{"id":"W2137723287","doi":"10.1145/1735970.1736038","title":"SherLog","year":2010,"lang":"en","type":"article","venue":"ACM SIGARCH Computer Architecture News","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":217,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Unavailability; Task (project management); Software bug; Code (set theory); Software; Server; Source code; Operating system; Software engineering; Programming language; Reliability engineering","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":[0.0005015893,0.0002998066,0.0003261306,0.000200592,0.0002387677,0.000247517,0.003931973,0.0001890716,0.00004164097],"category_scores_gemma":[0.0001653278,0.0002351303,0.0001947475,0.0005134995,0.0001452185,0.0003293391,0.001638131,0.001059426,0.0002701489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002214705,"about_ca_system_score_gemma":0.0001397664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000909599,"about_ca_topic_score_gemma":0.0001580266,"domain_scores_codex":[0.9975002,0.0001253207,0.000392759,0.0008309656,0.0005136175,0.0006371315],"domain_scores_gemma":[0.9958341,0.0005077423,0.00009609397,0.003162466,0.0001198638,0.0002797332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009440121,0.00008153354,0.009858941,0.00004482418,0.00002714284,0.00002646009,0.001615781,0.0003418675,0.002933007,0.001600588,0.004504762,0.9789556],"study_design_scores_gemma":[0.003083474,0.001263125,0.1810016,0.0001282671,0.00003398449,0.001436008,0.00002073762,0.04735393,0.01070989,0.1312951,0.6210061,0.002667767],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2180847,0.00003536532,0.7708983,0.005121856,0.003537521,0.0003820767,0.000001760413,0.000792434,0.001145984],"genre_scores_gemma":[0.575192,0.000004504297,0.4215974,0.001783335,0.001275554,0.00003453909,0.000003983358,0.00002086551,0.00008787443],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9762879,"threshold_uncertainty_score":0.9588335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007245533686210765,"score_gpt":0.2351668028681178,"score_spread":0.2279212691819071,"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."}}