{"id":"W4391915512","doi":"10.1007/s10664-024-10443-x","title":"Studying the impact of risk assessment analytics on risk awareness and code review performance","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"","keywords":"Analytics; Computer science; Data science; Code (set theory); Risk analysis (engineering); Business; 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":[0.001281814,0.0002720042,0.0003552908,0.0001936836,0.0001435891,0.0001802948,0.0007138682,0.00006458027,0.000009758146],"category_scores_gemma":[0.002829829,0.0001761048,0.0001710536,0.001199972,0.00003815848,0.0002713583,0.0003485836,0.0008328125,0.00001094091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002287796,"about_ca_system_score_gemma":0.0001592507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004302649,"about_ca_topic_score_gemma":8.696767e-7,"domain_scores_codex":[0.9981062,0.00008831247,0.0003570903,0.0004543928,0.0005824717,0.0004115693],"domain_scores_gemma":[0.9943905,0.00459697,0.00006508963,0.0007031382,0.00009295809,0.0001513835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002591907,0.00004172558,0.7245479,0.0009797936,0.0001842861,0.00002713937,0.0003042962,0.2526505,0.000007316076,0.00004771569,0.001079531,0.02012721],"study_design_scores_gemma":[0.0000749311,0.0001283033,0.5936566,0.001049468,0.00002924342,0.00001473183,0.000001989805,0.4043375,0.00003386747,0.00001738391,0.0004895492,0.0001664229],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5085651,0.007979798,0.4823895,0.00009432698,0.0002260136,0.0002091767,0.00002810898,0.0005030975,0.000004873036],"genre_scores_gemma":[0.9846113,0.005523089,0.009672006,0.00002399821,0.00008525793,0.00003523786,0.000002574979,0.00003677967,0.000009710259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4760462,"threshold_uncertainty_score":0.7181346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04283266006473341,"score_gpt":0.3663655825837216,"score_spread":0.3235329225189882,"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."}}