{"id":"W4410082490","doi":"10.20944/preprints202505.0168.v1","title":"Critical Analysis on Anomaly Detection in High-Frequency Financial Data Using Deep Learning for Options","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Anomaly detection; Anomaly (physics); Finance; Business; Computer science; Artificial intelligence; 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"],"consensus_categories":[],"category_scores_codex":[0.0192141,0.0004838172,0.001203021,0.002920858,0.0005311596,0.0002332081,0.003303978,0.000693938,0.0005583448],"category_scores_gemma":[0.1982815,0.0005000015,0.0005401065,0.003316407,0.0001859057,0.0003761738,0.005939593,0.001819306,0.0001004225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005084169,"about_ca_system_score_gemma":0.0005384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001222279,"about_ca_topic_score_gemma":0.001449074,"domain_scores_codex":[0.9906654,0.002334699,0.00179763,0.003232768,0.001252448,0.000717029],"domain_scores_gemma":[0.983402,0.01042751,0.0007148911,0.004403679,0.0008802235,0.0001717367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002634121,0.0002122441,0.760662,0.00009093974,0.000245151,0.0000149636,0.0002918933,0.176728,0.001242131,0.001761327,0.000007553006,0.05848044],"study_design_scores_gemma":[0.0002996757,0.00003031714,0.6665495,0.000157611,0.0005933883,0.000003034306,0.00006959432,0.2787466,0.001038111,0.05183018,0.0002443738,0.0004376253],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5818935,0.00005178412,0.4141632,0.0001543177,0.001397142,0.0005998101,0.0001176408,0.00009553196,0.001527044],"genre_scores_gemma":[0.9235808,0.00001388613,0.07528278,0.00005498825,0.0002806722,0.0001952594,0.00009290387,0.00002798248,0.0004707752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3416872,"threshold_uncertainty_score":0.9997452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.407783743745856,"score_gpt":0.5104097388210448,"score_spread":0.1026259950751888,"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."}}