{"id":"W4414578107","doi":"10.48550/arxiv.2503.08398","title":"OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Relevance (law); Adaptation (eye); Bridge (graph theory); Range (aeronautics); Language model; Labrador Retriever","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002002934,0.001396102,0.001458344,0.0007781535,0.000594941,0.00156202,0.00242746,0.002322962,0.005682775],"category_scores_gemma":[0.007219723,0.0004880122,0.0007473713,0.0006710443,0.0007572871,0.002849691,0.001956591,0.002265933,0.004492944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000750491,"about_ca_system_score_gemma":0.001279155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003695649,"about_ca_topic_score_gemma":0.006840155,"domain_scores_codex":[0.9986879,0.000433169,0.00005159133,0.0004601378,0.000225833,0.0001413807],"domain_scores_gemma":[0.9984182,0.0008217914,0.00007772855,0.0003828101,0.0002119947,0.00008743774],"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":[0.0007982314,0.0006644491,0.001938771,0.0004641235,0.0002045068,0.0004261645,0.0002691847,0.312887,0.02623636,0.00616283,0.03169678,0.6182516],"study_design_scores_gemma":[0.00006631641,0.0001923392,0.0003470837,0.00001515917,0.00003549746,0.0001502556,0.00006269341,0.9791011,0.00881214,0.007351119,0.003837999,0.00002841615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05675884,0.003183976,0.8793621,0.0005984966,0.0002992599,0.0003275725,0.0007488697,0.05320252,0.005518323],"genre_scores_gemma":[0.5232911,0.0005197265,0.458041,0.001291408,0.0002171627,0.0002823398,0.003592399,0.002328651,0.01043624],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005682775,"threshold_uncertainty_score":0.01901072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04396895051009762,"score_gpt":0.2890148634946892,"score_spread":0.2450459129845916,"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."}}