{"id":"W4409167231","doi":"10.1007/978-3-031-88708-6_3","title":"Is Relevance Propagated from Retriever to Generator in RAG?","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Relevance (law); Generator (circuit theory); Labrador Retriever; Medicine; Physics; Political science; Law; Pathology","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":[0.005093607,0.0009815679,0.001472078,0.003157518,0.001434524,0.006322133,0.002448935,0.002529223,0.01817418],"category_scores_gemma":[0.0318363,0.001320378,0.0009822232,0.00213413,0.001655026,0.01591891,0.002564061,0.002532354,0.01358803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001888668,"about_ca_system_score_gemma":0.001821515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004547532,"about_ca_topic_score_gemma":0.003103384,"domain_scores_codex":[0.9943896,0.001496279,0.0002847231,0.001344436,0.001795254,0.0006896785],"domain_scores_gemma":[0.9840919,0.007163326,0.0006877075,0.004375385,0.00302243,0.0006592897],"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":[0.002826368,0.0005548948,0.02497008,0.001715809,0.0004681679,0.002215589,0.004673999,0.009087468,0.1229016,0.1284224,0.1223601,0.5798035],"study_design_scores_gemma":[0.0005145865,0.001023794,0.04073134,0.0004018281,0.001358243,0.00412679,0.002817977,0.1556145,0.1863295,0.4040999,0.2023725,0.0006090508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3273553,0.008237931,0.4775711,0.0164806,0.003155694,0.0007404228,0.007971238,0.04822545,0.1102622],"genre_scores_gemma":[0.8929616,0.001654905,0.05443299,0.001390256,0.001633387,0.00008957017,0.005498135,0.005480211,0.03685905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01817418,"threshold_uncertainty_score":0.06079865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01878913682042273,"score_gpt":0.2455350456091588,"score_spread":0.2267459087887361,"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."}}