{"id":"W4312260323","doi":"10.1109/tse.2022.3217544","title":"Dynamic Human-in-the-Loop Assertion Generation","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Assertion; Computer science; Programming language; TypeScript; JavaScript; Test (biology); Test case; Workflow; Notation; Automation; Software engineering; Variable (mathematics); Database; Arithmetic; Mathematics; Machine learning","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":[0.0004199079,0.000139855,0.0001034403,0.0002981942,0.000428386,0.00009111392,0.0005620383,0.00003714183,0.00001416375],"category_scores_gemma":[0.00002376144,0.0001419721,0.00006939566,0.000662811,0.000007883123,0.0002191606,0.000005189188,0.0004379257,0.000006134325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001924362,"about_ca_system_score_gemma":0.00002469342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003561301,"about_ca_topic_score_gemma":0.000009999077,"domain_scores_codex":[0.9988868,0.00007014458,0.000200109,0.0002912585,0.0003332003,0.0002184773],"domain_scores_gemma":[0.9992608,0.0001839192,0.00003740201,0.0004643383,0.00002342816,0.00003005643],"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":[0.000002780584,0.0001847388,0.00008227889,0.00001582307,0.00001158848,0.0000355966,0.0007506981,0.9722473,0.002918815,0.0004038073,0.0008221422,0.02252443],"study_design_scores_gemma":[0.0002582424,0.0002104544,0.0007415158,0.00002498923,0.000009362707,0.0001089416,0.00001228914,0.994596,0.002845647,0.0004301229,0.0004316919,0.0003307289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04391376,0.00003200619,0.9501663,0.000106328,0.0005840136,0.0001535323,0.000003466421,0.005033438,0.000007161887],"genre_scores_gemma":[0.9054304,0.000002249426,0.09402318,0.0001632167,0.00001780544,0.0002760651,0.000004240299,0.00001829145,0.00006448261],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8615167,"threshold_uncertainty_score":0.5789454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02170916402304557,"score_gpt":0.2527178957400945,"score_spread":0.2310087317170489,"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."}}