{"id":"W4309617049","doi":"10.1145/3571281","title":"Efficiently Cleaning Structured Event Logs: A Graph Repair Approach","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Beijing National Research Center For Information Science And Technology; National Natural Science Foundation of China","keywords":"Computer science; Workflow; Event (particle physics); Pruning; Data mining; Graph; Profiling (computer programming); Information retrieval; Theoretical computer science; Database; Programming language","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.006514168,0.0002537365,0.0003957864,0.0007524402,0.001307311,0.0002765772,0.002230303,0.00004586341,0.0008134438],"category_scores_gemma":[0.0004147896,0.0002175674,0.0003174985,0.001873257,0.00008820976,0.0004223358,0.0002148386,0.0004936128,0.0001945438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001570881,"about_ca_system_score_gemma":0.00006976764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005676133,"about_ca_topic_score_gemma":0.00006747658,"domain_scores_codex":[0.9933639,0.001330328,0.001024144,0.001126115,0.002727783,0.0004277746],"domain_scores_gemma":[0.9949101,0.0006978599,0.0003144542,0.003807829,0.00009119069,0.0001786087],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000536886,0.002511915,0.0001251514,0.0002631,0.0005690636,0.000121829,0.003413769,0.7770706,0.000477668,0.02937876,0.1383023,0.04722892],"study_design_scores_gemma":[0.001962923,0.0005214039,0.0003274187,0.00006897005,0.0001956384,0.0001732986,0.06328368,0.05944963,0.0001504641,0.002055759,0.8708953,0.0009154814],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009426407,0.000256942,0.9766492,0.0004024369,0.003217915,0.001273625,0.006329013,0.000424474,0.002019937],"genre_scores_gemma":[0.9913121,0.00001361327,0.004396016,0.0004283733,0.00006508816,0.0004227625,0.0005775493,0.00002897143,0.002755507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9818857,"threshold_uncertainty_score":0.9999928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1167959570941646,"score_gpt":0.3589782289255208,"score_spread":0.2421822718313563,"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."}}