{"id":"W4412378237","doi":"10.1145/3726302.3730244","title":"Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Universitas Brawijaya","keywords":"Computer science; Conformal map; Quality (philosophy); Information retrieval; Artificial intelligence; Mathematics; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.002161729,0.00009838139,0.000137048,0.00008132746,0.0001914148,0.0001345291,0.0003192248,0.00006603249,0.00006450144],"category_scores_gemma":[0.0001831984,0.00009158999,0.00006852981,0.0001477276,0.00002404123,0.0004177022,0.0001272093,0.00007672228,0.000005851466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001631315,"about_ca_system_score_gemma":0.0003344291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002492292,"about_ca_topic_score_gemma":0.000008896049,"domain_scores_codex":[0.9985649,0.0002261064,0.0004156239,0.0003228782,0.000283561,0.0001869534],"domain_scores_gemma":[0.9988265,0.0003943946,0.00008404524,0.0004257864,0.0002198252,0.00004942338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002443649,0.00009161435,0.0002635581,0.00002718221,0.00004879773,9.058466e-7,0.0001427909,0.001145647,0.04127519,0.9423677,0.003369054,0.01102322],"study_design_scores_gemma":[0.0009576336,0.00005630778,0.01055579,0.000004802914,0.000004878265,0.000001277888,0.00002528298,0.9458652,0.02405523,0.01408852,0.004247709,0.0001373763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08035575,0.000005675092,0.9129591,0.00447502,0.0003899792,0.0003428535,0.00001959109,0.0001248321,0.001327219],"genre_scores_gemma":[0.8386229,5.27376e-7,0.1566629,0.002422479,0.00003843683,0.00002893542,0.00006547796,0.000002285063,0.00215597],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9447196,"threshold_uncertainty_score":0.3734931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08704555234092608,"score_gpt":0.3904801283648089,"score_spread":0.3034345760238829,"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."}}