{"id":"W4400343086","doi":"10.48550/arxiv.2407.00768","title":"PROZE: Generating Parameterized Unit Tests Informed by Runtime Data","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Knut och Alice Wallenbergs Stiftelse; Institut de Valorisation des Données; Stiftelsen för Strategisk Forskning","keywords":"Parameterized complexity; Unit (ring theory); Computer science; Unit testing; Operating system; Algorithm; Psychology; Mathematics education","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003735616,0.0005062698,0.0004514757,0.0003467104,0.0001164665,0.000513665,0.005600482,0.0003994527,0.000014828],"category_scores_gemma":[0.00004595828,0.0005794875,0.000129283,0.0008003431,0.0000870189,0.0007505511,0.01504393,0.001075702,0.0001097652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002126077,"about_ca_system_score_gemma":0.0004526908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001091327,"about_ca_topic_score_gemma":0.00001512816,"domain_scores_codex":[0.9972309,0.00009013125,0.000344548,0.001676259,0.0001704742,0.0004876769],"domain_scores_gemma":[0.9954008,0.0001278445,0.0002204372,0.003921633,0.0001331484,0.0001961754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004603346,0.000335034,0.00130821,0.001951803,0.0009690829,0.00169467,0.001179211,0.4738804,0.002529343,0.4340681,0.05272378,0.02931429],"study_design_scores_gemma":[0.0001878973,0.0000394279,0.00002370321,0.0002645458,0.00006500252,0.000008606302,0.000002824358,0.9715765,0.0003254485,0.009423042,0.01744031,0.0006426569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04828525,0.0001264598,0.9472596,0.00006689063,0.0004977454,0.0005212888,0.0002090881,0.002761811,0.0002718323],"genre_scores_gemma":[0.5639384,0.0001367404,0.4335808,0.00009747747,0.00009109997,0.000007981856,0.0004974743,0.00006664591,0.001583426],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5156531,"threshold_uncertainty_score":0.9997797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1243712334767623,"score_gpt":0.2282470431464741,"score_spread":0.1038758096697118,"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."}}