{"id":"W4396694063","doi":"10.1038/s41598-024-61284-z","title":"Measuring the prediction difficulty of individual cases in a dataset using machine learning","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Metric (unit); Machine learning; Artificial intelligence; Artificial neural network; Perspective (graphical); Data mining; Key (lock); Variety (cybernetics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01430788,0.001889945,0.001281707,0.009199333,0.0009549327,0.00379737,0.001858428,0.002203198,0.0009378041],"category_scores_gemma":[0.10524,0.0003423646,0.001534228,0.005567564,0.001368052,0.006643051,0.002311767,0.002766355,0.0004402498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001784453,"about_ca_system_score_gemma":0.001114688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002718512,"about_ca_topic_score_gemma":0.003808448,"domain_scores_codex":[0.985945,0.003655805,0.00333653,0.002544767,0.004042923,0.0004748798],"domain_scores_gemma":[0.8519703,0.1133764,0.01354494,0.01037608,0.008936049,0.001796412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008378931,0.0008868362,0.6098271,0.001491261,0.001116062,0.0007248225,0.001182142,0.149291,0.004793,0.006192662,0.01711588,0.2065414],"study_design_scores_gemma":[0.00009255034,0.0007495044,0.1598996,0.0003652431,0.0002637926,0.001061982,0.001732192,0.7811007,0.01070568,0.03524182,0.008507719,0.0002791162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8147276,0.002155459,0.1572821,0.001999695,0.0004280276,0.0008740854,0.01260787,0.002456256,0.007468955],"genre_scores_gemma":[0.8952274,0.0004062158,0.08799107,0.0001977781,0.0001395246,0.0004628868,0.01485247,0.0001282833,0.0005944236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01430788,"threshold_uncertainty_score":0.07566816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06299436719122843,"score_gpt":0.2899077230452051,"score_spread":0.2269133558539767,"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."}}