{"paper_id":"2601.10143","title":"History Is Not Enough: An Adaptive Dataflow System for Financial Time-Series Synthesis","authors":["Haochong Xia","Yao Long Teng","Regan Tan","Molei Qin","Xinrun Wang","Bo An"],"paper_date":"2026-01-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2601.10143v1","page_url":"https://thequant.space/flowcharts/history-is-not-enough-an-adaptive-dataflow-system-for-finan/","scores":{"empirical_rigor":7,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a drift‑aware adaptive dataflow system that unifies financial data synthesis, augmentation scheduling, and learning‑based feedback control within a single workflow architecture.","quote":"We present a drift‑aware adaptive dataflow system that unifies financial data synthesis, augmentation scheduling, and learning‑based feedback control within a single workflow architecture.","summary":"In quantitative finance, the gap between training and real-world performance-driven by concept drift and distributional non-stationarity-remains a critical obstacle for building reliable data-driven systems. Models trained on static historical data often overfit, resulting in poor generalization in…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The data used for machine‑learning models is independent and identically distributed (i.i.d.).","type":"data","stated":"explicit","quote":"A fundamental assumption in applying machine learning techniques is that the data is independent and identically distributed (i.i.d.)."},{"assumption":"Training/validation/test splits follow a chronological 0.6/0.2/0.2 ratio.","type":"data","stated":"explicit","quote":"splitting all samples from 2000 to (2010 + k) into Train/Validation/Test subsets with ratios of 0.6/0.2/0.2."},{"assumption":"The reinforcement‑learning trading environment applies a proportional transaction cost of 0.1% per trade.","type":"execution","stated":"explicit","quote":"A proportional transaction cost c = 10−3 applies to traded notional."},{"assumption":"Validation loss Lval is used as the objective to estimate generalization ability.","type":"model","stated":"explicit","quote":"where Lval is the validation loss, and Dvalid is the validation dataset."}]},"datasets":{"status":"available","items":[{"name":"Stocks (daily)","provider":null,"kind":"market-prices","access":"unknown","period":"2000–2024","universe":null,"quote":"For the stocks dataset (daily, 2000–2024), we adopt a rolling-year protocol where each fold incrementally extends the training horizon by one year"},{"name":"Crypto (hourly)","provider":null,"kind":"market-prices","access":"unknown","period":"2023‑09‑27 to 2025‑09‑26","universe":null,"quote":"For the crypto dataset (hourly, 2023-09-27 to 2025-09-26), we apply a higher-frequency rolling protocol, expanding the training horizon by one month per fold"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"partial","evidence_card":"yes","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"c = 10^{-3} proportional transaction cost per traded notional","card_quote":"A proportional transaction cost c = 10−3 applies to traded notional.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Across both markets, the validation distribution is statistically closer to the test distribution than the historical training distribution (Dist(Val, Test) < Dist(Train, Test)).","kind":"statistical","quote":"the results in Table I consistently show that Dist(Val, Test) < Dist(Train, Test), confirming that the validation window statistically resembles the near-future test distribution more closely than the historical training data."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":4,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:15:54Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}