{"id":"W4409965009","doi":"10.3390/math13091476","title":"A Generative Adversarial Network-Based Investor Sentiment Indicator: Superior Predictability for the Stock Market","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Predictability; Generative grammar; Stock market; Adversarial system; Stock (firearms); Generative adversarial network; Financial economics; Computer science; Econometrics; Artificial intelligence; Economics; Machine learning; Mathematics; Deep learning; Biology; Statistics; Engineering","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"],"consensus_categories":[],"category_scores_codex":[0.01435103,0.0002660952,0.0005166002,0.0001654439,0.0005716099,0.0002871824,0.001196754,0.0001452561,0.0007923024],"category_scores_gemma":[0.01904105,0.0001617368,0.0003060689,0.000812022,0.0003269631,0.00009392178,0.0003202192,0.00021114,0.00002125468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001615164,"about_ca_system_score_gemma":0.0004854818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005566899,"about_ca_topic_score_gemma":0.00002489219,"domain_scores_codex":[0.9960303,0.0007661919,0.001057591,0.0005762606,0.001119925,0.0004497167],"domain_scores_gemma":[0.9750493,0.02282106,0.0004087945,0.001322627,0.0002883551,0.0001099108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006964433,0.0006783478,0.03507492,0.0003014082,0.000487534,0.000002982481,0.003974209,0.006411339,0.0002083933,0.01077235,0.8784013,0.0629907],"study_design_scores_gemma":[0.001744662,0.0001401146,0.009423041,0.0000925776,0.0002646708,0.000002804625,0.0006537602,0.781116,0.0006105447,0.1285568,0.07707417,0.000320808],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03590731,0.0001920928,0.9517844,0.002239871,0.002032361,0.002693619,0.00009527554,0.0001046102,0.004950515],"genre_scores_gemma":[0.1132696,0.000003612184,0.872179,0.001689786,0.0007456814,0.001247147,0.000009359949,0.00005472398,0.01080108],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8013272,"threshold_uncertainty_score":0.989222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09779007016746331,"score_gpt":0.3917625181176722,"score_spread":0.2939724479502089,"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."}}