{"id":"W814172419","doi":"10.1109/saner.2016.105","title":"Analyzing the State of Static Analysis: A Large-Scale Evaluation in Open Source Software","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":206,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Java; Python (programming language); Computer science; Open source software; Software; Software engineering; JavaScript; Open source; Static analysis; Population; 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":[0.003426591,0.00007904486,0.0001786753,0.000355928,0.00004041549,0.0001226737,0.001551366,0.00001733381,0.00008839311],"category_scores_gemma":[0.001089268,0.00004268764,0.00005479177,0.00216014,0.00002527374,0.0004609598,0.0006767032,0.00007031646,0.0000190746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008862328,"about_ca_system_score_gemma":0.0001250462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002280221,"about_ca_topic_score_gemma":0.0004961703,"domain_scores_codex":[0.9984494,0.0002192443,0.0002603415,0.0002873648,0.0005062409,0.0002773456],"domain_scores_gemma":[0.9976454,0.001299611,0.00006717286,0.0007483413,0.0001911611,0.00004835156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001384924,0.0001258467,0.4982606,0.0000253627,0.0003341971,0.000003359182,0.005030285,0.09037391,0.0004351775,0.0002769277,0.0003681862,0.4047523],"study_design_scores_gemma":[0.0007429144,0.00004135286,0.2967128,0.00004877475,0.00004863256,6.421324e-7,0.00008391886,0.6985662,0.001022425,0.002457475,0.000135405,0.0001394921],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2214535,0.00005183516,0.7777928,0.0003597547,0.00001914135,0.0002437644,0.000002545024,0.00005290285,0.00002377855],"genre_scores_gemma":[0.9657508,0.00000709011,0.03363694,0.00002572273,0.000004631386,0.00005219153,0.000001154977,0.000006981925,0.0005145485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7442972,"threshold_uncertainty_score":0.2882849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02635283887304471,"score_gpt":0.3156834690939992,"score_spread":0.2893306302209546,"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."}}