{"id":"W2145733341","doi":"10.1145/2786805.2786858","title":"Assertions are strongly correlated with test suite effectiveness","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test suite; Assertion; Test (biology); Computer science; Suite; Java; Test case; Code coverage; Code (set theory); Unit testing; Programming language; Algorithm; Machine learning; Software; Regression analysis","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003682772,0.0001142475,0.0001228927,0.00007546842,0.0000772631,0.0001287764,0.0004254556,0.00004759713,0.000002123939],"category_scores_gemma":[0.0005842808,0.00008292763,0.00002066541,0.0004637451,0.00003416269,0.0002840222,0.0001113083,0.0001182816,0.0000463842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005493632,"about_ca_system_score_gemma":0.00009886685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001538013,"about_ca_topic_score_gemma":0.0000199481,"domain_scores_codex":[0.9991595,0.00006187771,0.00009397655,0.0002705797,0.0002054326,0.0002085899],"domain_scores_gemma":[0.9984511,0.0006471912,0.00005980289,0.000463305,0.0002463234,0.0001322884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001915286,0.0002742446,0.9667841,0.00001801161,0.00002291397,0.00008241671,0.0002379866,0.0007005297,0.0000801573,0.006631892,0.01993169,0.005216961],"study_design_scores_gemma":[0.002093531,0.002233465,0.7202278,0.000524271,0.00003593955,0.0003983375,0.00005341108,0.2298511,0.00452725,0.03787209,0.001116012,0.001066779],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04869111,0.00002165154,0.9318488,0.0001972951,0.0001050733,0.0001632435,0.000001100768,0.01599734,0.002974396],"genre_scores_gemma":[0.8883801,1.845376e-7,0.1112871,0.00005986833,0.00001300402,0.00002637597,0.000001672044,0.000008917734,0.0002228036],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.839689,"threshold_uncertainty_score":0.338169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02982942736725199,"score_gpt":0.2597681029273936,"score_spread":0.2299386755601416,"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."}}