Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 2 — bias O(T2δ2M)O(T^2\delta^2M)O(T2δ2M) and variance ≤2M2(T+1)\le 2M^2(T+1)≤2M2(T+1) of the untruncated PG estimator, without mixing

Proved
TPG.proposition_2_untruncated_pg

by Wenqian Xing · Oct 12, 2026 · Mathlib 0df444a (Lean v4.33.1)

causal-inferencemarkov-chainnonstationaritypolicy-gradienttreatment-effect

Setting. SSS is a finite state space and the action Zt∈{0,1}Z_t\in\{0,1\}Zt​∈{0,1} is control or treatment. Time is t=0,1,…,T−1t=0,1,\dots,T-1t=0,1,…,T−1, which is the source's time t+1t+1t+1. Under action zzz at time ttt the state moves according to a transition matrix PztP_z^tPzt​, i.e. P(Xt+1=x′∣Xt=x,Zt=z)=Pzt(x,x′)\mathbb P(X_{t+1}=x'\mid X_t=x,Z_t=z)=P_z^t(x,x')P(Xt+1​=x′∣Xt​=x,Zt​=z)=Pzt​(x,x′); the matrices may depend on ttt arbitrarily. The initial state X0X_0X0​ has distribution ρ\rhoρ, and the reward YtY_tYt​ has distribution R(⋅∣Xt,Zt)R(\cdot\mid X_t,Z_t)R(⋅∣Xt​,Zt​) on R\mathbb RR, with R([−M,M]∣x,z)=1R([-M,M]\mid x,z)=1R([−M,M]∣x,z)=1 for all x,zx,zx,z and conditional independence from everything else given (Xt,Zt)(X_t,Z_t)(Xt​,Zt​). Under the policy πθ\pi_\thetaπθ​ every action is treatment with probability θ\thetaθ, independently of everything else; Eθ\mathbb E_\thetaEθ​, Pθ\mathbb P_\thetaPθ​ and Var⁡θ\operatorname{Var}_\thetaVarθ​ refer to the law of the trajectory (Xt,Zt,Yt)t<T(X_t,Z_t,Y_t)_{t<T}(Xt​,Zt​,Yt​)t<T​ under πθ\pi_\thetaπθ​.

The global average treatment effect is τ=1T∑t<T(E1[Yt]−E0[Yt])\tau=\frac1T\sum_{t<T}\bigl(\mathbb E_1[Y_t]-\mathbb E_0[Y_t]\bigr)τ=T1​∑t<T​(E1​[Yt​]−E0​[Yt​]). The kernel deviation is δ=sup⁡t<Tsup⁡x∈S∥P1t(x,⋅)−P0t(x,⋅)∥TV\delta=\sup_{t<T}\sup_{x\in S}\|P_1^t(x,\cdot)-P_0^t(x,\cdot)\|_{\mathrm{TV}}δ=supt<T​supx∈S​∥P1t​(x,⋅)−P0t​(x,⋅)∥TV​ with ∥f−g∥TV=12∥f−g∥1\|f-g\|_{\mathrm{TV}}=\tfrac12\|f-g\|_1∥f−g∥TV​=21​∥f−g∥1​, and J(θ)=1T∑t<TEθ[Yt]J(\theta)=\frac1T\sum_{t<T}\mathbb E_\theta[Y_t]J(θ)=T1​∑t<T​Eθ​[Yt​].

Let τ^T\widehat\tau_TτT​ be the untruncated policy gradient estimator under π1/2\pi_{1/2}π1/2​,

τ^T=1T∑u=0T−1(1{Zu=1}1/2−1{Zu=0}1/2)∑t=uT−1Yt.\widehat\tau_T=\frac1T\sum_{u=0}^{T-1}\Bigl(\frac{\mathbf 1\{Z_u=1\}}{1/2}-\frac{\mathbf 1\{Z_u=0\}}{1/2}\Bigr)\sum_{t=u}^{T-1}Y_t .τT​=T1​u=0∑T−1​(1/21{Zu​=1}​−1/21{Zu​=0}​)t=u∑T−1​Yt​.

