{"id":"W4386988846","doi":"10.3905/jfds.2023.1.138","title":"RIFT: Pretraining and Applications for Representations of Interrelated Financial Time Series","year":2023,"lang":"en","type":"article","venue":"The Journal of Financial Data Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pairwise comparison; Portfolio optimization; Computer science; Portfolio; Autoencoder; Artificial intelligence; Representation (politics); Machine learning; Encoder; Artificial neural network; Econometrics; Finance; Economics","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":[0.02620294,0.00008182831,0.0002479227,0.0004524234,0.0005513378,0.0001099244,0.002938739,0.00003996696,0.00001956857],"category_scores_gemma":[0.0727268,0.00005225063,0.00004767337,0.003450511,0.001132661,0.001424115,0.0007737529,0.0001717666,0.00001016129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001661918,"about_ca_system_score_gemma":0.0007252847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009074983,"about_ca_topic_score_gemma":0.00001217593,"domain_scores_codex":[0.9975279,0.0001906364,0.0008193553,0.0002696207,0.0009663293,0.0002261723],"domain_scores_gemma":[0.9927112,0.004585624,0.0009091059,0.000891261,0.0008182068,0.00008463496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005860227,0.00006086119,0.00310763,0.00002135961,0.00001502864,0.000004794113,0.006440168,0.0008315716,0.02731861,0.01269808,0.04366467,0.9052512],"study_design_scores_gemma":[0.001416837,0.001083864,0.5655499,0.0002822775,0.0001839391,0.0005339676,0.002071352,0.08490521,0.005594541,0.2854667,0.05243416,0.0004773114],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5327064,0.0002278244,0.4587027,0.002748752,0.001290556,0.00108993,0.0007946002,0.00004513107,0.002394035],"genre_scores_gemma":[0.8488462,0.0001437379,0.1483736,0.0001593842,0.0007587333,0.00002940541,0.00002046294,0.00002399575,0.001644431],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9047739,"threshold_uncertainty_score":0.935084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1833950529321575,"score_gpt":0.4569542543097912,"score_spread":0.2735592013776337,"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."}}