{"id":"W4409160206","doi":"10.1007/978-3-031-88711-6_15","title":"Rank-Without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Regional Municipality of Waterloo; University of Waterloo","funders":"","keywords":"Computer science; Rank (graph theory); Open source; Artificial intelligence; Programming language; Natural language processing; Mathematics; Software","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":[0.003208174,0.004201436,0.002727,0.003681847,0.001425065,0.002679325,0.003837582,0.003371573,0.02432188],"category_scores_gemma":[0.01600742,0.001750294,0.002859851,0.002928025,0.0008380549,0.005836786,0.002850414,0.004752222,0.03301566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001181399,"about_ca_system_score_gemma":0.003454144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01046365,"about_ca_topic_score_gemma":0.03949787,"domain_scores_codex":[0.9972535,0.0008283336,0.0001808715,0.0007597191,0.0006495951,0.0003280334],"domain_scores_gemma":[0.9934436,0.003240934,0.0001800995,0.001826255,0.001067043,0.0002420951],"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":[0.0005370517,0.0004188762,0.001271652,0.000522854,0.000394,0.0002680621,0.0001581175,0.05155471,0.006536636,0.006764514,0.2009491,0.7306245],"study_design_scores_gemma":[0.0003896257,0.0002476125,0.0004992284,0.00005649378,0.0001417773,0.0001790053,0.0001036256,0.9404159,0.007257122,0.03285075,0.01777747,0.00008129474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01728471,0.00187355,0.7682508,0.0006615541,0.0009030204,0.0005364853,0.01100097,0.1930232,0.00646572],"genre_scores_gemma":[0.09291013,0.0006499689,0.8330901,0.0006597906,0.0006152025,0.0006953108,0.04413938,0.008994575,0.01824559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02432188,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01984332292328901,"score_gpt":0.2749590694641937,"score_spread":0.2551157465409047,"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."}}