Proposition. No mixing assumption is imposed. There is an absolute constant C>0C>0C>0, not depending on the state space, the environment, TTT or MMM, such that for every T≥1T\ge1T≥1:

  1. ∣E1/2[τ^T]−τ∣≤C T2δ2M\bigl|\mathbb E_{1/2}[\widehat\tau_T]-\tau\bigr|\le C\,T^2\delta^2M​E1/2​[τT​]−τ​≤CT2δ2M;
  2. the same bound holds for the derivative of JJJ itself, ∣J′(1/2)−τ∣≤C T2δ2M\bigl|J'(1/2)-\tau\bigr|\le C\,T^2\delta^2M​J′(1/2)−τ​≤CT2δ2M, hence for every unbiased estimator of ∇J(1/2)\nabla J(1/2)∇J(1/2);
  3. Var⁡1/2(τ^T)≤2M2(T+1)\operatorname{Var}_{1/2}(\widehat\tau_T)\le 2M^2(T+1)Var1/2​(τT​)≤2M2(T+1).

This is the untruncated counterpart of Theorem 1: without mixing and truncation the bias bound grows quadratically and the variance bound linearly in the horizon.

Formalization Note The O(⋅)O(\cdot)O(⋅) of the source is rendered by an existentially quantified constant chosen before the state space and the environment. Item 2 is stated for every real number ggg that is a derivative of JJJ at 1/21/21/2.

Preamble
import Mathlib
import Definitions.Def_TPG_Model
import Definitions.Def_TPG_Estimators

open MeasureTheory ProbabilityTheory
open scoped BigOperators ENNReal
Formal statement
namespace TPG
theorem proposition_2_untruncated_pg :
    ∃ C : ℝ, 0 < C ∧
      ∀ (S : Type) [Fintype S] [MeasurableSpace S] [MeasurableSingletonClass S]
        (E : Env S) (T : ℕ) (M : ℝ),
        0 < T → E.RewardBound M →
          |(∫ ω, tpgEst (1 / 2) T T ω ∂(E.expLaw T (1 / 2))) - E.gate T|
              ≤ C * ((T : ℝ) ^ 2 * (E.delta T) ^ 2 * M)
            ∧ (∀ g : ℝ, HasDerivAt (fun θ : ℝ => E.J T θ) g (1 / 2) →
                |g - E.gate T| ≤ C * ((T : ℝ) ^ 2 * (E.delta T) ^ 2 * M))
            ∧ variance (tpgEst (1 / 2) T T) (E.expLaw T (1 / 2))
              ≤ 2 * M ^ 2 * ((T : ℝ) + 1) := by sorry
end TPG
Source
Johari, Peng, Xing, Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator, revised manuscript of October 2026 (revision of arXiv:2506.05308v3, https://arxiv.org/abs/2506.05308); numbering follows the revised manuscript. §4, pp. 14–15, Proposition 2, eq. (8); proof in Appendix G.2, pp. 43–46.
Read-back

What the Lean code literally says, in plain math · claude-opus-5-5

Read-back of TPG.proposition_2_untruncated_pg.

Logical form. The statement asserts: there exists a single real number CCC with C>0C>0C>0 such that for all of the data listed below, if the two hypotheses (H1)–(H2) hold, then the three assertions (a) and (b) and (c) all hold. The constant CCC is chosen first and everything else is universally quantified after it, so CCC is absolute: it may not depend on the set SSS, on the environment EEE, on TTT or on MMM. The same CCC is used in (a) and in (b). Assertion (c) contains no unspecified constant.

Universally quantified data, in this order.

  1. A set SSS (a type in the lowest universe) which is finite, equipped with a σ\sigmaσ-algebra in which every singleton {x}\{x\}{x} is measurable. (As SSS is finite, this forces every subset of SSS to be measurable.) Non-emptiness of SSS is not assumed as a hypothesis.

