{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006819319,0.001726871,0.002042486,0.002609155,0.001252458,0.002193412,0.003503863,0.001770274,0.005335471],"category_scores_gemma":[0.0171895,0.001568312,0.002203369,0.001936046,0.003173938,0.00344099,0.003798997,0.003931609,0.00219917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0017863,"about_ca_system_score_gemma":0.001688968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002850892,"about_ca_topic_score_gemma":0.004035647,"domain_scores_codex":[0.9949632,0.002555559,0.0003105782,0.0008790651,0.0009732479,0.0003183232],"domain_scores_gemma":[0.9893711,0.00660522,0.0005932512,0.001854114,0.001145042,0.0004313386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002189557,0.0002238061,0.002149461,0.0002706706,0.00008495369,0.0002148483,0.0003691341,0.5050333,0.004042917,0.07503194,0.005236809,0.4071232],"study_design_scores_gemma":[0.0000147564,0.00007403098,0.0001610225,0.00003918045,0.00001023661,0.00006268869,0.00006081893,0.9524181,0.002621336,0.04278784,0.001733105,0.00001695031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002700554,0.00005710148,0.9958829,0.00006101053,0.00001111962,0.00008773677,0.00004262314,0.0004867794,0.0006702991],"genre_scores_gemma":[0.08035807,0.0001100818,0.9169116,0.0001836163,0.00003694306,0.000430598,0.0004847448,0.000369992,0.001114349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006819319,"threshold_uncertainty_score":0.03606445,"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."}}