{"paper_id":"2508.03474","title":"Unravelling the Probabilistic Forest: Arbitrage in Prediction Markets","authors":["Oriol Saguillo","Vahid Ghafouri","Lucianna Kiffer","Guillermo Suarez-Tangil"],"paper_date":"2025-08-05","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.03474v1","page_url":"https://thequant.space/flowcharts/unravelling-the-probabilistic-forest-arbitrage-in-predictio/","scores":{"empirical_rigor":6,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper conducts an empirical arbitrage analysis on Polymarket data, identifying two distinct forms of arbitrage and estimating extracted profit.","quote":"In this paper, we conduct an empirical arbitrage analysis on Polymarket data to answer three key questions: (Q1) What conditions give rise to arbitrage? (Q2) Does arbitrage actually occur on Polymarket?, and (Q3) Has anyone exploited these opportunities?","summary":"Polymarket is a prediction market platform where users can speculate on future events by trading shares tied to specific outcomes, known as conditions. Each market is associated with a set of one or more such conditions. To ensure proper market resolution, the condition set must be exhaustive…","strategy":"Market Rebalancing Arbitrage and Combinatorial Arbitrage"},"assumptions":{"status":"available","items":[{"assumption":"Each market’s condition set is exhaustive and mutually exclusive, so the sum of YES token prices should equal 1.","type":"market","stated":"explicit","quote":"Each market is associated with a set of one or more such conditions. To ensure proper market resolution, the condition set must be exhaustive -- collectively accounting for all possible outcomes -- and mutually exclusive -- only one condition may resolve as true."},{"assumption":"Arbitrage profit is calculated without accounting for any trading fees.","type":"execution","stated":"explicit","quote":"It is important to clarify that we do not take into account the fees because Polymarket currently does not charge per trade executed."},{"assumption":"The LLM can correctly infer logical dependencies between market conditions.","type":"model","stated":"implied","quote":"together with market description data to capture the state space of possible market resolutions to then infer semantic dependency between pairs of"},{"assumption":"Reducing markets to at most four high‑volume conditions plus a catch‑all preserves the essential logical dependencies.","type":"data","stated":"explicit","quote":"We thus pre-process markets with more than 4 conditions and reduce them to 4 or fewer conditions with the most total traded volume (in YES, and NO tokens), and a fifth condition to catch all other outcomes."},{"assumption":"A time window of 950 blocks (≈1 hour) captures the relevant bid matching delay for arbitrage execution.","type":"execution","stated":"explicit","quote":"We set T to 950 blocks (approx. 1 hour) to capture some delay in bids being matched (75% of bids fall within this window – see App. I.1 for the distribution)."}]},"datasets":{"status":"available","items":[{"name":"Polymarket historical bid data","provider":"Polymarket (on‑chain)","kind":"order-book","access":"public","period":"April 1, 2024 to April 1, 2025","universe":null,"quote":"Our data collection efforts span markets that were resolved over the period of one year, from April 1, 2024, to April 1, 2025."},{"name":"On‑chain historical order book data","provider":"Polymarket (Polygon blockchain)","kind":"order-book","access":"public","period":null,"universe":null,"quote":"We use on-chain historical order book data to analyze when these types of arbitrage opportunities have existed, and when they have been executed by users."}],"known":[{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"2024-05 2024-06 2024-07 2024-08 2024-09 2024-10 2024-11 2024-12 2025-01 2025-02 2025-03 0 1 2 3 4 5 6 Sum of Profit (Millions of Dollars) Profit from Market Arbitrage Crypto Culture Economy Politics Sports Technology Twitter 0.00 0.05 0.10 0.15 0.20 0.25 0.30 0.35 Profit per Dolar Figure 11 (Left) The total profit obtained through Rebalancing Arbitrage in NegRisk markets.","mentions":5,"used_in":1}],"sample":{"start":null,"end":null,"market":"Polymarket prediction markets","asset_class":"crypto","frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":"It is important to clarify that we do not take into account the fees because Polymarket currently does not charge per trade executed.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"It is important to clarify that we do not take into account the fees because Polymarket currently does not charge per trade executed.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The authors estimate that about $40 million of profit was extracted from arbitrage on Polymarket.","kind":"performance","quote":"We find a realized estimate of 40 million USD of profit extracted."},{"finding":"Total profit summed across all detected arbitrage strategies amounts to $39,587,585.02 (assuming $1 profit per trade).","kind":"performance","quote":"The combined amount extracted from all strategies presented totals $39,587,585.02, assuming an ε = $1 profit per trade."},{"finding":"Out of 1,578 NegRisk markets, 662 had at least one arbitrage opportunity, averaging about 100 opportunities per market.","kind":"statistical","quote":"In general, we see many more opportunities per market, averaging around 100 per market."},{"finding":"Only about 1 % of estimated U.S. election arbitrage opportunities were actually exploited by users.","kind":"performance","quote":"About 1% of our estimated U.S. election opportunities were exploited by users."},{"finding":"The top arbitrageur generated $2,009,631.76 in profit.","kind":"performance","quote":"The user with the highest profits generated a total of $2,009,631.76 through these strategies."}],"reported_performance":{"strategy":"Market Rebalancing Arbitrage and Combinatorial Arbitrage","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"none","headline_out_of_sample":false}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[{"paper":{"paper_id":"2605.00864","title":"Arbitrage Analysis in Polymarket NBA Markets","paper_date":"2026-04-22","authors":["Guang Cheng","Jiaxin Yang","Haoxuan Zou"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/arbitrage-analysis-in-polymarket-nba-markets/"},"question":"How much profit can be extracted from arbitrage on Polymarket?","this_paper_finding":"The authors estimate that about $40 million of profit was extracted from arbitrage on Polymarket.","other_paper_finding":"Capped profit from single‑market arbitrage totals $210.19 (median yield 11.0% per episode) while theoretical uncapped profit would be $4,418.44.","other_paper_quote":"Assuming a maximum capital deployment of $100 per episode, the aggregate capped profit totaled $210.19","note":"A reports $40 million total arbitrage profit; B reports a capped $210.19 per‑market profit (median 11.0% yield) and a theoretical $4,418.44 uncapped profit.","confidence":0.44}],"compared_with":21,"citations":{"cited_by_in_corpus":6,"by_independent_authors":6,"how_cited":{"used_as_baseline":0,"uses_method_or_data":2,"extends":0,"discusses_findings":1,"mentions":2,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2605.00493","title":"ForesightFlow: An Information Leakage Score Framework for Prediction Markets","paper_date":"2026-05-01","authors":["Maksym Nechepurenko"],"empirical_rigor":9,"page_url":"https://thequant.space/flowcharts/foresightflow-an-information-leakage-score-framework-for-prediction-markets/"},"how":"discusses_findings","quote":"independently documented $40 million of arbitrage and quasi-arbitrage profit from a complementary on-chain measurement."},{"paper":{"paper_id":"2605.00864","title":"Arbitrage Analysis in Polymarket NBA Markets","paper_date":"2026-04-22","authors":["Guang Cheng","Jiaxin Yang","Haoxuan Zou"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/arbitrage-analysis-in-polymarket-nba-markets/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2510.15612","title":"SoK: Market Microstructure for Decentralized Prediction Markets (DePMs)","paper_date":"2025-10-17","authors":["Nahid Rahman","Joseph Al-Chami","Jeremy Clark"],"empirical_rigor":3,"page_url":"https://thequant.space/flowcharts/sok-market-microstructure-for-decentralized-prediction-mark/"},"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":"2026-11-14T17:30:34Z"},"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/"}