{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0158683,0.002652287,0.002552324,0.00501328,0.001163968,0.004427186,0.003570657,0.004230806,0.003687751],"category_scores_gemma":[0.09515761,0.001446002,0.001865959,0.005834988,0.003193734,0.01476274,0.004480783,0.006176539,0.001331531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003256278,"about_ca_system_score_gemma":0.001757877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003579393,"about_ca_topic_score_gemma":0.002411092,"domain_scores_codex":[0.9869141,0.008579929,0.0005581887,0.001618605,0.002005938,0.0003232351],"domain_scores_gemma":[0.9202051,0.0598479,0.003784705,0.007001295,0.007662395,0.00149858],"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":[0.0001569101,0.0003699482,0.003399903,0.0006269898,0.000247347,0.00007512385,0.0004062821,0.2746662,0.001192312,0.3946344,0.01188202,0.3123426],"study_design_scores_gemma":[0.00001733643,0.00008492269,0.0004563665,0.00009780612,0.00002400939,0.00007598379,0.00005226514,0.656727,0.0003932523,0.3373029,0.0047251,0.00004293547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.013728,0.00769812,0.9728386,0.002266626,0.0001485222,0.0000698201,0.0001200074,0.0002664775,0.002863839],"genre_scores_gemma":[0.2790957,0.01046751,0.7014927,0.0008662728,0.001358647,0.0003565434,0.001009687,0.00078766,0.004565152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0158683,"threshold_uncertainty_score":0.0839206,"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."}}