{"id":"W4399369033","doi":"10.21428/d82e957c.885a78c0","title":"Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows","year":2024,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature (linguistics); Estimation; Pattern recognition (psychology); Density estimation; Distribution (mathematics); Mathematics; Computer science; Artificial intelligence; Statistics; Engineering; Estimator; Mathematical analysis","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":[0.0001642376,0.00007020448,0.0000707334,0.00005602924,0.0001300565,0.00008866932,0.0001400888,0.0000743355,0.000002925555],"category_scores_gemma":[0.00001348823,0.00006436996,0.00007805008,0.0002929609,0.00001076845,0.0003565195,0.00004085055,0.00007084183,0.00001441387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005703907,"about_ca_system_score_gemma":0.00001919745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002050223,"about_ca_topic_score_gemma":0.00003129241,"domain_scores_codex":[0.9994732,0.00001006131,0.0001185185,0.000210914,0.00008815269,0.00009919049],"domain_scores_gemma":[0.9995933,0.00004045654,0.00004011546,0.0002007959,0.00009716454,0.00002813036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006117343,0.00002745013,0.00001166409,0.00009961544,0.00001702979,6.029628e-7,0.0001186437,0.0002507617,0.07877347,0.1052667,0.002822187,0.8126058],"study_design_scores_gemma":[0.0000289772,0.00004476462,0.0001213223,0.00001032561,0.000007052619,0.000007117324,0.000003292939,0.7269124,0.2520562,0.006454211,0.01429185,0.00006246269],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002942272,0.00004212859,0.9948863,0.0006566637,0.0003140203,0.0002785409,0.000007502566,0.0007211926,0.0001513369],"genre_scores_gemma":[0.824541,0.000003923919,0.1750932,0.00002383622,0.00004538801,0.00007562447,0.00001903262,0.000004368898,0.0001936642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8215987,"threshold_uncertainty_score":0.2624931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01266013060957819,"score_gpt":0.2694363708563547,"score_spread":0.2567762402467765,"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."}}