{"paper_id":"2610.01115","title":"Certified Alpha Capacity: Statistical Evidence, Economic Lifetime, and Arbitrage under Decay","authors":["Nicolò Bonacorsi"],"paper_date":"2026-10-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2610.01115","page_url":"https://thequant.space/flowcharts/certified-alpha-capacity-statistical-evidence-economic-lifetime-and-arbitrage/","scores":{"empirical_rigor":6,"math_complexity":9,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes Certified Alpha Capacity (CAC), a framework that compares statistical evidence generated by a trading signal to its remaining economic lifetime using KL information.","quote":"We introduce Certified Alpha Capacity (CAC) to compare these two quantities.","summary":"In this paper we study whether a trading signal can accumulate enough statistical evidence for reliable deployment before its economic value decays. We solve the problem by measuring statistical evidence and remaining opportunity on a common Kullback-Leibler information scale, obtaining an exact…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Deterministic information lifetime A for the certification/deployment rule.","type":"model","stated":"explicit","quote":"For deterministic information lifetime A, a certification/deployment rule is a pair (S, δ), where S ∈TA and δ ∈{0, 1} is GS-measurable."},{"assumption":"Near the economic endpoint the drift gap follows ∆t = c(T −t)^p + o((T −t)^p) with p>0 and Σt converges to a positive‑definite matrix.","type":"model","stated":"explicit","quote":"Assume that as t ↑T, for some p > 0 and nonzero c ∈Rd, ∆t = c(T −t)^p + o((T −t)^p), Σt →ΣT ≻0."},{"assumption":"Instantaneous trading objective is quadratic: qᵀµ_t − ½ qᵀΓ_t q with Γ_t ≻0.","type":"model","stated":"explicit","quote":"Let the instantaneous trading objective be q⊤µt −1/2 q⊤Γt q, Γt ≻0,"},{"assumption":"The economic boundary model b = (b_t) defines KL divergence relative to b.","type":"model","stated":"explicit","quote":"Throughout this section, a superscript (b) on an information quantity means that KL divergence is measured relative to the economic‑boundary model b = (b_t)."},{"assumption":"Funding‑rate events require a continuous 180‑day pre‑event history and a seven‑day outcome window.","type":"data","stated":"explicit","quote":"An event requires a continuous 180‑day pre‑event history, current absolute funding at or above its trailing 95th percentile, a seven‑day cooldown, and a complete seven‑day outcome window."},{"assumption":"Implementation costs (turnover, short‑sale costs, capacity, price impact) vary substantially across anomaly strategies.","type":"execution","stated":"implied","quote":"The implementation coefficient matters empirically because turnover, short‑sale costs, capacity, and price impact vary substantially across anomaly strategies."}]},"datasets":{"status":"available","items":[{"name":"Open Source Asset Pricing data set","provider":null,"kind":"alternative","access":"public","period":null,"universe":null,"quote":"Using the Open Source Asset Pricing data set [1], let top_i denote the originally reported in‑sample t‑statistic for predictor i..."},{"name":"BTC‑USDT and ETH‑USDT perpetual‑futures funding histories","provider":"Binance, Bybit, Gate, HTX, KuCoin, MEXC","kind":"other","access":"public","period":null,"universe":"BTC‑USDT and ETH‑USDT contracts","quote":"The data contain BTC‑USDT and ETH‑USDT perpetual‑futures funding histories from Binance, Bybit, Gate, HTX, KuCoin, and MEXC, observed at eight‑hour settlements.","known_id":"binance"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Exact Gaussian certification threshold: deployment probability πα(A)=Φ(√A−z_{1−α}) and feasibility requires A ≥ A_crit(α,β) = (z_{1−α}+z_{1−β})²/2.","kind":"theoretical","quote":"... the largest possible probability of deployment by information time A among all level‑α rules is πα(A)=Φ(√A−z_{1−α}). Consequently ... A"},{"finding":"Survival frontier: for instantaneous Sharpe S=2 and M=100 candidates, the minimum half‑life required is 7.245 years.","kind":"theoretical","quote":"... The highlighted point is S = 2, M = 100, for which the minimum half‑life is 7.245 years."},{"finding":"Empirical association: Spearman correlation between the funding‑rate lifetime score and next‑seven‑day signed funding is 0.476 (BTC/ETH combined).","kind":"statistical","quote":"Spearman association with next‑seven‑day signed funding"},{"finding":"Equilibrium insight: below the certification frontier reliable post‑certification value is zero; above it rents finance entry and crowding reduces remaining information budget.","kind":"theoretical","quote":"Below the frontier, reliable post‑certification value is zero. Above the frontier, rents finance entry and crowding reduces the remaining information budget."},{"finding":"Remaining KL information near death scales as I_rem(t) ≈ cᵀΣ_T⁻¹c /[2(2p+1)] (T−t)^{2p+1}; for p=1, I_rem(t) ∼ cᵀΣ_T⁻¹c·(T−t)³/6.","kind":"theoretical","quote":"/[2(2p+1)] (T−t)^{2p+1} + o((T−t)^{2p+1}). In particular, for a transverse crossing p = 1, I(b)_rem(t) ∼"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"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":"2026-11-14T17:04:08Z"},"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/"}