{"id":"W13093665","doi":"10.1042/bj0550204","title":"Toward better scoring metrics for pseudo-independent models: Research Articles","year":2004,"lang":"en","type":"article","venue":"International Journal of Intelligent Systems","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of Guelph","funders":"","keywords":"Computer science; Heuristic; Dimension (graph theory); Artificial intelligence; Hypercube; Domain (mathematical analysis); Perspective (graphical); Machine learning; Theoretical computer science; Algorithm; Mathematics; Combinatorics","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":[0.002627813,0.000134444,0.0002272731,0.0008051769,0.00008304387,0.0006525666,0.002016794,0.00008185906,0.000003513006],"category_scores_gemma":[0.000261261,0.0001119116,0.0001828443,0.0003428448,0.00004025988,0.000818276,0.0001974975,0.0003771927,0.00003120036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004788909,"about_ca_system_score_gemma":0.000256696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001283121,"about_ca_topic_score_gemma":0.000003654577,"domain_scores_codex":[0.9968005,0.00009810087,0.0008465746,0.0002537417,0.001673946,0.000327073],"domain_scores_gemma":[0.9960805,0.0002733268,0.0003303455,0.0002370439,0.002909764,0.0001690272],"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":[0.0001103298,0.0003719674,0.000294722,0.00006459553,0.0004083643,0.0002325595,0.003489319,0.3044491,0.002961986,0.6347489,0.0009136976,0.05195448],"study_design_scores_gemma":[0.001057154,0.000549073,0.00003942816,0.0009406874,0.00001882461,0.001020727,0.001022224,0.6582208,0.0338385,0.3013349,0.001616473,0.0003412667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03939503,0.0007376033,0.9537928,0.002341381,0.003284126,0.0001634323,0.00000389637,0.00002656046,0.0002552433],"genre_scores_gemma":[0.9639361,0.0001559857,0.03499061,0.0001279352,0.0006936576,0.00001469085,7.712219e-7,0.00001270558,0.00006755998],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9245411,"threshold_uncertainty_score":0.6292714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2615360544351394,"score_gpt":0.38425387352951,"score_spread":0.1227178190943705,"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."}}