{"id":"W4396943949","doi":"10.48550/arxiv.2406.06968","title":"Beyond the Norms: Detecting Prediction Errors in Regression Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif","keywords":"Computer science; Regression; Regression analysis; Artificial intelligence; Statistics; Machine learning; Mathematics","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":[0.01552715,0.001741135,0.002198681,0.002820627,0.0009355047,0.003118359,0.003092366,0.002168678,0.0007742406],"category_scores_gemma":[0.1099208,0.0008601016,0.001165917,0.001912124,0.003996051,0.005776885,0.006014917,0.00507197,0.0004149114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001141586,"about_ca_system_score_gemma":0.001353311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002684285,"about_ca_topic_score_gemma":0.001713074,"domain_scores_codex":[0.983098,0.007633924,0.0008424232,0.002953775,0.004949768,0.0005221556],"domain_scores_gemma":[0.9033233,0.07122546,0.01026743,0.008818399,0.005057407,0.001308045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004078721,0.0001534684,0.03873639,0.0002866394,0.0003211999,0.0004125915,0.0008559477,0.7254106,0.003813378,0.08207043,0.002997492,0.144534],"study_design_scores_gemma":[0.000006383311,0.00004204805,0.0007492178,0.00002571599,0.00001046959,0.00007877186,0.00003973163,0.9159186,0.001420737,0.08106185,0.0006268097,0.0000197195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0303332,0.00041376,0.9675619,0.0004401188,0.00003622036,0.00002122579,0.00009696438,0.0006200198,0.0004765963],"genre_scores_gemma":[0.7506847,0.0004709012,0.2456994,0.0003317537,0.00032927,0.0001010584,0.0007087145,0.0005667929,0.001107446],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01552715,"threshold_uncertainty_score":0.08211637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05429113154828653,"score_gpt":0.2013957076051875,"score_spread":0.147104576056901,"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."}}