{"id":"W4401114488","doi":"10.1109/ecti-con60892.2024.10595036","title":"A Graph-based Data Mining Approach for Template Recognition using Large Log Datasets in Software Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Data mining; Software; Graph; Pattern recognition (psychology); Artificial intelligence; Theoretical computer science; Operating system","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":[0.0007871435,0.0001185635,0.0001402772,0.0002121605,0.0001239293,0.0005711666,0.001015469,0.0000543499,0.000003081171],"category_scores_gemma":[0.00004238538,0.0001083423,0.00002475314,0.0006820645,0.00001620626,0.0009815975,0.0003546565,0.0000842375,0.0000102247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002593042,"about_ca_system_score_gemma":0.00009802952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000175117,"about_ca_topic_score_gemma":0.00002442845,"domain_scores_codex":[0.998556,0.00003232523,0.0002653302,0.0007343965,0.0001369588,0.000275021],"domain_scores_gemma":[0.998624,0.0001913387,0.00004529416,0.001059495,0.00002503616,0.00005485038],"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":[0.00002330834,0.001075119,0.0008375155,0.002615726,0.0001736465,0.00011377,0.000805838,0.005248375,0.0005900469,0.01150106,0.1505495,0.8264661],"study_design_scores_gemma":[0.0002132716,0.00001481515,0.00001972236,0.0001447849,0.00001267219,0.00001826039,0.00007275364,0.9914157,0.00002625542,0.0001599177,0.007742927,0.0001588518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008904519,0.0002200342,0.9879133,0.00006127267,0.0001852561,0.0003987719,0.01001568,0.0002711488,0.00004410155],"genre_scores_gemma":[0.01477716,0.000003220363,0.9646825,0.0000887582,0.00006223482,0.0001346662,0.02022031,0.00001499909,0.00001616694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9861674,"threshold_uncertainty_score":0.5507773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1491570247757092,"score_gpt":0.3378350482161478,"score_spread":0.1886780234404386,"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."}}