{"id":"W4281741287","doi":"10.1145/3543146.3543168","title":"LogStamp","year":2022,"lang":"en","type":"article","venue":"ACM SIGMETRICS Performance Evaluation Review","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Parsing; Computer science; Set (abstract data type); Training set; Service (business); Data set; Data mining; Artificial intelligence; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009683977,0.0001917987,0.0003495545,0.0003796569,0.0006562987,0.00006156898,0.002454391,0.00003797961,0.001014667],"category_scores_gemma":[0.00184631,0.000168711,0.0001421956,0.005005853,0.00002859896,0.0008306166,0.001238114,0.0003387612,0.0003720096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004296386,"about_ca_system_score_gemma":0.000421647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005376501,"about_ca_topic_score_gemma":2.539564e-7,"domain_scores_codex":[0.9958087,0.0004956715,0.0006642003,0.0005423175,0.002135076,0.0003539924],"domain_scores_gemma":[0.9966247,0.0002781001,0.0003399821,0.002179117,0.0004842358,0.00009385895],"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":[0.000002688217,0.0001343111,0.01176589,0.00104331,0.00001849438,0.000001455532,0.0001286144,0.001434797,0.000006226768,0.0005713452,0.02026604,0.9646268],"study_design_scores_gemma":[0.001417682,0.0007774342,0.0426404,0.0008054015,0.0001630435,0.0001630596,0.00004193875,0.2710124,0.000190688,0.00147837,0.680223,0.00108659],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2754159,0.6129209,0.06133278,0.0146913,0.01057025,0.009842051,0.0000254651,0.001728588,0.01347277],"genre_scores_gemma":[0.9286552,0.05474466,0.008674069,0.005820197,0.0001188058,0.001577059,0.00005623162,0.00002318631,0.0003306136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9635403,"threshold_uncertainty_score":0.9998986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06053903006316866,"score_gpt":0.3235410959505138,"score_spread":0.2630020658873451,"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."}}