{"id":"W4393610751","doi":"10.5281/zenodo.6994691","title":"Flakify: A Black-Box, Language Model-based Predictor for Flaky Tests – Replication Package","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Replication (statistics); Black box; Computer science; Programming language; Mathematics; Artificial intelligence; Statistics","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":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00149615,0.0003245286,0.0003009569,0.000527358,0.001962327,0.001162658,0.004474125,0.0001781188,0.003773563],"category_scores_gemma":[0.004813689,0.0003601764,0.0001343062,0.0008185821,0.0001530553,0.000270891,0.002691604,0.0005691948,0.0006751827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003303628,"about_ca_system_score_gemma":0.0000378109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003450268,"about_ca_topic_score_gemma":6.65586e-7,"domain_scores_codex":[0.9967918,0.0003628905,0.0004168503,0.001218794,0.000690019,0.0005196569],"domain_scores_gemma":[0.9953446,0.0002454574,0.0003574064,0.00329105,0.0005515719,0.0002098638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002528738,0.000147712,2.572484e-7,0.0001955038,0.00002048344,0.00001427457,0.0002726472,0.0002279041,0.0000917367,0.0002883617,0.9865646,0.01215118],"study_design_scores_gemma":[0.0003854706,0.0004607296,0.000007147965,0.00006933565,0.00002715562,0.0000372186,0.00001041739,0.03821097,0.0001027267,0.001102383,0.9592222,0.0003642666],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00002570997,0.00005312253,0.3403288,0.0006259262,0.0001241178,0.001129513,0.644308,0.01273328,0.000671517],"genre_scores_gemma":[0.0007424046,0.00002327335,0.02298119,0.0004956299,0.0001694313,0.000002540966,0.9742064,0.00106708,0.000312035],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3298984,"threshold_uncertainty_score":0.999885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03671388466794158,"score_gpt":0.283911857080683,"score_spread":0.2471979724127414,"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."}}