{"paper_id":"2508.02758","title":"CTBench: Cryptocurrency Time Series Generation Benchmark","authors":["Yihao Ang","Qiang Wang","Qiang Huang","Yifan Bao","Xinyu Xi","Anthony K. H. Tung","Chen Jin","Zhiyong Huang"],"paper_date":"2025-08-03","paper_type":"dataset-benchmark","paper_url":"https://arxiv.org/pdf/2508.02758v1","page_url":"https://thequant.space/flowcharts/ctbench-cryptocurrency-time-series-generation-benchmark/","scores":{"empirical_rigor":6,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes CTBench, a comprehensive benchmark for cryptocurrency time series generation, including a curated dataset and dual-task evaluation framework.","quote":"To address these gaps, we introduce CTBench, the first comprehensive TSG benchmark tailored for the cryptocurrency domain.","summary":"Synthetic time series are essential tools for data augmentation, stress testing, and algorithmic prototyping in quantitative finance. However, in cryptocurrency markets, characterized by 24/7 trading, extreme volatility, and rapid regime shifts, existing Time Series Generation (TSG) methods and…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Cryptocurrency markets operate continuously 24/7 with extreme volatility and irregular liquidity.","type":"market","stated":"explicit","quote":"However, in cryptocurrency markets, characterized by 24/7 trading, extreme volatility, and rapid regime shifts, existing Time Series Generation (TSG) methods and benchmarks often fall short"},{"assumption":"Residuals between real returns and reconstructed returns follow mean‑reverting dynamics for the Statistical Arbitrage task.","type":"statistical","stated":"explicit","quote":"In this task, residuals between real 𝑹train and reconstructed returns ˆ𝑹train are assumed to follow mean-reverting dynamics."},{"assumption":"Trading strategies are evaluated under two fee regimes: zero fee and a flat 0.03% fee.","type":"execution","stated":"explicit","quote":"Zero Trading Fee 0.03% Trading Fee"}]},"datasets":{"status":"available","items":[{"name":"Crypto-Centric Datasets","provider":"Binance exchange","kind":"market-prices","access":"public","period":"January 2020 to December 2024","universe":"452 cryptocurrencies (spot pairs against USDT)","quote":"Hourly 24/7 OHLC data from 452 cryptocurrencies, curated and processed via a standardized pipeline for consistency and reliability.","known_id":"binance"}],"known":[{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"We construct our datasets using historical hourly data for all spot trading pairs listed on the Binance exchange [6].","mentions":1,"used_in":1}],"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":"0.03% trading fee (flat fee) used in evaluation alongside a zero‑fee baseline","card_quote":"Zero Trading Fee 0.03% Trading Fee","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Diffusion‑TS achieves the highest predictive accuracy in the 2021 bull market but yields a negative CAGR and low Sharpe, indicating an accuracy‑alpha gap.","kind":"performance","quote":"its negative CAGR and low Sharpe ratio highlight an accuracy–alpha gap"},{"finding":"TimeVAE provides a balanced trade‑off, delivering solid forecasting accuracy together with robust returns.","kind":"performance","quote":"TimeVAE strikes a compelling balance, delivering solid forecasting accuracy and robust returns"},{"finding":"COSCI‑GAN produces promising CAGRs and Sharpe ratios above five under trend‑sensitive strategies.","kind":"performance","quote":"COSCI-GAN thrives under trend‑sensitive strategies such as LOTQ and PW, producing promising CAGRs and Sharpe ratios above five"},{"finding":"Models with smoother residual signals (e.g., TimeVAE, Diffusion‑TS) exhibit smaller rank erosion when a 0.03% fee is introduced, suggesting lower turnover.","kind":"statistical","quote":"smoother models like TimeVAE and Diffusion-TS show smaller rank erosion"},{"finding":"LS4 shows strong fee resilience, compounding almost monotonically in the Statistical Arbitrage task, especially during regime shifts.","kind":"performance","quote":"LS4 compounds almost monotonically, highlighting its superior fee resilience"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":36,"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":"2026-11-14T17:30:42Z"},"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/"}