{"id":"W2904534786","doi":"10.1016/j.procs.2018.11.056","title":"Developing a macro cognitive common model test bed for real world expertise","year":2018,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Macro; Test (biology); Cognition; Artificial intelligence; Programming language","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":[0.00315904,0.0008138353,0.0005079005,0.001117012,0.0005109885,0.001578258,0.002889099,0.001103768,0.005689807],"category_scores_gemma":[0.01627508,0.0004623646,0.000544074,0.0007534246,0.001205194,0.002551225,0.002446646,0.001523747,0.001839105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001308725,"about_ca_system_score_gemma":0.001404945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004747461,"about_ca_topic_score_gemma":0.004648007,"domain_scores_codex":[0.9975752,0.001009323,0.0001690159,0.0003673485,0.0006584033,0.0002206742],"domain_scores_gemma":[0.98759,0.005866474,0.0005745505,0.002636574,0.002438867,0.000893587],"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":[0.005928022,0.01918895,0.05458723,0.001949601,0.0004855607,0.001999772,0.007253449,0.2620048,0.07817455,0.09130212,0.04111841,0.4360075],"study_design_scores_gemma":[0.001547995,0.01051184,0.03394342,0.0003332552,0.0002215483,0.0009199062,0.002457076,0.7153383,0.1014367,0.05389582,0.07911623,0.0002778804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6140101,0.0001685743,0.3478644,0.0006734901,0.000194985,0.003734582,0.002127535,0.003939057,0.02728733],"genre_scores_gemma":[0.8016557,0.0001237542,0.1831347,0.0003569443,0.00002866044,0.004249063,0.003978414,0.000442947,0.006029841],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005689807,"threshold_uncertainty_score":0.01903427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04543527759340191,"score_gpt":0.3130839182194968,"score_spread":0.2676486406260948,"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."}}