{"id":"W3202264790","doi":"10.1007/s10664-021-10016-2","title":"Rotten green tests in Java, Pharo and Python","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Python (programming language); Java; Computer science; Programming language; Unit testing; Test (biology); Software; Biology; Ecology","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":[0.0002956027,0.0002249443,0.0002665306,0.0002291775,0.0000434208,0.0001445788,0.0004917932,0.000122115,0.00002046175],"category_scores_gemma":[0.003013671,0.000242061,0.0000550996,0.001166706,0.00001996651,0.0003820984,0.0005946724,0.0004650071,0.00003744595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001309819,"about_ca_system_score_gemma":0.00008870789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004475958,"about_ca_topic_score_gemma":0.00001172229,"domain_scores_codex":[0.9981206,0.00003850554,0.0002632236,0.0005908718,0.0003982885,0.0005884987],"domain_scores_gemma":[0.9977119,0.001408811,0.00002042814,0.0005240989,0.0000759944,0.0002587934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002918618,0.00007786667,0.9692427,0.000148471,0.00002610554,0.001001611,0.0005603389,0.006321461,0.001100271,0.0001593412,0.0006710747,0.02068783],"study_design_scores_gemma":[0.0005103119,0.00004160158,0.9542382,0.0001069923,0.000003312822,0.000154256,0.000004854572,0.03318632,0.001658947,0.0001835171,0.009465955,0.0004456697],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5171917,0.001356305,0.4788109,0.001021961,0.0003330008,0.0001402033,0.000002816495,0.001116931,0.00002619029],"genre_scores_gemma":[0.8797066,0.00003466506,0.1194004,0.0002619427,0.0001509215,0.00005175068,0.000005844661,0.00006090393,0.0003269581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.362515,"threshold_uncertainty_score":0.9870961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02234213422314712,"score_gpt":0.284636052570599,"score_spread":0.2622939183474519,"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."}}