{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004930646,0.001598627,0.0009160584,0.00155047,0.0003673263,0.001372543,0.002458753,0.001071329,0.003723014],"category_scores_gemma":[0.03586983,0.001027434,0.001317032,0.0006195165,0.001700712,0.003234671,0.002894048,0.001471433,0.001215721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009106857,"about_ca_system_score_gemma":0.00190485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001812749,"about_ca_topic_score_gemma":0.0025231,"domain_scores_codex":[0.9940286,0.002041946,0.0004210224,0.001282416,0.001779992,0.0004460661],"domain_scores_gemma":[0.9693303,0.01625257,0.001970208,0.009512745,0.002458556,0.0004756236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002274137,0.0008044747,0.06261195,0.001171016,0.0003941428,0.001939795,0.00142716,0.3326011,0.1079155,0.03838269,0.01865875,0.4318193],"study_design_scores_gemma":[0.0001759517,0.0003487404,0.003128113,0.00007708697,0.00007526198,0.0002795167,0.0001129049,0.8934362,0.07094841,0.02537596,0.00597121,0.00007068671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07933244,0.0001707763,0.8594694,0.0002547371,0.00006504192,0.0003185421,0.001209925,0.05723127,0.001947878],"genre_scores_gemma":[0.5055113,0.00009600155,0.4811229,0.0002862499,0.00004289027,0.0005899402,0.004376408,0.00597243,0.002001891],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004930646,"threshold_uncertainty_score":0.02607608,"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."}}