{"id":"W4412877219","doi":"10.1145/3711896.3737849","title":"The 4th Workshop on AI Agent for Information Retrieval: Generating and Ranking","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Lawrence Berkeley National Laboratory; University of California, San Diego; University of Illinois at Urbana-Champaign; University of Technology Sydney; Arizona State University; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; University of Illinois at Chicago; Tencent; Georgia Institute of Technology; Institute for Catastrophic Loss Reduction; National Science Foundation","keywords":"Ranking (information retrieval); Computer science; Information retrieval; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003089042,0.00004212866,0.00003640102,0.00003147949,0.0004480429,0.0005866241,0.0002418101,0.00001743915,4.008794e-7],"category_scores_gemma":[0.0000885526,0.00002758204,0.0000132238,0.0001971223,0.00001203037,0.0003359801,0.0001036005,0.00004546566,0.000003266017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001189675,"about_ca_system_score_gemma":0.00002353419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004130326,"about_ca_topic_score_gemma":0.000002941936,"domain_scores_codex":[0.9996157,0.000007547092,0.0001200297,0.00009581698,0.00006949676,0.00009146932],"domain_scores_gemma":[0.9994467,0.0002281047,0.00003179786,0.0002359903,0.00004418205,0.00001321084],"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":[0.000001684037,0.000002863589,0.000003605753,0.0000030875,0.000003601572,1.584263e-8,0.0001102731,0.0000768932,0.00002721599,0.2711304,0.01195376,0.7166866],"study_design_scores_gemma":[0.0001322416,0.000009848623,0.0001022548,0.00001848453,0.000002075412,3.28316e-7,0.00006367686,0.7934321,0.0003969363,0.001327406,0.2044743,0.00004031933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008241449,0.00004626542,0.9900966,0.006374823,0.0001342155,0.0001745365,0.000002271501,0.00005777872,0.002289311],"genre_scores_gemma":[0.09232257,0.0002856521,0.8794255,0.02198529,0.000183078,0.0002268372,0.00005051438,0.000008686542,0.005511832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7933552,"threshold_uncertainty_score":0.565683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0178067433191934,"score_gpt":0.2906828532696844,"score_spread":0.272876109950491,"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."}}