  2. An environment EEE on SSS. This is a package consisting of:

    • for every natural number t∈Nt\in\mathbb{N}t∈N and every Boolean value z∈{1,0}z\in\{1,0\}z∈{1,0} (here and below 111 = true, 000 = false), a real matrix Pt,z=(Pt,z(x,x′))x,x′∈SP_{t,z}=(P_{t,z}(x,x'))_{x,x'\in S}Pt,z​=(Pt,z​(x,x′))x,x′∈S​ with all entries ≥0\ge 0≥0 and every row summing to 111: ∑x′∈SPt,z(x,x′)=1\sum_{x'\in S}P_{t,z}(x,x')=1∑x′∈S​Pt,z​(x,x′)=1 for all t,z,xt,z,xt,z,x;
    • a function ρ:S→R\rho:S\to\mathbb{R}ρ:S→R with ρ(x)≥0\rho(x)\ge 0ρ(x)≥0 for all xxx and ∑x∈Sρ(x)=1\sum_{x\in S}\rho(x)=1∑x∈S​ρ(x)=1;
    • for every x∈Sx\in Sx∈S and every Boolean zzz, a Borel probability measure Rx,zR_{x,z}Rx,z​ on R\mathbb{R}R.
  3. A natural number TTT.

  4. A real number MMM.

Hypotheses.

  • (H1) 0<T0<T0<T.
  • (H2) ("reward bound MMM") For every x∈Sx\in Sx∈S and every Boolean zzz: Rx,z([−M,M])=1R_{x,z}\bigl([-M,M]\bigr)=1Rx,z​([−M,M])=1.

There is no other hypothesis. In particular no contraction or mixing condition on the matrices Pt,zP_{t,z}Pt,z​ is assumed.

Objects used in the conclusion.

Trajectory space. ΩT=(S×{1,0}×R)T\Omega_T=(S\times\{1,0\}\times\mathbb{R})^{T}ΩT​=(S×{1,0}×R)T, the set of sequences ω=(ωt)t=0T−1\omega=(\omega_t)_{t=0}^{T-1}ω=(ωt​)t=0T−1​ indexed by the times t∈{0,1,…,T−1}t\in\{0,1,\dots,T-1\}t∈{0,1,…,T−1}, with the product σ\sigmaσ-algebra (the given one on SSS, the discrete one on {1,0}\{1,0\}{1,0}, the Borel one on R\mathbb{R}R). The coordinate maps are written Xt(ω)∈SX_t(\omega)\in SXt​(ω)∈S, Zt(ω)∈{1,0}Z_t(\omega)\in\{1,0\}Zt​(ω)∈{1,0}, Yt(ω)∈RY_t(\omega)\in\mathbb{R}Yt​(ω)∈R for the three components of ωt\omega_tωt​.

Trajectory measure with constant parameter θ\thetaθ, defined for every real θ\thetaθ. For a state sequence x=(x0,…,xT−1)∈STx=(x_0,\dots,x_{T-1})\in S^Tx=(x0​,…,xT−1​)∈ST and a Boolean sequence z=(z0,…,zT−1)∈{1,0}Tz=(z_0,\dots,z_{T-1})\in\{1,0\}^Tz=(z0​,…,zT−1​)∈{1,0}T define the real weight

wθ(x,z)  =  ρ(x0)  ⋅  ∏s=0T−2Ps,zs(xs,xs+1)  ⋅  ∏t=0T−1{θ,zt=1,1−θ,zt=0.w_\theta(x,z)\;=\;\rho(x_0)\;\cdot\;\prod_{s=0}^{T-2}P_{s,z_s}(x_s,x_{s+1})\;\cdot\;\prod_{t=0}^{T-1}\begin{cases}\theta,& z_t=1,\\ 1-\theta,& z_t=0.\end{cases}wθ​(x,z)=ρ(x0​)⋅s=0∏T−2​Ps,zs​​(xs​,xs+1​)⋅t=0∏T−1​{θ,1−θ,​zt​=1,zt​=0.​

(The code writes this as three products over all time indices with indicator conditions "t=0t=0t=0" and "s+1=ts+1=ts+1=t"; for T≥1T\ge 1T≥1 it equals the displayed expression. The transition from time sss to time s+1s+1s+1 uses the matrix with time index sss and the Boolean zsz_szs​.) The measure on ΩT\Omega_TΩT​ is the finite mixture

