{"id":"W7029356603","doi":"","title":"An Industrial Study on Predicting Crash Report Log 
\\nTypes Using Large Language Models","year":2023,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs; Concordia University","keywords":"Crash; Artificial neural network; Software; Classifier (UML); Feature (linguistics); Feature engineering; Relevance (law); Process (computing)","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.002826124,0.0004415722,0.0006299531,0.00178547,0.001488632,0.000487509,0.002269782,0.0006634074,0.000007650023],"category_scores_gemma":[0.0002266741,0.0004547595,0.0002347241,0.002489145,0.00009669774,0.001264133,0.0004712854,0.002061988,0.00004095904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035199,"about_ca_system_score_gemma":0.0019887,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02505562,"about_ca_topic_score_gemma":0.01489876,"domain_scores_codex":[0.9934344,0.001307157,0.0006027556,0.001684345,0.001871723,0.00109966],"domain_scores_gemma":[0.9961237,0.0003586436,0.0004383459,0.002237496,0.0004507262,0.0003910897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008761761,0.001989476,0.9307809,0.0003837722,0.0007163584,0.03338651,0.02324154,0.002989996,0.002001961,0.0008171451,0.0009891102,0.001827071],"study_design_scores_gemma":[0.00740388,0.008466255,0.6846792,0.002119818,0.0004314004,0.0004279754,0.1565872,0.1196981,0.01353773,0.001265305,0.001642499,0.003740722],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981611,0.00002555259,0.0005130566,0.00002738635,0.004735985,0.001373804,0.00001395596,0.0007712317,0.0109281],"genre_scores_gemma":[0.9819486,0.000009789398,0.00002414277,0.000002996525,0.001025631,0.000009127848,0.00009814293,0.00006595905,0.01681563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2461018,"threshold_uncertainty_score":0.9998113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06174276438027777,"score_gpt":0.3323113778645881,"score_spread":0.2705686134843104,"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."}}