{"id":"W4400978763","doi":"10.1109/tse.2024.3433463","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Oracle; Test (biology); Artificial neural network; Machine learning; Artificial intelligence; Data mining; Software engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006126131,0.000171948,0.0001218216,0.0004755925,0.0001828065,0.0007344597,0.0002334049,0.000084829,0.000005203648],"category_scores_gemma":[0.0004818787,0.0001788935,0.0001036801,0.0009372985,0.00000833983,0.0009988125,0.000002320123,0.0002104141,0.000008752761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001864135,"about_ca_system_score_gemma":0.00008641359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007298679,"about_ca_topic_score_gemma":9.716007e-7,"domain_scores_codex":[0.9987964,0.00002243017,0.0002173827,0.000395953,0.0003364909,0.0002313533],"domain_scores_gemma":[0.9980827,0.001347353,0.00002816816,0.0003181786,0.0001609088,0.00006272188],"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":[8.27718e-7,0.00005045619,0.00002313153,0.0000825326,0.00002101719,0.000005230546,0.0001373855,0.3568023,0.001482174,0.0001334175,0.001050884,0.6402107],"study_design_scores_gemma":[0.00009620027,0.00007930615,0.00005396589,0.00008893503,0.00003259746,0.00002188221,0.000001275753,0.9847773,0.01407474,0.0002373525,0.0003389926,0.0001974514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003105365,0.0003090284,0.9794731,0.0000780105,0.002041862,0.0002934086,0.000008906988,0.01468493,0.000005374083],"genre_scores_gemma":[0.5750729,0.00000365502,0.4245925,0.00003122379,0.0001015385,0.0001509139,0.000003780568,0.00002490283,0.00001861435],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6400132,"threshold_uncertainty_score":0.7295064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0715888736640746,"score_gpt":0.3253112017937551,"score_spread":0.2537223281296804,"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."}}