PT,θ  =  ∑x∈ST ∑z∈{1,0}T max⁡{wθ(x,z), 0}  ⋅  ⨂t=0T−1(Dirac(xt)⊗Dirac(zt)⊗Rxt,zt),\mathbb{P}_{T,\theta}\;=\;\sum_{x\in S^T}\ \sum_{z\in\{1,0\}^T}\ \max\{w_\theta(x,z),\,0\}\;\cdot\;\bigotimes_{t=0}^{T-1}\Bigl(\mathrm{Dirac}(x_t)\otimes\mathrm{Dirac}(z_t)\otimes R_{x_t,z_t}\Bigr),PT,θ​=x∈ST∑​ z∈{1,0}T∑​ max{wθ​(x,z),0}⋅t=0⨂T−1​(Dirac(xt​)⊗Dirac(zt​)⊗Rxt​,zt​​),

where Dirac(a)\mathrm{Dirac}(a)Dirac(a) is the unit point mass at aaa and ⨂\bigotimes⨂ is the product measure over the TTT time coordinates. A negative weight is replaced by 000.

For θ∈[0,1]\theta\in[0,1]θ∈[0,1] all weights are non-negative and sum to 111, and PT,θ\mathbb{P}_{T,\theta}PT,θ​ is the probability law under which: X0X_0X0​ has distribution ρ\rhoρ; Z0,…,ZT−1Z_0,\dots,Z_{T-1}Z0​,…,ZT−1​ are independent of X0X_0X0​ and i.i.d. with Pr⁡(Zt=1)=θ\Pr(Z_t=1)=\thetaPr(Zt​=1)=θ; given the past, Xs+1X_{s+1}Xs+1​ is drawn from row XsX_sXs​ of Ps,ZsP_{s,Z_s}Ps,Zs​​; and, given the whole sequences (Xt)(X_t)(Xt​) and (Zt)(Z_t)(Zt​), the YtY_tYt​ are independent with Yt∼RXt,ZtY_t\sim R_{X_t,Z_t}Yt​∼RXt​,Zt​​. For θ=12\theta=\tfrac12θ=21​ the weight is 2−Tρ(x0)∏s=0T−2Ps,zs(xs,xs+1)2^{-T}\rho(x_0)\prod_{s=0}^{T-2}P_{s,z_s}(x_s,x_{s+1})2−Tρ(x0​)∏s=0T−2​Ps,zs​​(xs​,xs+1​). For θ=1\theta=1θ=1 the weight is 000 unless every zt=1z_t=1zt​=1; for θ=0\theta=0θ=0 it is 000 unless every zt=0z_t=0zt​=0. For θ∉[0,1]\theta\notin[0,1]θ∈/[0,1] some weights are negative and are replaced by 000, and PT,θ\mathbb{P}_{T,\theta}PT,θ​ is then a finite measure that need not have total mass 111.

The estimator. For ω∈ΩT\omega\in\Omega_Tω∈ΩT​,

G^T(ω)  =  1T∑u=0T−1σ(Zu(ω))∑t∈{0,…,T−1}u≤t≤u+TYt(ω),σ(1)=11/2=2,σ(0)=−11−1/2=−2.\widehat G_{T}(\omega)\;=\;\frac1T\sum_{u=0}^{T-1}\sigma\bigl(Z_u(\omega)\bigr)\sum_{\substack{t\in\{0,\dots,T-1\}\\ u\le t\le u+T}}Y_t(\omega),\qquad \sigma(1)=\frac{1}{1/2}=2,\quad \sigma(0)=-\frac{1}{1-1/2}=-2 .GT​(ω)=T1​u=0∑T−1​σ(Zu​(ω))t∈{0,…,T−1}u≤t≤u+T​∑​Yt​(ω),σ(1)=1/21​=2,σ(0)=−1−1/21​=−2.

This is the code's windowed estimator with window length parameter set equal to TTT. Since every time index satisfies t≤T−1<u+Tt\le T-1<u+Tt≤T−1<u+T, the condition u≤t≤u+Tu\le t\le u+Tu≤t≤u+T is the same as t≥ut\ge ut≥u, so

G^T(ω)  =  1T∑u=0T−1σ(Zu(ω))∑t=uT−1Yt(ω).\widehat G_{T}(\omega)\;=\;\frac1T\sum_{u=0}^{T-1}\sigma\bigl(Z_u(\omega)\bigr)\sum_{t=u}^{T-1}Y_t(\omega).GT​(ω)=T1​u=0∑T−1​σ(Zu​(ω))t=u∑T−1​Yt​(ω).

The comparison quantity (called gate in the code).

