{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003060673,0.00009165923,0.0001023189,0.0002643075,0.0002748712,0.0007708353,0.0004014082,0.00003345502,0.000009821157],"category_scores_gemma":[0.0004640774,0.00006306133,0.00003637269,0.001033309,0.0001012036,0.00056477,0.0002853625,0.000273042,0.000005037263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003897144,"about_ca_system_score_gemma":0.0001232019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003231075,"about_ca_topic_score_gemma":0.00009402892,"domain_scores_codex":[0.9980357,0.0001633698,0.0004178905,0.0005947784,0.0006129848,0.0001752894],"domain_scores_gemma":[0.9988475,0.0001168018,0.0001742849,0.0007786322,0.00004401499,0.00003870059],"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":[0.00002821591,0.0006598148,0.3728998,0.0009078313,0.0002042391,0.004865908,0.02087123,0.09621721,0.2252549,0.008159289,0.03034369,0.2395879],"study_design_scores_gemma":[0.00008034237,0.00003276628,0.02355635,0.0002218447,0.00002675903,0.001400311,0.0001248969,0.9042864,0.00377282,0.000700083,0.06563374,0.0001636285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9548698,0.001174263,0.03745778,0.0004048872,0.005192472,0.0002952931,0.0001892808,0.0002670906,0.0001491567],"genre_scores_gemma":[0.9975321,0.00000418465,0.001328177,0.000006085148,0.00003648869,0.000006021285,0.000976934,0.000005793861,0.0001042435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8080692,"threshold_uncertainty_score":0.7433183,"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."}}