{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004252698,0.001317909,0.00174417,0.0009128737,0.0008056083,0.002042611,0.002811908,0.002314019,0.006261011],"category_scores_gemma":[0.01206035,0.0007979129,0.001285692,0.0006904911,0.00115278,0.002629277,0.002204997,0.003079458,0.0008062933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001484462,"about_ca_system_score_gemma":0.00198002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0101423,"about_ca_topic_score_gemma":0.01084322,"domain_scores_codex":[0.9982967,0.0008304105,0.0000896893,0.000258273,0.0003200196,0.0002048637],"domain_scores_gemma":[0.9939764,0.00444351,0.0004716358,0.0002278813,0.0006007205,0.0002798874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001117265,0.00005767335,0.0008240981,0.00007068551,0.00007363081,0.0001030897,0.0001118945,0.9329528,0.000454555,0.03908052,0.001355622,0.02480365],"study_design_scores_gemma":[0.000007074007,0.000008962779,0.00002158637,0.000003271653,0.000003868588,0.000004836515,0.000005011904,0.9913031,0.0000506154,0.008342315,0.0002463058,0.000003157759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01084326,0.0002803505,0.984925,0.0004540076,0.00006591732,0.00006612283,0.0001396374,0.0005539922,0.002671776],"genre_scores_gemma":[0.6153402,0.0002977497,0.37673,0.0004842463,0.0001706246,0.0004073914,0.0004382822,0.0002087991,0.00592262],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0101423,"threshold_uncertainty_score":0.02249068,"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."}}