{"id":"W4384302749","doi":"10.1109/icse48619.2023.00205","title":"Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Assertion; Task (project management); Code (set theory); Embedding; Artificial intelligence; Selection (genetic algorithm); Language model; Source code; Natural language processing; Programming language; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0008104197,0.0000941338,0.00009948753,0.0002736226,0.0001575866,0.0001270566,0.0003963421,0.00007892396,0.00003800922],"category_scores_gemma":[0.001637135,0.00009028892,0.00005431902,0.002041734,0.00001463365,0.0001688878,0.00008478711,0.0002262427,0.0002535715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008237002,"about_ca_system_score_gemma":0.0001178297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009954448,"about_ca_topic_score_gemma":0.000002433498,"domain_scores_codex":[0.9987479,0.00003957463,0.0001487884,0.0003472165,0.0003246308,0.0003919023],"domain_scores_gemma":[0.9985118,0.001009413,0.00002715603,0.0002164996,0.0001562657,0.00007884943],"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":[0.0001786298,0.0002162385,0.08046797,0.0005283808,0.0002093376,0.0000399752,0.001485602,0.702516,0.08890817,0.02264906,0.05939602,0.04340463],"study_design_scores_gemma":[0.0003904284,0.0001828898,0.00633988,0.0000141954,0.000001844642,0.000002747317,0.000004505184,0.9678103,0.02017142,0.0002774852,0.004675869,0.0001283966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09525284,0.00001111727,0.8986326,0.0009870352,0.0003077862,0.0004279277,8.118561e-7,0.004139298,0.0002405684],"genre_scores_gemma":[0.9686115,0.000002006871,0.02133607,0.00003574855,0.00004245352,0.00005657557,0.00001436208,0.00002859118,0.009872679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8772966,"threshold_uncertainty_score":0.3681875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03815834648910112,"score_gpt":0.3065794255146276,"score_spread":0.2684210790255265,"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."}}