{"id":"W4392736519","doi":"10.48550/arxiv.2403.05647","title":"Minor Issues Escalated to Critical Levels in Large Samples: A Permutation-Based Fix","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC; Alliance de recherche numérique du Canada; Western Canada Research Grid","keywords":"Minor (academic); Permutation (music); Mathematics; Statistics; Political science; Philosophy; Law","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08281766,0.001945011,0.002130718,0.002859896,0.003494394,0.006021139,0.005469749,0.004716332,0.006862924],"category_scores_gemma":[0.3776143,0.001260767,0.00314541,0.002414524,0.01217347,0.008608525,0.008422211,0.013066,0.002001947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003163443,"about_ca_system_score_gemma":0.005937392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002088044,"about_ca_topic_score_gemma":0.002165779,"domain_scores_codex":[0.9355856,0.04385235,0.002627714,0.008365396,0.008241062,0.001327875],"domain_scores_gemma":[0.7216764,0.2152266,0.008276427,0.03990564,0.01222921,0.002685689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001320386,0.000374468,0.01368361,0.0009502608,0.0007473735,0.001369315,0.002906118,0.03310984,0.007115513,0.5944293,0.0328796,0.3111141],"study_design_scores_gemma":[0.0002572218,0.0006123206,0.001319156,0.0004635709,0.0002376838,0.0008155574,0.0004006854,0.05706247,0.006453372,0.9029345,0.02929905,0.0001443408],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01249614,0.001287708,0.955373,0.01898811,0.00129422,0.0004929394,0.000266538,0.001431787,0.008369543],"genre_scores_gemma":[0.2331353,0.0008733632,0.7451997,0.0135005,0.001107296,0.001682052,0.0002558746,0.0009697084,0.003276246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08281766,"threshold_uncertainty_score":0.4379869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4136169841367431,"score_gpt":0.4140297358051339,"score_spread":0.0004127516683907761,"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."}}