{"id":"W2994640520","doi":"10.1109/rew.2019.00041","title":"Data Preprocessing for Goal-Oriented Process Discovery","year":2019,"lang":"en","type":"article","venue":"","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Process mining; Computer science; Event (particle physics); Process (computing); Business process discovery; TRACE (psycholinguistics); Preprocessor; Data mining; Table (database); Row; Scheme (mathematics); Data science; Work in process; Artificial intelligence; Business process; Business process management; Database; Engineering; Business process modeling; Mathematics","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":[0.0003938168,0.0002077521,0.0002780785,0.0001949284,0.0001904434,0.0007542207,0.0007171655,0.00006723651,0.0001445218],"category_scores_gemma":[0.0001829088,0.0001668237,0.00007184071,0.0007523433,0.00002804085,0.006631591,0.0003298079,0.00008449711,0.0002138947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001039427,"about_ca_system_score_gemma":0.00005295096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001269438,"about_ca_topic_score_gemma":0.0000405988,"domain_scores_codex":[0.9982936,0.000002152523,0.0003158752,0.0007641383,0.0002828377,0.0003413547],"domain_scores_gemma":[0.9985088,0.000032033,0.0002234799,0.0007971353,0.0004283306,0.00001026249],"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":[0.001998752,0.003105243,0.5243822,0.04411157,0.001418388,0.00001598193,0.0005273079,0.06300075,0.009189809,0.1376788,0.04506342,0.1695078],"study_design_scores_gemma":[0.001032692,0.000006063642,0.0005083827,0.0001985387,0.0002361999,9.125497e-7,0.0007059362,0.9456477,0.0001594136,0.006018477,0.04493658,0.0005490577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6064382,0.0002608441,0.3632283,0.001855676,0.0006826287,0.0007902763,0.00004601439,0.0006639714,0.02603403],"genre_scores_gemma":[0.9918292,0.000003585342,0.0008524987,0.001304886,0.0008352461,0.00003859235,0.0006290284,0.00004507679,0.004461859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.882647,"threshold_uncertainty_score":0.7272968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03084859346953151,"score_gpt":0.2813104333348309,"score_spread":0.2504618398652994,"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."}}