{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01596562,0.001171021,0.000835544,0.004196637,0.0009501083,0.004669188,0.002749005,0.002727513,0.001338948],"category_scores_gemma":[0.1798463,0.001376141,0.001033503,0.001986195,0.005152537,0.01239184,0.003499215,0.002084877,0.0005199747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001558419,"about_ca_system_score_gemma":0.002327923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003050309,"about_ca_topic_score_gemma":0.002743011,"domain_scores_codex":[0.9722415,0.01272144,0.002793113,0.002828043,0.008027589,0.001388248],"domain_scores_gemma":[0.7189856,0.1955202,0.02952386,0.03528652,0.01867695,0.002006954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001001232,0.0006571236,0.1544165,0.001850223,0.0002765476,0.00582518,0.01834038,0.1426561,0.04087816,0.3354688,0.004641004,0.2939888],"study_design_scores_gemma":[0.0001066351,0.0007555234,0.01578574,0.00127814,0.000271384,0.003743777,0.002633297,0.5179235,0.0531892,0.3707064,0.03330152,0.0003047872],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1610315,0.0007137136,0.8311719,0.0005414739,0.00006836399,0.0003104279,0.0002785719,0.003071754,0.00281233],"genre_scores_gemma":[0.7063916,0.000319698,0.2900509,0.0003338907,0.0000673085,0.0004319506,0.0006862753,0.0007155598,0.00100287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01596562,"threshold_uncertainty_score":0.08443522,"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."}}