{"id":"W4404688907","doi":"10.1109/icds62089.2024.10756470","title":"Delta-Convex Skins for Constructing Training and Testing sets in Supervised Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Training (meteorology); Artificial intelligence; Machine learning; Delta; Regular polygon; Pattern recognition (psychology); Mathematics; Engineering","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":[0.0003439385,0.00006163987,0.00007863694,0.0001203677,0.00009155286,0.0001128657,0.0001350647,0.00004294914,0.000005413457],"category_scores_gemma":[0.0001861176,0.00005791606,0.00001320869,0.000276728,0.00003327541,0.0002278945,0.00006641458,0.0001659354,0.000001623025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001941249,"about_ca_system_score_gemma":0.0001303819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009907852,"about_ca_topic_score_gemma":0.000008847385,"domain_scores_codex":[0.9994042,0.00001624184,0.0001249451,0.0002405517,0.00005088333,0.0001631863],"domain_scores_gemma":[0.9991477,0.0007228575,0.00001562095,0.00006545705,0.00002473426,0.00002362395],"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":[4.088916e-7,0.00001095394,0.03691031,0.00005672737,0.000008583755,0.000009168835,0.00282948,0.00006648114,0.001098513,0.4225087,0.0000304792,0.5364702],"study_design_scores_gemma":[0.0004162928,0.0001198347,0.008938654,0.0002925883,0.000007209314,0.0001930928,0.0091856,0.9088653,0.00261192,0.06708349,0.001973881,0.0003120835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7787154,0.0002053223,0.2139409,0.0031135,0.0002545555,0.0001357332,6.768768e-7,0.000409615,0.003224212],"genre_scores_gemma":[0.72891,0.000001677127,0.2709306,0.00006525293,0.00001609365,0.00001859041,9.992743e-7,0.000003268764,0.0000535159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9087989,"threshold_uncertainty_score":0.2361748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06665170022761008,"score_gpt":0.3289783286938243,"score_spread":0.2623266284662142,"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."}}