{"id":"W3210025856","doi":"10.1109/icpm53251.2021.9576679","title":"Selecting Representative Sample Traces from Large Event Logs","year":2021,"lang":"en","type":"article","venue":"","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Event (particle physics); Computer science; Sampling (signal processing); Data mining; Metric (unit); Process mining; Event data; Sample (material); Generality; Process (computing); Quality (philosophy); Work in process; Artificial intelligence; Engineering; Detector; Business process management; Business process","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":[0.003618753,0.0008722179,0.0008152658,0.002120071,0.0005156135,0.001363186,0.001107018,0.0008352888,0.0006964988],"category_scores_gemma":[0.02783982,0.0003133475,0.0006100418,0.001730235,0.0005001506,0.001760779,0.001213254,0.0008862372,0.0004122285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004095485,"about_ca_system_score_gemma":0.001096611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002077706,"about_ca_topic_score_gemma":0.003240969,"domain_scores_codex":[0.9980304,0.0007688089,0.0001630876,0.0003249514,0.0005878794,0.0001249495],"domain_scores_gemma":[0.9835048,0.01064463,0.001019241,0.00245557,0.001977582,0.0003982024],"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":[0.001476531,0.001610473,0.1745758,0.0009901222,0.000399836,0.001427923,0.002215174,0.2408606,0.04535079,0.0186028,0.008289531,0.5042004],"study_design_scores_gemma":[0.00008919739,0.0003284148,0.01752765,0.0000693992,0.0000742351,0.0005422741,0.001127769,0.9346917,0.01424974,0.02607907,0.005183108,0.00003740016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2404,0.0002151888,0.7548454,0.0003395882,0.00004002313,0.000404132,0.0007932399,0.002069348,0.000893134],"genre_scores_gemma":[0.7541739,0.0002136641,0.2409384,0.00009492208,0.0000585929,0.0004541239,0.003270645,0.0001789965,0.0006166915],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003618753,"threshold_uncertainty_score":0.01913798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02466001536197406,"score_gpt":0.2699342664647372,"score_spread":0.2452742511027632,"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."}}