{"paper_id":"2610.04959","title":"AlphaPADI: Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete Diffusion","authors":["Yanzheng Jin","Pengyang Shao","Yunshan Ma","Haowen Pan","Naixin Zhai","Chen-Hui Song","Fei Shen","Kenji Kawaguchi"],"paper_date":"2026-10-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2610.04959","page_url":"https://thequant.space/flowcharts/alphapadi-formulaic-alpha-discovery-via-pool-aware-hierarchical-discrete/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes AlphaPADI, a framework for formulaic alpha discovery that treats the alpha pool as the common unit of generation, evaluation, and learning.","quote":"we introduce AlphaPADI (Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete Diffusion)","summary":"Formulaic alpha discovery seeks symbolic expressions that predict cross-sectional asset returns. In deployment, multiple formulas are combined into an alpha pool, where each formula is valued through the complementary information it contributes to joint predictive performance. While Reinforcement…","strategy":"AlphaPADI"},"assumptions":{"status":"available","items":[{"assumption":"Pool combination is performed with a ridge combiner fitted once on the training period and then frozen for validation and testing.","type":"model","stated":"implied","quote":"We evaluate every pool, including those returned by the baselines, with the ridge combiner in Eq. 3, fitted once on the training period and frozen during validation and testing."},{"assumption":"Data are split chronologically into training (2016‑01‑01–2020‑12‑31), validation (2021‑01‑01–2022‑12‑31), and testing (2023‑01‑01–2025‑12‑31).","type":"data","stated":"implied","quote":"three universes share a chronological split: 2016-01-01–2020-12-31 for training, 2021-01-01–2022-12-31 for validation, and 2023-01-01–2025-12-31 for testing."},{"assumption":"Trading costs are not accounted for in the reported performance results.","type":"execution","stated":"implied","quote":"Deploying a discovered strategy would require further assessment of execution costs and financial risk."}]},"datasets":{"status":"available","items":[{"name":"CSI300","provider":"Qlib","kind":"market-prices","access":"public","period":"2016-01-01 to 2025-12-31","universe":"large‑cap Chinese equities","quote":"Datasets. We evaluate CSI300, CSI500, and S&P500, representing large‑cap Chinese, mid‑cap Chinese, and large‑cap U.S. equities, respectively.","known_id":"qlib"},{"name":"CSI500","provider":"Qlib","kind":"market-prices","access":"public","period":"2016-01-01 to 2025-12-31","universe":"mid‑cap Chinese equities","quote":"Datasets. We evaluate CSI300, CSI500, and S&P500, representing large‑cap Chinese, mid‑cap Chinese, and large‑cap U.S. equities, respectively.","known_id":"qlib"},{"name":"S&P500","provider":"Qlib","kind":"market-prices","access":"public","period":"2016-01-01 to 2025-12-31","universe":"large‑cap U.S. equities","quote":"Datasets. We evaluate CSI300, CSI500, and S&P500, representing large‑cap Chinese, mid‑cap Chinese, and large‑cap U.S. equities, respectively.","known_id":"qlib"}],"known":[{"id":"qlib","name":"Qlib datasets","provider":"Microsoft","kind":"market-prices","access":"public","quote":"Following formulaic alpha studies (Shi et al., 2025a; Chen et al., 2026), we use Qlib daily market data (Yang et al., 2020) and predict the 20-trading-day forward return.","mentions":1,"used_in":1}],"sample":{"start":"2023-01","end":"2025-12","market":"China and US equities","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"AlphaPADI ranks first on every reported predictive metric while achieving the highest annualized return and Sharpe ratio, as well as the lowest maximum drawdown across all three datasets.","kind":"performance","quote":"AlphaPADI ranks first on every reported predictive metric while achieving the highest annualized return and Sharpe ratio, as well as the lowest maximum drawdown, across all three datasets."},{"finding":"AlphaPADI leads at both pool sizes (K=20 and K=50), maintaining superior predictive and portfolio performance compared to baselines.","kind":"performance","quote":"AlphaPADI leads at both pool sizes. At both K = 20 and 50, AlphaPADI attai…"}],"reported_performance":{"strategy":"AlphaPADI","sharpe":5.8423,"sharpe_benchmark":null,"annual_return_pct":20.61,"total_return_pct":null,"max_drawdown_pct":8.6},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"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":"2026-11-14T17:03:18Z"},"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/"}