{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001738468,0.0006518309,0.0006722755,0.001129153,0.0002097075,0.001847281,0.005018922,0.0004680974,0.00002065731],"category_scores_gemma":[0.0001805743,0.0005777461,0.000159582,0.0009965061,0.000244834,0.0004241315,0.002718241,0.001493805,0.0005937876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005490846,"about_ca_system_score_gemma":0.0006957491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004137951,"about_ca_topic_score_gemma":0.00001827824,"domain_scores_codex":[0.9940926,0.00004032932,0.0006975008,0.002473305,0.001799744,0.0008965465],"domain_scores_gemma":[0.9960738,0.0005796006,0.0001775905,0.002512638,0.0003111519,0.0003451499],"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":[0.000003047932,0.00001089666,0.000005829122,0.000125863,0.00001914983,0.000290454,0.001551647,0.41276,0.00004023013,0.3064481,0.00008745987,0.2786574],"study_design_scores_gemma":[0.00006305025,0.00007796141,0.000004037346,0.001349068,0.000009368422,0.00008429433,1.700887e-7,0.7002108,0.000059421,0.2934542,0.004170268,0.0005173249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004805729,0.001933422,0.9794727,0.002468456,0.01001567,0.0007166126,0.000005312864,0.0004262829,0.004913463],"genre_scores_gemma":[0.1515496,0.00004050645,0.8389505,0.003374299,0.002146467,0.0000510115,0.000002270247,0.00009698993,0.003788393],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2874509,"threshold_uncertainty_score":0.9996674,"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."}}