{"id":"W4410552841","doi":"10.1109/saner64311.2025.00053","title":"Evaluating the Effectiveness and Efficiency of Demonstration Retrievers in RAG for Coding Tasks","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Manitoba","funders":"","keywords":"Computer science; Coding (social sciences); Mathematics; Statistics","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":[0.002333028,0.0000354506,0.00005926023,0.00006131694,0.00008220827,0.00003885529,0.0001686369,0.00002089249,5.186661e-7],"category_scores_gemma":[0.000881068,0.00002463912,0.00001139414,0.0003284171,0.0000252673,0.000109767,0.00004541396,0.00005225783,1.757815e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001438739,"about_ca_system_score_gemma":0.00004770372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004325647,"about_ca_topic_score_gemma":0.000009296522,"domain_scores_codex":[0.999417,0.0001806272,0.0001186521,0.0001482841,0.00007335024,0.00006205447],"domain_scores_gemma":[0.9985273,0.001217337,0.00004736031,0.0001612022,0.00003996504,0.000006771718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005174548,0.00003080379,0.02985378,0.0001224262,0.000005651824,8.241312e-8,0.0003022405,0.001508243,0.02966025,0.6428978,0.00002601199,0.2955409],"study_design_scores_gemma":[0.0003513024,0.00007138862,0.1547681,0.00004368812,0.000003344721,3.804827e-7,0.00004426962,0.8367075,0.005181458,0.002768669,0.00002855808,0.00003129679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2361887,0.00002886528,0.7619802,0.0004131867,0.00004941516,0.0002131306,4.450894e-7,0.00001474319,0.001111373],"genre_scores_gemma":[0.9897498,0.000002865882,0.01016744,0.00002863585,0.000002906912,0.00001628383,0.00000175636,8.602365e-7,0.0000294766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8351993,"threshold_uncertainty_score":0.1054784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03623371557916335,"score_gpt":0.3680599931510121,"score_spread":0.3318262775718487,"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."}}