{"id":"W4415421841","doi":"10.15439/2025f5708","title":"Out-Of-Distribution Is Not Magic: The Clash Between Rejection Rate and Model Success","year":2025,"lang":"en","type":"article","venue":"Annals of Computer Science and Information Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Government (linguistics); Perspective (graphical)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002283796,0.00009065946,0.0001728666,0.0002333656,0.0001872154,0.0005028475,0.000792873,0.00004440466,1.065898e-7],"category_scores_gemma":[0.00004812915,0.0000662919,0.0000217622,0.0007174221,0.0002904624,0.006053844,0.0004715472,0.00006547919,0.000001646439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001283922,"about_ca_system_score_gemma":0.0001434384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005765533,"about_ca_topic_score_gemma":3.020162e-7,"domain_scores_codex":[0.9987712,0.00004533132,0.0004826205,0.0001670728,0.000380281,0.000153511],"domain_scores_gemma":[0.9983108,0.0000828492,0.0003339367,0.0004241931,0.0008067761,0.0000414274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001960581,0.00003194856,0.002649759,0.0005001259,0.00004816711,2.279938e-7,0.008320001,0.001450314,0.0004325761,0.5029578,0.05493405,0.4286554],"study_design_scores_gemma":[0.0001082519,0.00008695488,0.009605438,0.0001520258,0.000004482126,0.000002090368,0.00004734075,0.9683601,0.01363727,0.001301045,0.006600266,0.00009474338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03620389,0.00002837912,0.9605789,0.001672168,0.0002640312,0.0002098895,0.00005149421,0.00005804438,0.0009331584],"genre_scores_gemma":[0.9953226,0.00007601538,0.003783594,0.0007685547,0.0000182745,0.000005912931,0.000008999909,9.694196e-7,0.00001503905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9669098,"threshold_uncertainty_score":0.484897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05066555381671407,"score_gpt":0.3211341940343513,"score_spread":0.2704686402176373,"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."}}