{"id":"W7160315630","doi":"10.1109/aixb65684.2025.00015","title":"AI-FINALYST: Multi-Agentic Debating Framework with Confidence-Weighting for Investment Decisions","year":2025,"lang":"","type":"article","venue":"","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Investment (military); Investment decisions; Context (archaeology); Government (linguistics); Work (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":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00391295,0.0006511569,0.001011205,0.001190724,0.002009822,0.001916648,0.001366043,0.0004966258,0.001127933],"category_scores_gemma":[0.01407055,0.0004578149,0.0004391145,0.004572059,0.0003041209,0.0009220428,0.0003614679,0.0005736543,0.0002133699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001549283,"about_ca_system_score_gemma":0.001326145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001509488,"about_ca_topic_score_gemma":0.0002589728,"domain_scores_codex":[0.9925579,0.0003783484,0.00261818,0.001717189,0.001702221,0.001026148],"domain_scores_gemma":[0.9843318,0.0106163,0.001011713,0.001555138,0.00205425,0.0004307285],"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":[0.0006811937,0.0009705967,0.04829633,0.0000687856,0.0007170101,0.00004494369,0.004958747,0.08153415,0.0001594995,0.6450846,0.02840891,0.1890753],"study_design_scores_gemma":[0.00255104,0.0004274074,0.003400485,0.001999898,0.0006148382,0.00001287414,0.005352931,0.8081945,0.001496372,0.127341,0.04775122,0.000857397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008338558,0.001497459,0.974329,0.004238681,0.001526903,0.001994994,0.00002354967,0.00009778389,0.007953097],"genre_scores_gemma":[0.4251866,0.001092889,0.5376814,0.008078638,0.0001286166,0.0001933196,0.00001706684,0.00003964143,0.02758184],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7266604,"threshold_uncertainty_score":0.9997873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.104689803016715,"score_gpt":0.421389742985868,"score_spread":0.3166999399691529,"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."}}