{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004566906,0.0002365258,0.000194245,0.0004497249,0.0001999149,0.0001592792,0.0009741353,0.0002409991,0.000002458111],"category_scores_gemma":[0.0003451117,0.0003047597,0.0001330009,0.0006624892,0.00004574502,0.0002381851,0.0005805905,0.0003576913,0.00004088354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002844381,"about_ca_system_score_gemma":0.0004758316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001205666,"about_ca_topic_score_gemma":0.000273959,"domain_scores_codex":[0.9983516,0.00006573106,0.0001658926,0.0009444459,0.0001241206,0.0003481791],"domain_scores_gemma":[0.9973415,0.00103805,0.0001069397,0.001032898,0.0003292816,0.0001513273],"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":[0.000007293814,0.00003694933,0.000616227,0.00007748832,0.00001977892,0.0007725477,0.000133789,0.9821632,0.00008084985,0.01567264,0.0002547264,0.0001645481],"study_design_scores_gemma":[0.0004658653,0.00005235363,0.0001444003,0.00003677774,0.00002017956,0.00001044857,0.0000254883,0.9881489,0.000190193,0.01050715,0.00009903766,0.0002992085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1398333,0.00000918406,0.858436,0.0001197464,0.0003438367,0.0005033036,0.00009772584,0.0006414535,0.00001535456],"genre_scores_gemma":[0.924974,0.0000088631,0.07378422,0.00002803549,0.0000933203,0.00001324946,0.0001106568,0.00003792001,0.0009497756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7851406,"threshold_uncertainty_score":0.9999405,"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."}}