{"id":"W4402647202","doi":"10.1007/978-3-031-70242-6_37","title":"CoURAGE: A Framework to Evaluate RAG Systems","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Courage; Computer science; Theology; Philosophy","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":[0.004309275,0.001466135,0.0008172924,0.002053971,0.0008229339,0.004077836,0.002330126,0.001569342,0.01518199],"category_scores_gemma":[0.01576648,0.0003723875,0.0008279904,0.001150287,0.001888901,0.005021888,0.00241774,0.001780017,0.002423842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001351612,"about_ca_system_score_gemma":0.001476117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003367457,"about_ca_topic_score_gemma":0.003223471,"domain_scores_codex":[0.9973112,0.001339503,0.0001091375,0.000269986,0.000773243,0.0001969585],"domain_scores_gemma":[0.9951867,0.003056585,0.0004007358,0.0004453618,0.0006340059,0.0002765406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002493544,0.0001208501,0.001578899,0.0002247605,0.00009987764,0.0001422904,0.0002856208,0.2104885,0.00195211,0.6441998,0.01376514,0.1268928],"study_design_scores_gemma":[0.00003893808,0.0001002071,0.0003194585,0.00004220627,0.00003855839,0.00003916388,0.00009081401,0.7525402,0.001547636,0.2325404,0.01266991,0.00003246496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009306331,0.0004336733,0.9636032,0.0003423488,0.0001361808,0.0001798109,0.0003461736,0.003434253,0.022218],"genre_scores_gemma":[0.3824769,0.0004553948,0.5914787,0.000188447,0.0002406397,0.000681665,0.0007711065,0.001160466,0.02254681],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01518199,"threshold_uncertainty_score":0.05078882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02741885497644407,"score_gpt":0.2844265836925258,"score_spread":0.2570077287160817,"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."}}