{"id":"W4402035625","doi":"10.32920/26882485.v1","title":"Graph and Semantic Analysis Approach for Template Recognition in Large Scale Log Data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Graph; Scale (ratio); Natural language processing; Information retrieval; Artificial intelligence; Data mining; Theoretical computer science; Geography; Cartography","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":[0.000770784,0.0001559528,0.0002820509,0.0004808933,0.00006554925,0.0004739429,0.001222726,0.0001235871,0.000005931309],"category_scores_gemma":[0.00001399541,0.0001406412,0.00007164071,0.0009325263,0.00002366369,0.0001837805,0.004478449,0.0002602144,0.00001046196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000119268,"about_ca_system_score_gemma":0.00004138993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002050611,"about_ca_topic_score_gemma":0.0002755126,"domain_scores_codex":[0.9981494,0.00002438929,0.0002766074,0.001227345,0.0001173112,0.0002049278],"domain_scores_gemma":[0.998185,0.00006068391,0.00007333336,0.001587679,0.00003880751,0.00005446176],"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":[0.000014792,0.001545438,0.003997877,0.00349068,0.002990874,0.0000225895,0.003029275,0.001512684,0.0000933117,0.01970233,0.03806051,0.9255396],"study_design_scores_gemma":[0.0001044203,0.000006533692,0.000942449,0.00003672978,0.0002543934,0.000002814757,0.00004932239,0.976055,0.000009322671,0.02197489,0.000372384,0.0001917037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003532229,0.0002157336,0.9919693,0.000419397,0.00008304824,0.0004299855,0.002429284,0.0001284139,0.0007925575],"genre_scores_gemma":[0.04793612,0.0001257007,0.941521,0.00007858591,0.00005198982,0.0002911832,0.009757278,0.00001254105,0.0002255765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9745424,"threshold_uncertainty_score":0.5735182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07290353216277942,"score_gpt":0.3152091593200427,"score_spread":0.2423056271572633,"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."}}