{"id":"W4387634923","doi":"10.48550/arxiv.2310.07856","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Oracle; Computer science; Test (biology); Metric (unit); Assertion; Machine learning; Test case; Artificial intelligence; Data mining; Programming language; Regression analysis; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01706335,0.002139727,0.0009991627,0.004824183,0.0004423424,0.002528213,0.002667018,0.001685662,0.001298981],"category_scores_gemma":[0.1216332,0.0004587583,0.0007632621,0.002504391,0.001178552,0.004206317,0.002014447,0.002167629,0.0006794462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003183682,"about_ca_system_score_gemma":0.002183366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007025388,"about_ca_topic_score_gemma":0.009132746,"domain_scores_codex":[0.980838,0.008912308,0.001904228,0.002433156,0.005261826,0.0006504534],"domain_scores_gemma":[0.8944715,0.07485919,0.006729351,0.0093967,0.01276239,0.00178083],"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":[0.001384366,0.001028839,0.1461193,0.001474495,0.0008089783,0.0002822886,0.0007082887,0.319778,0.006349955,0.004186105,0.01061359,0.5072657],"study_design_scores_gemma":[0.00009378499,0.001057687,0.02039981,0.0002626072,0.000146019,0.000189755,0.0002560705,0.9611423,0.009016591,0.00451546,0.002854267,0.00006568036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7358739,0.009962993,0.2244664,0.001625282,0.0004023203,0.0005759249,0.003172524,0.01543632,0.008484359],"genre_scores_gemma":[0.9178461,0.0005523133,0.07379158,0.000304056,0.0000571532,0.0002541367,0.005726538,0.0004889246,0.0009791122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01706335,"threshold_uncertainty_score":0.09024072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.334270648900014,"score_gpt":0.2987627042028986,"score_spread":0.03550794469711538,"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."}}