GT(E)  =  1T∑t=0T−1(∫ΩTYt dPT,1  −  ∫ΩTYt dPT,0).G_T(E)\;=\;\frac1T\sum_{t=0}^{T-1}\Bigl(\int_{\Omega_T}Y_t\,d\mathbb{P}_{T,1}\;-\;\int_{\Omega_T}Y_t\,d\mathbb{P}_{T,0}\Bigr).GT​(E)=T1​t=0∑T−1​(∫ΩT​​Yt​dPT,1​−∫ΩT​​Yt​dPT,0​).

The function JJJ. For every real θ\thetaθ,

JT(θ)  =  1T∑t=0T−1∫ΩTYt dPT,θ.J_T(\theta)\;=\;\frac1T\sum_{t=0}^{T-1}\int_{\Omega_T}Y_t\,d\mathbb{P}_{T,\theta}.JT​(θ)=T1​t=0∑T−1​∫ΩT​​Yt​dPT,θ​.

This is a function R→R\mathbb{R}\to\mathbb{R}R→R (for θ∉[0,1]\theta\notin[0,1]θ∈/[0,1] it is computed with the clipped measure described above).

The quantity δT(E)\delta_T(E)δT​(E) (called delta in the code).

δT(E)  =  sup⁡t∈{0,…,T−1} sup⁡x∈S 12∑x′∈S∣Pt,1(x,x′)−Pt,0(x,x′)∣,\delta_T(E)\;=\;\sup_{t\in\{0,\dots,T-1\}}\ \sup_{x\in S}\ \frac12\sum_{x'\in S}\bigl|P_{t,1}(x,x')-P_{t,0}(x,x')\bigr| ,δT​(E)=t∈{0,…,T−1}sup​ x∈Ssup​ 21​x′∈S∑​​Pt,1​(x,x′)−Pt,0​(x,x′)​,

i.e. the largest, over times t<Tt<Tt<T and states xxx, of half the ℓ1\ell^1ℓ1-distance between row xxx of Pt,1P_{t,1}Pt,1​ and row xxx of Pt,0P_{t,0}Pt,0​. (The supremum is the real-number supremum with the convention that an empty supremum is 000; under (H1), and because an environment can only exist on a non-empty SSS, both index sets are finite and non-empty, so this is a maximum, and it lies in [0,1][0,1][0,1].)

Integral and variance. ∫\int∫ denotes the Lebesgue (Bochner) integral, which by convention is 000 for a non-integrable integrand. The variance of a function FFF under a measure μ\muμ is

Var⁡μ(F)  =  ∫ΩT∣F−∫F dμ∣2dμ,\operatorname{Var}_\mu(F)\;=\;\int_{\Omega_T}\Bigl|F-\int F\,d\mu\Bigr|^2 d\mu ,Varμ​(F)=∫ΩT​​​F−∫Fdμ​2dμ,

computed as an integral with values in [0,∞][0,\infty][0,∞] and then converted to a real number, with the value ∞\infty∞ converted to 000. (Under (H2) every YtY_tYt​ lies in [−M,M][-M,M][−M,M] almost surely for each of the measures above, so all integrands here are almost surely bounded.)

Conclusion. Under (H1)–(H2), all three of the following hold.

(a)

∣∫ΩTG^T dPT,1/2  −  GT(E)∣  ≤  C⋅T2 δT(E)2 M.\Bigl|\int_{\Omega_T}\widehat G_{T}\,d\mathbb{P}_{T,1/2}\;-\;G_T(E)\Bigr|\;\le\;C\cdot T^{2}\,\delta_T(E)^{2}\,M .​∫ΩT​​GT​dPT,1/2​−GT​(E)​≤C⋅T2δT​(E)2M.

(b) For every real number ggg: if the function θ↦JT(θ)\theta\mapsto J_T(\theta)θ↦JT​(θ) has derivative ggg at the point θ=12\theta=\tfrac12θ=21​ (ordinary two-sided derivative, i.e. JT(θ)=JT(12)+g (θ−12)+o(∣θ−12∣)J_T(\theta)=J_T(\tfrac12)+g\,(\theta-\tfrac12)+o(|\theta-\tfrac12|)JT​(θ)=JT​(21​)+g(θ−21​)+o(∣θ−21​∣) as θ→12\theta\to\tfrac12θ→21​), then

∣g−GT(E)∣  ≤  C⋅T2 δT(E)2 M.\bigl|g-G_T(E)\bigr|\;\le\;C\cdot T^{2}\,\delta_T(E)^{2}\,M .​g−GT​(E)​≤C⋅T2δT​(E)2M.

