{"id":"W7128867818","doi":"","title":"Multi-Agentic Retriever (MAR): Redefining Information Retriever in the Era of AI agents","year":2025,"lang":"es","type":"dissertation","venue":"Digital Library of the University of Innsbruck (University of Innsbruck)","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Flexibility (engineering); Key (lock); Component (thermodynamics); Labrador Retriever; Isolation (microbiology); Plan (archaeology); Conjunction (astronomy)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005438284,0.000486749,0.0009667595,0.0009306195,0.0005174002,0.0001283468,0.00473972,0.0005676197,0.0001281122],"category_scores_gemma":[0.0002302399,0.0005024429,0.0006823816,0.003170931,0.0006418623,0.006531085,0.0013622,0.001194751,0.00001716365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009981709,"about_ca_system_score_gemma":0.001070761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001172725,"about_ca_topic_score_gemma":0.00005409835,"domain_scores_codex":[0.9968014,0.0003767719,0.0008407013,0.0005231074,0.001020641,0.0004373815],"domain_scores_gemma":[0.9954106,0.0005362775,0.002293203,0.001185251,0.0004750032,0.00009963138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007776425,0.002776653,0.5309782,0.01474729,0.002662142,0.0002700871,0.2577317,0.01101846,0.0007936478,0.02700267,0.08107221,0.06317049],"study_design_scores_gemma":[0.01075544,0.001383201,0.7684014,0.02461352,0.001023731,0.00002481737,0.0946585,0.05407091,0.004166838,0.002446425,0.0358645,0.002590704],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9734858,0.0003363264,0.007067643,0.001925428,0.000630606,0.0009855855,0.001865923,0.00008333192,0.01361938],"genre_scores_gemma":[0.9879887,0.0001976491,0.006587671,0.0001789759,0.0000118119,7.922765e-8,0.0009494228,0.00001763775,0.004068046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2374232,"threshold_uncertainty_score":0.9997427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01090199126935825,"score_gpt":0.1867431558238747,"score_spread":0.1758411645545165,"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."}}