{"id":"W4394585993","doi":"10.1109/tc.2024.3386068","title":"LogSay: An Efficient Comprehension System for Log Numerical Reasoning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Comprehension; Computer science; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001643713,0.0001844985,0.0001751541,0.000271009,0.0002993939,0.0003440468,0.0002800565,0.00008173817,0.00001159571],"category_scores_gemma":[0.000001337373,0.0001797743,0.0001546416,0.000439849,0.0000359013,0.0002884531,0.000003148641,0.0001841506,0.00006035699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001526599,"about_ca_system_score_gemma":0.00008350347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000176718,"about_ca_topic_score_gemma":0.000004148549,"domain_scores_codex":[0.9986114,0.00008109634,0.0002572385,0.0005621098,0.0002336819,0.0002544601],"domain_scores_gemma":[0.9991782,0.0001980467,0.00003931521,0.0003587201,0.00007412731,0.0001516261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001273448,0.00006190924,0.000001321115,0.00004202358,0.00002558067,0.00001083627,0.000305026,0.8137012,0.0001606603,0.007963032,0.0001416957,0.177574],"study_design_scores_gemma":[0.0002926963,0.0001745242,0.00004040657,0.0001702931,0.0000176,0.00009788002,0.0000429939,0.9968806,0.001229525,0.00002552502,0.0008304207,0.0001975644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001664447,0.00002483817,0.9903838,0.0004788186,0.005659631,0.0003422461,0.00001371371,0.001338927,0.0000935826],"genre_scores_gemma":[0.798617,0.000002725898,0.2011075,0.0001332905,0.00006125942,0.00003173205,0.000004496993,0.0000168641,0.000025087],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7969526,"threshold_uncertainty_score":0.7330984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01640801608658802,"score_gpt":0.2538376564882267,"score_spread":0.2374296404016387,"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."}}