{"paper_id":"2306.12806","title":"Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness","authors":["Andrea Coletta","Joseph Jerome","Rahul Savani","Svitlana Vyetrenko"],"paper_date":"2023-06-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.12806v1","page_url":"https://thequant.space/flowcharts/conditional-generators-for-limit-order-book-environments-ex/","scores":{"empirical_rigor":6,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes new LOBGAN models that improve both realism and robustness based on analysis of feature dependence and adversarial strategies.","quote":"Using the insights from our analysis and adversarial strategies, we designed new LOBGAN models that are better in terms of both realism and robustness.","summary":"Limit order books are a fundamental and widespread market mechanism. This paper investigates the use of conditional generative models for order book simulation. For developing a trading agent, this approach has drawn recent attention as an alternative to traditional backtesting due to its ability…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Market replay simulators assume the financial market does not react to the presence of the trading agent being tested.","type":"market","stated":"explicit","quote":"Thus, one implicitly makes the assumption that the financial market does not react to the presence of the trading agent which is being tested.","support":"full"},{"assumption":"The adversarial attacks presented are not considered market manipulation.","type":"other","stated":"explicit","quote":"2 Remark: our adversarial attacks are not “market manipulation”.","support":"full"},{"assumption":"Altering input features may produce unrealistic order‑book and trade combinations, but the CGAN output remains relatively well‑behaved.","type":"model","stated":"explicit","quote":"We note that, in this approach the input to the CGAN after having been altered could correspond to an unrealistic orderbook and historical trade combination.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"LOBSTER","provider":"LOBSTER","kind":"order-book","access":"commercial","period":null,"universe":null,"quote":"Throughout the paper we use LOBGAN along with high-fidelity historical order data from LOBSTER [27].","support":"full","known_id":"lobster"}],"known":[{"id":"lobster","name":"LOBSTER","provider":"LOBSTER","kind":"order-book","access":"commercial","quote":"Throughout the paper we use LOBGAN along with high-fidelity historical order data from LOBSTER [27].","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"l2-book"},"transaction_costs":{"status":"none_found","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"none","rule":"R0b","candidates":{"front_matter":"unclear","evidence_card":"no","evidence_card_quoted":false},"meaning":"no cost treatment was found in the passages the extractor read; that is not evidence that costs are not modeled"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"LOBGAN generates realistic price‑impact paths but shows a greater impact of limit orders over market orders, which is unexpected.","kind":"statistical","quote":"While we find that LOBGAN can generate realistic price impact paths, we also find that the paths show a greater impact of limit orders over market orders, which is unexpected, and was not studied in the earlier papers on LOBGAN.","support":"full"},{"finding":"The third version of LOBGAN (v3) improves realism for volume and spread and shows enhanced robustness to both BookImbalance1 adversarial and market‑making strategies.","kind":"performance","quote":"The figure clearly shows an improvement on real-ism for both volume and spread with respect to the previous attempt (the middle row in Figure 18). As shown in Figures 19 and 20, we can see that LOBGAN v3 improves upon all of the previous versions of LOBGAN in terms of robustness to both the BookImbalance1 adversarial strategy and the market-making strategy.","support":"full"},{"finding":"Adversarial attacks that manipulate features and the model’s mechanism expose weaknesses in LOBGAN’s feature conditioning.","kind":"negative","quote":"As such, we design adversarial attacks to exploit and show weaknesses of such models by manipulating the features and mechanism of the models.","support":"full"},{"finding":"Interactive realism—realistic reactivity to external agents—was explored in depth, demonstrating LOBGAN’s behavior when interacting with various trading agents.","kind":"theoretical","quote":"In Sec-tion 6, we explore interactive realism in depth – for the first time. We analyse LOBGAN’s outputs when it interacts with a range of trading agents.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2303.07393","title":"Many learning agents interacting with an agent-based market model","paper_date":"2023-03-13","authors":["Matthew Dicks","Andrew Paskaramoorthy","Tim Gebbie"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/many-learning-agents-interacting-with-an-agent-based-market-model/"},"question":"Do limit orders reduce price impact in a limit order book?","this_paper_finding":"LOBGAN generates realistic price‑impact paths but shows a greater impact of limit orders over market orders, which is unexpected.","other_paper_finding":"Agents that can use limit orders achieve lower price impact and faster decay of absolute returns.","other_paper_quote":"The ability to use LOs to execute a parent order results in lower price impact and faster decay in the size of absolute returns.","note":"Finding A reports lower price impact with limit orders, while Finding B reports a greater impact of limit orders, contradicting A.","confidence":0.566}],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":23,"by_independent_authors":23,"how_cited":{"used_as_baseline":0,"uses_method_or_data":5,"extends":0,"discusses_findings":0,"mentions":9,"unclassified":9},"independent_papers":[{"paper":{"paper_id":"2509.05107","title":"Painting the market: generative diffusion models for financial limit order book simulation and forecasting","paper_date":"2025-09-05","authors":["Alfred Backhouse","Kang Li","Jakob Foerster","Anisoara Calinescu","Stefan Zohren"],"empirical_rigor":9,"page_url":"https://thequant.space/flowcharts/painting-the-market-generative-diffusion-models-for-financi/"},"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":"2408.12991","title":"Controllable Financial Market Generation with Diffusion Guided Meta Agent","paper_date":"2024-08-23","authors":["Yu-Hao Huang","Chang Xu","Yang Liu","Weiqing Liu","Wu-Jun Li","Jiang Bian"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/controllable-financial-market-generation-with-diffusion-guid/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2503.17909","title":"Financial Wind Tunnel: A Retrieval-Augmented Market Simulator","paper_date":"2025-03-23","authors":["Bokai Cao","Xueyuan Lin","Yiyan Qi","Chengjin Xu","Cehao Yang","Jian Guo"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/financial-wind-tunnel-a-retrieval-augmented-market-simulato/"},"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":2,"extracted_at":"2026-11-14T20:02:26Z"},"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/"}