{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007512184,0.002786714,0.001913163,0.002208212,0.0008458235,0.001949513,0.004643397,0.004193611,0.00150506],"category_scores_gemma":[0.02348954,0.0006978136,0.001379206,0.001067591,0.001917548,0.004303523,0.002677886,0.004421372,0.0008420239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003102293,"about_ca_system_score_gemma":0.001626989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009342107,"about_ca_topic_score_gemma":0.0101977,"domain_scores_codex":[0.9958537,0.001368403,0.0001940167,0.001503742,0.0008077872,0.0002725288],"domain_scores_gemma":[0.9846585,0.01109251,0.0008159975,0.001271134,0.001392413,0.0007694947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001995752,0.002208544,0.0145327,0.001196647,0.000765959,0.0002576447,0.0003584499,0.5333946,0.01000179,0.00373464,0.01350857,0.4180447],"study_design_scores_gemma":[0.00004312371,0.0002943999,0.0009144303,0.00004008291,0.00003972303,0.00005732616,0.00003880806,0.9929969,0.003375356,0.001514505,0.000666724,0.00001879257],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6102431,0.02157241,0.3360267,0.002827749,0.001117233,0.000708886,0.001901396,0.01667543,0.008927023],"genre_scores_gemma":[0.8476381,0.001102514,0.1394579,0.00129431,0.0002856198,0.0002730052,0.004502909,0.0006320029,0.004813599],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009342107,"threshold_uncertainty_score":0.0397287,"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."}}