{"id":"W4417090763","doi":"10.1109/icmla66185.2025.00041","title":"Sliced-Wasserstein Distance-based Data Selection","year":2025,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Benchmark (surveying); Anomaly detection; Selection (genetic algorithm); Scalability; Data point; Model selection; Feature selection; Euclidean distance; Data modeling","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003765276,0.001176521,0.001947143,0.001994942,0.0008677723,0.001669006,0.003121253,0.001487616,0.001909768],"category_scores_gemma":[0.01657521,0.0006146304,0.001683255,0.002266559,0.001043946,0.00277922,0.002492173,0.002500807,0.00118919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009789668,"about_ca_system_score_gemma":0.001979268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004467903,"about_ca_topic_score_gemma":0.006050942,"domain_scores_codex":[0.9959508,0.001152579,0.0003959497,0.001116271,0.00113976,0.000244584],"domain_scores_gemma":[0.9925038,0.002981325,0.0005257554,0.001714334,0.001998747,0.000276093],"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":[0.0004166918,0.0003584319,0.011195,0.0002658158,0.0002775784,0.0002634966,0.0003484719,0.3610741,0.01592825,0.02404615,0.01079259,0.5750334],"study_design_scores_gemma":[0.00001453031,0.00006210829,0.0005268095,0.00001127309,0.000008297595,0.00007436069,0.00002161394,0.984861,0.003759115,0.008871516,0.001773462,0.00001581874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009135908,0.0001002671,0.9891136,0.0001200876,0.00004097101,0.00005410175,0.0002264178,0.0009416128,0.0002670927],"genre_scores_gemma":[0.186762,0.0001356931,0.8074469,0.0002692092,0.0001074524,0.0003074281,0.003146923,0.0003495084,0.001474748],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004467903,"threshold_uncertainty_score":0.0199129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02196130828809907,"score_gpt":0.2936971163154363,"score_spread":0.2717358080273372,"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."}}