{"id":"W4223996667","doi":"10.48550/arxiv.2204.05979","title":"Discovering material information using hierarchical Reformer model on financial regulatory filings","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mandate; Task (project management); Financial market; Computer science; Construct (python library); Machine learning; Finance; Artificial intelligence; Investment (military); Business; Economics","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":[0.003296096,0.0004195219,0.0005758405,0.0009804359,0.0005713528,0.0003564962,0.001781812,0.000395853,0.0006555763],"category_scores_gemma":[0.002663073,0.0004195764,0.0003890338,0.000866803,0.0002013266,0.001106665,0.003535175,0.001294469,0.00004783299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008933648,"about_ca_system_score_gemma":0.0007721494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001456229,"about_ca_topic_score_gemma":0.00001153374,"domain_scores_codex":[0.9962839,0.000585665,0.0007653514,0.001088052,0.0007876771,0.0004893669],"domain_scores_gemma":[0.9966559,0.0006155978,0.0008512725,0.001471211,0.0002151313,0.0001909097],"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":[0.0007213231,0.00003158193,0.0006703851,0.00002721317,0.00001782589,0.0000317654,0.0003630895,0.9785361,0.00007208071,0.01646967,0.0004308748,0.002628047],"study_design_scores_gemma":[0.0003675084,0.00006220074,0.00232617,0.00006808565,0.0000447909,0.000004645447,0.0001586489,0.8719696,0.00013644,0.123154,0.001226644,0.0004812748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8255501,0.000002107739,0.1655675,0.0000300161,0.00187212,0.0003113137,0.0002197895,0.0001001197,0.006346966],"genre_scores_gemma":[0.9900097,0.000005738956,0.007845069,0.0001482248,0.0001959655,0.000002374214,0.00005839357,0.00002976124,0.001704788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1644596,"threshold_uncertainty_score":0.9998256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2126320741856788,"score_gpt":0.2924735340868103,"score_spread":0.07984145990113145,"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."}}