{"id":"W2084669353","doi":"10.1109/icpc.2013.6613851","title":"Towards generating human-oriented summaries of unit test cases","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Unit testing; Computer science; Java; USable; Test (biology); Code coverage; Code (set theory); Programming language; Test case; Unit (ring theory); Software engineering; Software; Machine learning; World Wide Web; Set (abstract data type)","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":[0.0001572472,0.0001060284,0.0001372184,0.00008901634,0.0001403753,0.0001170158,0.0004373434,0.00004024988,0.00004880143],"category_scores_gemma":[0.001010367,0.00008636786,0.00003469451,0.0003044374,0.00006923317,0.0002198279,0.0002597301,0.00006873007,0.00001410472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001062398,"about_ca_system_score_gemma":0.0000472563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003446569,"about_ca_topic_score_gemma":0.00002862031,"domain_scores_codex":[0.9991774,0.00002822309,0.0002287761,0.0002053662,0.000176106,0.0001841264],"domain_scores_gemma":[0.9986647,0.0004755435,0.00008457093,0.0004595634,0.0002606698,0.00005496203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001744326,0.000489869,0.4098739,0.0001268815,0.0000437907,0.00006792142,0.001803899,0.0000562584,0.03491134,0.1735995,0.1805536,0.1984714],"study_design_scores_gemma":[0.001143564,0.002556999,0.09926183,0.0005442048,0.00004069274,0.0003964665,0.0002208293,0.2582746,0.4470607,0.1813251,0.006956384,0.002218734],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.402135,0.00009024206,0.5782651,0.000408604,0.0001482178,0.0002539707,0.000004155263,0.01063373,0.008060975],"genre_scores_gemma":[0.6276187,8.814672e-7,0.3718886,0.0001413937,0.00002425291,0.00001600243,0.000002013302,0.000005087395,0.0003030343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4121493,"threshold_uncertainty_score":0.5210205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04241395473701962,"score_gpt":0.2900342707541397,"score_spread":0.2476203160171201,"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."}}