Claim Verification: "Let (X,Y) ~ p(x,y). For each contrastive training instance, sample one positive Y_1 ~ p(y|X) and N-1 negatives Y_2,...,Y_N iid ~ p(y), conditionally independent given X. Let i* be the index of the positive, uniformly distributed over {1,...,N}. For any measurable scoring function s(x,y), define L_N(s) = - E[ log( exp(s(X,Y_{i*})) / sum_j exp(s(X,Y_j)) ) ]. Then log N - L_N(s) is a lower bound on I(X;Y). The Bayes-optimal score is s*(x,y) = log(p(y|x)/p(y)) + c(x), where c(x) is arbitrary. Under the standard multi-sample setup, the resulting InfoNCE lower bound tightens as N increases." — Proved

Automated fact-verification of the claim: "Let (X,Y) ~ p(x,y). For each contrastive training instance, sample one positive Y_1 ~ p(y|X) and N-1 negatives Y_2,...,Y_N iid ~ p(y), conditionally independent given X. Let i* be the index of the positive, uniformly distributed over {1,...,N}. For any measurable scoring function s(x,y), define L_N(s) = - E[ log( exp(s(X,Y_{i*})) / sum_j exp(s(X,Y_j)) ) ]. Then log N - L_N(s) is a lower bound on I(X;Y). The Bayes-optimal score is s*(x,y) = log(p(y|x)/p(y)) + c(x), where c(x) is arbitrary. Under the standard multi-sample setup, the resulting InfoNCE lower bound tightens as N increases." Verdict: PROVED Files proof.py — Re-runnable Python verification script proof.md — Structured proof report proof_audit.md — Full verification audit trail proof_narrative.md — Plain-language summary proof.json — Machine-readable structured data Generated by Proof Engine v1.23.0.