{"paper_id":"2508.02247","title":"ByteGen: A Tokenizer-Free Generative Model for Orderbook Events in Byte Space","authors":["Yang Li","Zhi Chen"],"paper_date":"2025-08-04","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2508.02247v2","page_url":"https://thequant.space/flowcharts/bytegen-a-tokenizer-free-generative-model-for-orderbook-eve/","scores":{"empirical_rigor":8,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes ByteGen, a generative model that learns directly from raw byte streams of limit order book events, eliminating feature engineering and tokenization.","quote":"we introduce ByteGen, a novel generative model that operates directly on the raw byte streams of LOB events.","summary":"Generative modeling of high-frequency limit order book (LOB) dynamics is a critical yet unsolved challenge in quantitative finance, essential for robust market simulation and strategy backtesting. Existing approaches are often constrained by simplifying stochastic assumptions or, in the case of…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The 32‑byte packed binary format represents market messages without information loss.","type":"data","stated":"implied","quote":"design a compact and efficient 32-byte packed binary format to represent market messages without information loss."},{"assumption":"The H‑Net architecture can discover the inherent structure of market messages without predefined rules.","type":"model","stated":"implied","quote":"the H‑Net architecture, a hybrid Mamba‑Transformer model that uses a dynamic chunking mechanism to discover the inherent structure of market messages without predefined rules."},{"assumption":"Financial markets are non‑stationary, so a fixed binning strategy may become inappropriate under regime changes.","type":"market","stated":"explicit","quote":"Financial markets are non‑stationary."},{"assumption":"A fixed binning strategy that is appropriate for a low‑volatility regime will be entirely inappropriate during a high‑volatility period.","type":"model","stated":"explicit","quote":"A fixed binning strategy that is appropriate for a low‑volatility regime will be entirely inappropriate during a high‑volatility period."}]},"datasets":{"status":"available","items":[{"name":"CME Bitcoin futures (BTCX4) Level 3 (Market‑By‑Order) data","provider":"CME Group via Databento","kind":"order-book","access":"commercial","period":"November 11‑15, 2024","universe":"single BTCX4 futures contract","quote":"We evaluate ByteGen on CME Bitcoin futures (BTCX4) Level 3 (Market‑By‑Order) data from CME Group via Databento."},{"name":"Training dataset","provider":null,"kind":"order-book","access":"unknown","period":"November 11‑15, 2024 (5 trading days)","universe":null,"quote":"Our training dataset spans November 11‑15, 2024 (5 trading days) and contains 34.2 million order‑book messages totaling 1.02 GB in our packed 32-byte format."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"l2-book"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"The model captures heavy‑tailed price returns but with slightly lower volatility.","kind":"statistical","quote":"The model captures the heavy‑tailed nature of price movements, though with slightly lower volatility (12.6 bps vs 16.9 bps in real data)."},{"finding":"Event type distribution is biased: more cancel orders (47% vs 31%) and fewer trades than observed.","kind":"performance","quote":"event type frequencies show systematic biases, with the model generating more cancel orders (47% vs 31%) and fewer trades than observed in real data."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":11,"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":"2026-11-14T17:30:43Z"},"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/"}