{"id":"W4385965483","doi":"10.48550/arxiv.2308.08033","title":"Domain Adaptation for Code Model-based Unit Test Case Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Computer science; Leverage (statistics); Unit testing; Domain adaptation; Code coverage; Artificial intelligence; Machine learning; Transformer; Task (project management); Source code; Test data; Adaptation (eye); Test case; Data mining; Software; Software engineering; Programming language; Engineering","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":[0.001396034,0.001176526,0.0005382195,0.001253133,0.0001832961,0.0006574562,0.00174954,0.00076352,0.002417021],"category_scores_gemma":[0.008358624,0.0003911013,0.0009975515,0.0009925696,0.0005292236,0.001435171,0.001098678,0.001671959,0.001175414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008882517,"about_ca_system_score_gemma":0.001210824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003350412,"about_ca_topic_score_gemma":0.004838611,"domain_scores_codex":[0.9985179,0.000534891,0.0001150991,0.0004159104,0.0002911282,0.0001250152],"domain_scores_gemma":[0.9958755,0.002108843,0.0003068138,0.0008814005,0.0007096667,0.0001177787],"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":[0.0003431004,0.0005081366,0.01202706,0.0004500298,0.000148493,0.0004866892,0.0002650157,0.3408189,0.03221034,0.003807975,0.01609614,0.5928382],"study_design_scores_gemma":[0.0000581355,0.000135332,0.001201807,0.0000288775,0.00003667732,0.000184981,0.00005411682,0.9712673,0.01787242,0.004266193,0.00487153,0.00002264977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1880302,0.001545558,0.7618604,0.0005497088,0.0001645959,0.0004066835,0.002128442,0.03945634,0.005858027],"genre_scores_gemma":[0.6925398,0.000372205,0.2941643,0.0005779483,0.00003449016,0.0004556499,0.007757164,0.001485999,0.002612527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003350412,"threshold_uncertainty_score":0.008085787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2393901657242993,"score_gpt":0.2420723057480061,"score_spread":0.002682140023706758,"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."}}