0.00633951,0.01543022,0.01185913,0.01391105,0.01190756,0.001099937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003589676,"about_ca_system_score_gemma":0.005018861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003218923,"about_ca_topic_score_gemma":0.002282457,"domain_scores_codex":[0.9249526,0.05095048,0.004632242,0.006601303,0.01175831,0.001105053],"domain_scores_gemma":[0.7252909,0.2356763,0.006436987,0.02424566,0.006653523,0.001696613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002135999,0.0002423213,0.0027217,0.000510603,0.0006206904,0.0003183009,0.001996216,0.03379147,0.0009569353,0.8763936,0.002527204,0.07970733],"study_design_scores_gemma":[0.00005583192,0.00008186842,0.000256343,0.00008360942,0.0000572793,0.00009264026,0.0001524773,0.103927,0.0004077906,0.8919322,0.002913638,0.0000393078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002002858,0.00007162327,0.9958124,0.0003757573,0.00003265377,0.0001773572,0.00009714111,0.0002204383,0.001209743],"genre_scores_gemma":[0.06688984,0.0001020111,0.9300292,0.0002852788,0.0001125743,0.001685497,0.0003322504,0.0001559985,0.000407306],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06170998,"threshold_uncertainty_score":0.3263575,"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."}}