{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002210971,0.0001574356,0.000241142,0.0001084349,0.0002842285,0.0003890243,0.0001512344,0.00005623965,0.002401465],"category_scores_gemma":[0.0004733738,0.0001405544,0.0001245144,0.0009005046,0.00001588449,0.0008372331,0.0001669822,0.000128706,0.0001872314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001437647,"about_ca_system_score_gemma":0.00003218098,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006620883,"about_ca_topic_score_gemma":0.0012325,"domain_scores_codex":[0.9987038,0.00001270568,0.0002763354,0.0004589091,0.0002526868,0.0002955421],"domain_scores_gemma":[0.9990481,0.0001234964,0.0001527336,0.0002257327,0.0004383797,0.0000115403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001511497,0.0022399,0.7886587,0.0007441499,0.001690848,0.0003023758,0.001999598,0.0184624,0.01118091,0.05454883,0.04251878,0.07750238],"study_design_scores_gemma":[0.002703484,0.000008001493,0.02193357,0.0002569354,0.000973664,0.000004910701,0.01793959,0.7439497,0.009853307,0.1113189,0.08934345,0.001714468],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.684194,0.0007796782,0.2953334,0.004138209,0.0003494,0.00009528552,0.0000201275,0.0004385736,0.01465139],"genre_scores_gemma":[0.9935742,0.00002090261,0.00216141,0.001964509,0.000920093,0.00001037905,0.0002263653,0.00002262251,0.00109954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7667251,"threshold_uncertainty_score":0.9999941,"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."}}