{"id":"W6958618483","doi":"10.6084/m9.figshare.29085063.v1","title":"Additional file 1 of Comparison of methods for tuning machine learning model hyper-parameters: with application to predicting high-need high-cost health care users","year":2025,"lang":"en","type":"dataset","venue":"Figshare","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Health care; Feature (linguistics); Training set; Key (lock); Support vector machine","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00280141,0.001925788,0.001226047,0.00243354,0.0007403617,0.001931839,0.002594461,0.002340627,0.569961],"category_scores_gemma":[0.02796281,0.0006090266,0.00164787,0.003080264,0.0003925816,0.001213406,0.001123272,0.001538664,0.1601513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001579638,"about_ca_system_score_gemma":0.001890031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01342499,"about_ca_topic_score_gemma":0.03581142,"domain_scores_codex":[0.9989342,0.0003012239,0.0001593557,0.000313512,0.0001677699,0.0001238795],"domain_scores_gemma":[0.9829334,0.01301569,0.0005997824,0.001216071,0.001886832,0.0003481316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001689272,0.00008438351,0.001459757,0.0008784054,0.00005744459,0.00001782441,0.00001358828,0.000752182,0.00003675914,0.0003804489,0.9930906,0.003059491],"study_design_scores_gemma":[0.006917154,0.0003884443,0.02143297,0.002111797,0.0003478487,0.0003249219,0.0003091241,0.008773046,0.0009136972,0.01401251,0.9443051,0.0001633733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001796298,0.00003291944,0.0001378582,0.00005868379,0.00002229949,0.00003293451,0.9989422,0.0001984255,0.000395024],"genre_scores_gemma":[0.002619289,0.0000582444,0.001677196,0.0002064085,0.0000390813,0.0005351466,0.9927042,0.0002750491,0.001885371],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.569961,"threshold_uncertainty_score":0.6133985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07850799966010773,"score_gpt":0.3121971433994649,"score_spread":0.2336891437393571,"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."}}