{"id":"W4400680797","doi":"10.1109/saner60148.2024.00017","title":"Gloss: Guiding Large Language Models to Answer Questions from System Logs","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Gloss (optics); Computer science; Natural language processing; Programming language; Artificial intelligence","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":[0.0001982898,0.000100884,0.0001078469,0.0001025112,0.00006771291,0.0003501798,0.0005452873,0.00005054806,0.00002948335],"category_scores_gemma":[0.000009223396,0.00008643847,0.0000477436,0.0002518304,0.000003683878,0.0004817171,0.0003001467,0.00006364559,0.000374828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009474168,"about_ca_system_score_gemma":0.00008096382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009698833,"about_ca_topic_score_gemma":0.00007178875,"domain_scores_codex":[0.9989352,0.0000317505,0.0001807138,0.0004301982,0.0001901185,0.0002319674],"domain_scores_gemma":[0.9992285,0.00004521794,0.00001093344,0.0005707048,0.00003568742,0.000108945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[2.979471e-7,0.00001030956,0.000009329914,0.00002224234,0.00001055917,0.00004307646,0.001985948,0.002561264,0.0004603852,0.9847715,0.001694027,0.008430986],"study_design_scores_gemma":[0.00003872712,0.000006709084,0.000007060524,0.0002223527,0.00000497459,0.000007765683,0.0004694877,0.9894909,0.00031095,0.005869181,0.00344774,0.0001241991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01269174,0.001096199,0.9576559,0.0006006127,0.00104442,0.0001170218,0.00001349897,0.001198435,0.02558218],"genre_scores_gemma":[0.8323585,0.000001815858,0.1651035,0.0005326529,0.0001915471,0.00001606052,0.000002385997,0.000009001599,0.001784506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9869296,"threshold_uncertainty_score":0.4817781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03842013210703462,"score_gpt":0.2762254992872696,"score_spread":0.237805367180235,"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."}}