{"id":"W2102967730","doi":"10.1145/2451116.2451128","title":"Production-run software failure diagnosis via hardware performance counters","year":2013,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministère de l'Économie, de la Science et de l'Innovation - Québec","keywords":"Concurrency; Computer science; Overhead (engineering); Software; Embedded system; Reliability engineering; Software bug; Instrumentation (computer programming); Operating system; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000276623,0.0002506982,0.000244379,0.0001091885,0.0003240625,0.0002434569,0.0009748296,0.000119732,0.0004376564],"category_scores_gemma":[0.00009841612,0.0001849988,0.0001064921,0.0005252207,0.0000869582,0.002618007,0.0002387665,0.0001985991,0.002462081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001052339,"about_ca_system_score_gemma":0.00007638586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000203502,"about_ca_topic_score_gemma":0.00002295787,"domain_scores_codex":[0.9979874,0.0000434656,0.0003711341,0.0006735658,0.000456551,0.0004678239],"domain_scores_gemma":[0.9981167,0.00007415067,0.0001061449,0.001155644,0.0003949695,0.0001524229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000331944,0.0001148362,0.7566302,0.0002839176,0.00004094838,0.000002228933,0.0008073476,0.000396407,0.0001040356,0.0001009978,0.1064394,0.1350763],"study_design_scores_gemma":[0.001171512,0.0006484788,0.7891647,0.0005241171,0.00003891621,0.0002752333,0.0003989867,0.04448485,0.02512925,0.001245874,0.1344589,0.002459207],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8021284,0.0001571321,0.1856779,0.00580651,0.002731843,0.001173301,0.00000226671,0.001714774,0.0006078625],"genre_scores_gemma":[0.9649966,0.00006154859,0.03196575,0.0006075707,0.0002225075,0.0005866237,0.000004158096,0.00001721062,0.001537969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1628682,"threshold_uncertainty_score":0.9983146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007835913682536794,"score_gpt":0.2020632126152486,"score_spread":0.1942272989327118,"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."}}