(c)

Var⁡PT,1/2(G^T)  ≤  2 M2 (T+1).\operatorname{Var}_{\mathbb{P}_{T,1/2}}\bigl(\widehat G_{T}\bigr)\;\le\;2\,M^{2}\,(T+1).VarPT,1/2​​(GT​)≤2M2(T+1).

All inequalities are non-strict. The estimator's parameter and the sampling law's parameter in (a) and (c) are both the fixed number 12\tfrac1221​, and the derivative in (b) is taken at 12\tfrac1221​; no other value of the parameter is covered.

Boundary and degenerate cases as the statement literally has them.

  • Assertion (b) is conditional. It does not assert that JTJ_TJT​ is differentiable at 12\tfrac1221​. It says that any real number ggg which is a derivative of JTJ_TJT​ at 12\tfrac1221​ satisfies the bound; if JTJ_TJT​ had no derivative at 12\tfrac1221​, (b) would hold with nothing to check. (A derivative, when it exists, is unique, so (b) is a statement about at most one ggg.) Only the values of JTJ_TJT​ near 12\tfrac1221​ matter for this hypothesis, and for θ\thetaθ in (0,1)(0,1)(0,1) no weight is clipped.
  • Empty SSS. If SSS is empty there is no environment on SSS (the condition ∑xρ(x)=1\sum_x\rho(x)=1∑x​ρ(x)=1 cannot hold), so nothing is asserted for empty SSS.
  • Sign of MMM. MMM ranges over all reals. For M<0M<0M<0 the interval [−M,M][-M,M][−M,M] is empty, (H2) cannot hold, and nothing is asserted. For M=0M=0M=0, (H2) says every Rx,zR_{x,z}Rx,z​ is the point mass at 000, and all three right-hand sides are 000.
  • Which matrices are constrained and which are used. The measures PT,θ\mathbb{P}_{T,\theta}PT,θ​ involve only Ps,zP_{s,z}Ps,z​ for 0≤s≤T−20\le s\le T-20≤s≤T−2. The quantity δT(E)\delta_T(E)δT​(E) involves Pt,zP_{t,z}Pt,z​ for 0≤t≤T−10\le t\le T-10≤t≤T−1, i.e. it also involves PT−1,zP_{T-1,z}PT−1,z​, which does not enter any of the measures. The matrices Pt,zP_{t,z}Pt,z​ with t≥Tt\ge Tt≥T appear nowhere. In particular for T=1T=1T=1 no transition matrix enters the measures, while δ1(E)\delta_1(E)δ1​(E) is computed from P0,1P_{0,1}P0,1​ and P0,0P_{0,0}P0,0​.
  • What δT(E)\delta_T(E)δT​(E) measures. Only the transition matrices enter δT(E)\delta_T(E)δT​(E); the measures Rx,1R_{x,1}Rx,1​ and Rx,0R_{x,0}Rx,0​ do not. When δT(E)=0\delta_T(E)=0δT​(E)=0 the right-hand sides of (a) and (b) are 000, so (a) then asserts equality and (b) asserts that any derivative ggg equals GT(E)G_T(E)GT​(E).
  • Form of the bounds. The right-hand side of (a) and (b) is CCC times the product T2⋅δT(E)2⋅MT^{2}\cdot\delta_T(E)^{2}\cdot MT2⋅δT​(E)2⋅M, with TTT regarded as a real number. The right-hand side of (c) is 2M2(T+1)2M^{2}(T+1)2M2(T+1); it is not divided by TTT and does not involve δT(E)\delta_T(E)δT​(E) or CCC.
  • The last Boolean coordinate. zT−1z_{T-1}zT−1​ enters no transition factor of the weight; it affects only the law RxT−1,zT−1R_{x_{T-1},z_{T-1}}RxT−1​,zT−1​​ of YT−1Y_{T-1}YT−1​.
Human review
  • Endorsed by tianyipeng · Oct 12, 2026

  • Endorsed by Wenqian Xing · Oct 12, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me