{"id":"W4416749873","doi":"10.1109/iros60139.2025.11245837","title":"RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Bridging (networking); Feature (linguistics); Domain (mathematical analysis); Bridge (graph theory); Key (lock); Generalization; Feature extraction; Limiting; Advanced driver assistance systems","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001731459,0.0007198089,0.0008260682,0.0008583801,0.000768379,0.0001616938,0.000893626,0.0006046086,0.0003636608],"category_scores_gemma":[0.000197018,0.0005911304,0.0001490089,0.002980968,0.0002966839,0.0002602181,0.0005327686,0.002551568,0.0001477852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001049046,"about_ca_system_score_gemma":0.0003373142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004566839,"about_ca_topic_score_gemma":0.0009492246,"domain_scores_codex":[0.9958647,0.0002908823,0.001104332,0.000954137,0.0003157679,0.00147021],"domain_scores_gemma":[0.9980637,0.000484355,0.0001693125,0.001045147,0.00007998323,0.0001575307],"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":[0.0008657022,0.0002850218,0.1840712,0.0004341025,0.001115828,0.0004244736,0.006493959,0.6435635,0.01396,0.07237082,0.001342619,0.07507278],"study_design_scores_gemma":[0.006515948,0.0008031805,0.2549567,0.003374163,0.0003423876,0.00008327476,0.009617111,0.6742597,0.01551926,0.003083631,0.02859756,0.002847155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7849776,0.0005080511,0.1079525,0.007784899,0.0004280612,0.001377476,0.000002800869,0.00181348,0.09515515],"genre_scores_gemma":[0.984807,0.0003786793,0.002472914,0.0003686727,0.00007246152,0.00005268853,0.000006645189,0.0001048872,0.01173601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1998295,"threshold_uncertainty_score":0.9997496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005302823044906852,"score_gpt":0.2210648261789303,"score_spread":0.2157620031340235,"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."}}