{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002979299,0.002556275,0.00188761,0.001635786,0.0007517697,0.001249737,0.003852542,0.002734305,0.004747191],"category_scores_gemma":[0.01342504,0.0008762831,0.001355209,0.001118441,0.001058878,0.004367953,0.002406412,0.003831067,0.003921268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001184498,"about_ca_system_score_gemma":0.002088698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004889112,"about_ca_topic_score_gemma":0.008598667,"domain_scores_codex":[0.9982535,0.0004882675,0.00009350217,0.0008020537,0.0002152426,0.0001473253],"domain_scores_gemma":[0.993087,0.004431169,0.0002497694,0.001002564,0.000891901,0.0003375273],"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":[0.001166267,0.001275593,0.004757948,0.001031399,0.0002271189,0.0004484192,0.0005465185,0.1313038,0.02650261,0.00366531,0.03170756,0.7973674],"study_design_scores_gemma":[0.0001380202,0.0004304018,0.0008547493,0.00004274686,0.00006472206,0.0001677199,0.0001351165,0.9733314,0.01170688,0.009543784,0.003533621,0.00005074282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09085193,0.003180383,0.8488328,0.0006317855,0.0004164106,0.0006209887,0.001416937,0.05058655,0.003462245],"genre_scores_gemma":[0.6258302,0.000773065,0.3497419,0.001676858,0.0002741676,0.001104765,0.009659218,0.001555906,0.009383859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004889112,"threshold_uncertainty_score":0.01588088,"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."}}