{"id":"W2295745251","doi":"","title":"CrashAutomata: an approach for the detection of duplicate crash reports based on generalizable automata","year":2015,"lang":"en","type":"article","venue":"Computer Science and Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Crash; Computer science; False positive paradox; Software; Automaton; Precision and recall; Data mining; Generalization; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.002756174,0.0001891184,0.0001957823,0.000332736,0.0002202225,0.0003707532,0.001214075,0.00005803748,2.115017e-7],"category_scores_gemma":[0.001376354,0.0001483518,0.00004432176,0.001106602,0.00012844,0.0008028573,0.0003563333,0.0001414697,7.007258e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001034676,"about_ca_system_score_gemma":0.0002455795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001742454,"about_ca_topic_score_gemma":3.323034e-7,"domain_scores_codex":[0.9977776,0.00002088686,0.0002631338,0.0006672026,0.0008097211,0.0004615011],"domain_scores_gemma":[0.9973975,0.0006152729,0.00007581503,0.001218486,0.0004186938,0.0002741654],"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":[0.000003471408,0.00005529566,0.001531943,0.00007061306,0.0000077392,0.000007023139,0.000189948,0.960867,0.0009686429,0.0002641397,0.0001199994,0.03591416],"study_design_scores_gemma":[0.0002098295,0.0001910823,0.01016585,0.00002036382,0.000003839991,0.00004630334,0.000002718788,0.9852555,0.003420146,0.00003972712,0.0004674662,0.0001771414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01970883,0.0001005075,0.9784009,0.00005330988,0.0006665945,0.0003507676,0.000001803317,0.0007145505,0.00000269469],"genre_scores_gemma":[0.562071,0.000002011077,0.4376893,0.00005372981,0.00009228857,0.00007031887,0.000001836884,0.0000151015,0.000004321756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5423622,"threshold_uncertainty_score":0.6049613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03035857657399654,"score_gpt":0.2547864409965724,"score_spread":0.2244278644225758,"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."}}