{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006306313,0.001394699,0.0005400535,0.001674494,0.0003932909,0.001351008,0.001933716,0.0007406588,0.006553347],"category_scores_gemma":[0.04292724,0.0007530291,0.0008070478,0.0005642779,0.0009706139,0.001597163,0.001775114,0.001212774,0.002976038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004867096,"about_ca_system_score_gemma":0.00149167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001143017,"about_ca_topic_score_gemma":0.00133138,"domain_scores_codex":[0.9950175,0.001478715,0.000401743,0.001361619,0.001425934,0.0003145732],"domain_scores_gemma":[0.9615985,0.02672986,0.001950384,0.005084747,0.004181247,0.0004552823],"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":[0.001266447,0.001148475,0.04237473,0.001633876,0.000224294,0.003942758,0.005701212,0.06717591,0.08944133,0.02977415,0.05652895,0.7007878],"study_design_scores_gemma":[0.0003586528,0.0005776924,0.006582786,0.0003688415,0.0001332021,0.001859436,0.0006066855,0.6834618,0.196752,0.02616993,0.08294416,0.0001847444],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08029779,0.0001488378,0.8291138,0.0002582523,0.000194834,0.0009048952,0.001770006,0.08249565,0.004815862],"genre_scores_gemma":[0.3627919,0.0001370417,0.61448,0.0003542,0.00006843639,0.001145407,0.005259159,0.01045714,0.005306778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006553347,"threshold_uncertainty_score":0.0333513,"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."}}