{"id":"W4403255280","doi":"10.1007/s10664-024-10441-z","title":"Evaluating few-shot and contrastive learning methods for code clone detection","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; clone (Java method); Artificial intelligence; Code (set theory); Shot (pellet); Programming language; Biology; DNA; Genetics","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001720957,0.0002512587,0.0002712153,0.0002708819,0.0001620661,0.0003979222,0.0003139579,0.0001374692,0.000006441904],"category_scores_gemma":[0.01248517,0.0002512692,0.0001014386,0.0007204803,0.00002664126,0.0003948864,0.0002355323,0.0006276869,0.00001091352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001947566,"about_ca_system_score_gemma":0.00006707539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000573772,"about_ca_topic_score_gemma":5.777108e-7,"domain_scores_codex":[0.9980891,0.00009822487,0.0002802058,0.0006706298,0.0003013687,0.0005604316],"domain_scores_gemma":[0.9894595,0.009957649,0.00002610699,0.0002340466,0.0001171844,0.0002055117],"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":[0.00002186358,0.00002591694,0.003990198,0.0006770184,0.000178518,0.00002777002,0.001434285,0.1416033,0.02679378,0.0003951221,0.0001395977,0.8247126],"study_design_scores_gemma":[0.0002605028,0.0002608737,0.007532994,0.0001337744,0.0000182295,0.00005319568,0.000007917377,0.9723797,0.006766586,0.0001871121,0.01206937,0.0003297021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04149492,0.002392469,0.9522672,0.000161973,0.0008139101,0.0003338526,0.00000303724,0.002529778,0.000002861775],"genre_scores_gemma":[0.3955578,0.00001458578,0.6038764,0.00002441623,0.0002100506,0.0001732244,0.000003175255,0.00005779413,0.0000825458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8307765,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09238815332234587,"score_gpt":0.4441704756515731,"score_spread":0.3517823223292272,"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."}}