{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009726874,0.0002675288,0.0002568067,0.0003655867,0.001208161,0.0006730599,0.002060801,0.00005515796,0.000001790756],"category_scores_gemma":[0.0001866945,0.0002523588,0.00005878539,0.001683247,0.0005257808,0.001265909,0.0007957084,0.0001621876,0.0000362622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001561512,"about_ca_system_score_gemma":0.001048441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003625742,"about_ca_topic_score_gemma":0.00006227677,"domain_scores_codex":[0.997188,0.00002453094,0.0003602501,0.001037543,0.0005201031,0.0008695326],"domain_scores_gemma":[0.9978522,0.0005223777,0.0001771758,0.0004465733,0.000748336,0.000253307],"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":[0.0001543658,0.0004597418,0.04679916,0.0003717403,0.00005550477,0.00005399463,0.06065755,0.002628231,0.005722972,0.1195447,0.008793595,0.7547584],"study_design_scores_gemma":[0.000405369,0.0002408051,0.0008480187,0.0002451055,0.000005239106,0.00001652892,0.00001117822,0.9789968,0.01188075,0.006800531,0.0001473042,0.0004023725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02935309,0.00003775582,0.9674685,0.0008911417,0.0005754663,0.0004408901,0.000007976881,0.0004284424,0.0007967586],"genre_scores_gemma":[0.5440286,0.000002728103,0.454463,0.00112198,0.0002396093,0.00006478643,0.000002711735,0.00001053431,0.0000660294],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9763685,"threshold_uncertainty_score":0.9999928,"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."}}