{"paper_id":"2309.00638","title":"Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network","authors":["Peer Nagy","Sascha Frey","Silvia Sapora","Kang Li","Anisoara Calinescu","Stefan Zohren","Jakob Foerster"],"paper_date":"2023-08-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.00638v1","page_url":"https://thequant.space/flowcharts/generative-ai-for-end-to-end-limit-order-book-modelling-a-t/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the first end-to-end autoregressive generative model that generates tokenized limit order book (LOB) messages.","quote":"we propose the first end-to-end autoregressive generative model that generates tokenized limit order book (LOB) messages.","summary":"Developing a generative model of realistic order flow in financial markets is a challenging open problem, with numerous applications for market participants. Addressing this, we propose the first end-to-end autoregressive generative model that generates tokenized limit order book (LOB) messages.…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Data is limited to regular NASDAQ trading times on working days between 09:30 and 16:00 US East Coast time.","type":"market","stated":"implied","quote":"We only use data during regular NASDAQ trading times, on working days between 09:30 and 16:00 US East Coast time."},{"assumption":"Only the first four LOBSTER message types are used, ignoring hidden orders and trading halts.","type":"data","stated":"implied","quote":"we only use the first 4 types, ignoring hidden orders, which do not affect the visible dynamics of the LOB, and trading halts."},{"assumption":"Prices are truncated to the range [-999, 999] ticks around the mid-price and order sizes to a maximum of 9999, affecting less than 0.1% of the data.","type":"data","stated":"implied","quote":"In practice, these thresholds affect less than 0.1% of the data."}]},"datasets":{"status":"available","items":[{"name":"LOBSTER","provider":"LOBSTER","kind":"order-book","access":"unknown","period":null,"universe":"NASDAQ equity LOBs (e.g., GOOG, INTC)","quote":"Using LOBSTER data of NASDAQ equity LOBs","known_id":"lobster"}],"known":[{"id":"lobster","name":"LOBSTER","provider":"LOBSTER","kind":"order-book","access":"commercial","quote":"Using LOBSTER data of NASDAQ equity LOBs, we develop a custom tokenizer for message data, converting groups of successive digits to tokens, similar to tokenization in large language models.","mentions":4,"used_in":3}],"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":"forecast-accuracy","findings":[{"finding":"The model achieves per-token perplexity of 3.63 (std.err. 0.0047) for GOOG and 4.04 (std.err. 0.0043) for INTC.","kind":"performance","quote":"Calculating overall per-token perplexity results in a score of 3.63 (std.err. 0.0047) for GOOG and 4.04 (std.err. 0.0043) for INTC."},{"finding":"Generated mid-price returns show a Pearson correlation of approximately 0.1 for GOOG and 0.2 for INTC, remaining statistically significant up to 80–100 messages ahead.","kind":"predictive-accuracy","quote":"Figure 8 shows a sustained positive correlation for both GOOG (𝜌≈0.1) and INTC (𝜌≈0.2). For INTC, the stock with less liquidity, correlations remain statistically significant at least 100 messages into the future."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"citations":{"cited_by_in_corpus":40,"by_independent_authors":35,"how_cited":{"used_as_baseline":1,"uses_method_or_data":5,"extends":0,"discusses_findings":0,"mentions":14,"unclassified":20},"independent_papers":[{"paper":{"paper_id":"2602.03776","title":"DiffLOB: Diffusion Models for Counterfactual Generation in Limit Order Books","paper_date":"2026-02-03","authors":["Zhuohan Wang","Carmine Ventre"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/difflob-diffusion-models-for-counterfactual-generation-in-limit-order-books/"},"how":"used_as_baseline","quote":null},{"paper":{"paper_id":"2405.10654","title":"Microstructure Modes -- Disentangling the Joint Dynamics of Prices & Order Flow","paper_date":"2024-05-17","authors":["Salma Elomari-Kessab","Guillaume Maitrier","Julius Bonart","Jean-Philippe Bouchaud"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/microstructure-modes-disentangling-the-joint-dynamics/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2409.06514","title":"Limit Order Book Simulation and Trade Evaluation with $K$-Nearest-Neighbor Resampling","paper_date":"2024-09-10","authors":["Michael Giegrich","Roel Oomen","Christoph Reisinger"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/limit-order-book-simulation-and-trade-evaluation-with-k-ne/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2402.17359","title":"Limit Order Book Simulations: A Review","paper_date":"2024-02-27","authors":["Konark Jain","Nick Firoozye","Jonathan Kochems","Philip Treleaven"],"empirical_rigor":7,"page_url":"https://thequant.space/flowcharts/limit-order-book-simulations-a-review/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2411.16585","title":"MarketGPT: Developing a Pre-trained transformer (GPT) for Modeling Financial Time Series","paper_date":"2024-11-25","authors":["Aaron Wheeler","Jeffrey D. Varner"],"empirical_rigor":7,"page_url":"https://thequant.space/flowcharts/marketgpt-developing-a-pre-trained-transformer-gpt-for-mo/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2509.00982","title":"Prospects of Imitating Trading Agents in the Stock Market","paper_date":"2025-08-31","authors":["Mateusz Wilinski","Juho Kanniainen"],"empirical_rigor":2.5,"page_url":"https://thequant.space/flowcharts/prospects-of-imitating-trading-agents-in-the-stock-market/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T18:22:55Z"},"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/"}