{"id":"W2975484362","doi":"10.22215/etd/2019-13526","title":"Identifying Software Defects Using Neural Graph Classifiers","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Suite; Java; Artificial intelligence; Graph; Source code; Software; Machine learning; Test suite; Task (project management); Software suite; Test case; Data mining; Programming language; Theoretical computer science; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007203121,0.0009150195,0.0007489813,0.003523333,0.0004061437,0.001126039,0.001074563,0.001361768,0.002250678],"category_scores_gemma":[0.002602103,0.0002980275,0.001037254,0.001279535,0.0004492516,0.001126796,0.0004924895,0.0009471583,0.001295931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001024516,"about_ca_system_score_gemma":0.0006928295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009594243,"about_ca_topic_score_gemma":0.01039364,"domain_scores_codex":[0.9994273,0.00007314448,0.00002732222,0.0002269705,0.0001563228,0.00008901441],"domain_scores_gemma":[0.9984286,0.0007060469,0.0001678383,0.0001651921,0.0004668653,0.00006534915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002825569,0.0003127767,0.009847772,0.0001416053,0.0001412098,0.000199929,0.00007734538,0.1651853,0.01115603,0.004507143,0.01183234,0.796316],"study_design_scores_gemma":[0.000006718807,0.00004990596,0.001426734,0.00002087286,0.00002868396,0.00004443243,0.00002491103,0.9908325,0.002536482,0.0041963,0.0008260426,0.000006459171],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2812187,0.002232363,0.6935424,0.0007740001,0.0002485553,0.0003179729,0.001488073,0.007447047,0.01273084],"genre_scores_gemma":[0.8517763,0.0007182912,0.1335193,0.0002643887,0.0001032881,0.0001431295,0.003722295,0.0003078447,0.00944524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009594243,"threshold_uncertainty_score":0.01907676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04384843707961259,"score_gpt":0.3148986019848136,"score_spread":0.271050164905201,"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."}}