{"id":"W4411450040","doi":"10.1145/3715741","title":"Understanding and Characterizing Mock Assertions in Unit Tests","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Assertion; Test (biology); Testability; Complement (music); Unit testing; Programming language; Control flow; Test case; Software engineering; Reliability engineering; Machine learning; Software","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":[0.0002826743,0.0001450051,0.0001683054,0.0003315633,0.00008346063,0.00009827772,0.001324862,0.00006849306,3.674826e-7],"category_scores_gemma":[0.005764493,0.0001221018,0.00003889127,0.0009019843,0.00002856516,0.0002472767,0.0008549483,0.0002382269,5.137527e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008864116,"about_ca_system_score_gemma":0.00002722162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001116515,"about_ca_topic_score_gemma":7.725355e-7,"domain_scores_codex":[0.9991672,0.000003648098,0.0002055411,0.0002565745,0.0001567722,0.0002102595],"domain_scores_gemma":[0.9989876,0.0004183603,0.00008183287,0.0004065417,0.00007031894,0.00003536468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001462881,0.0001233397,0.8459496,0.0005216215,0.00004285828,0.000002683647,0.0007570027,0.0002573219,0.007576813,0.1358705,0.005826236,0.00305732],"study_design_scores_gemma":[0.0005587831,0.000130042,0.7854823,0.003359353,0.00002103145,0.00002619776,0.00003221078,0.02356692,0.01654953,0.1691465,0.0005938642,0.0005333024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8708465,0.0001652486,0.1163605,0.003683979,0.0004753258,0.0004390221,0.0000031739,0.007546982,0.0004792975],"genre_scores_gemma":[0.8889307,0.000007371475,0.1108032,0.0001560571,0.00001140276,0.00002149921,1.690648e-7,0.00001125917,0.00005833878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06046741,"threshold_uncertainty_score":0.6901053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05208794963468529,"score_gpt":0.2627753376960894,"score_spread":0.2106873880614041,"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."}}