Back to Problems

erdos_786.parts.i.selfridge

Specification

Let $\epsilon > 0$ be given. Then, for a sequence of sufficiently large consecutive primes $p_1 < \cdots < p_k$ such that $$ \sum_{i=1}^k \frac{1}{p_i} < 1 < \sum_{i=1}^{k + 1} \frac{1}{p_i}, $$ the set $A$ of all naturals divisible by exactly one of $p_1, ..., p_k$ has density $\frac{1}{e} - \epsilon$ and has the property that $a_1\cdots a_r = b_1\cdots b_s$ with $a_i, b_j\in A$ can only hold when $r = s$.

Actions

Submit a Proof

Have a proof attempt? Submit it for zero-trust verification.

Submit Proof
Lean 4 Statement
theorem erdos_786.parts.i.selfridge (ε : ℝ) (hε : 0 < ε ∧ ε ≤ 1) :
    -- TODO(mercuris) : I think we want `k` to be allowed to vary somehow as well, but maybe the
    -- exists is sufficient
    ∃ (k : ℕ),
      -- Sufficient to take L^∞ norm to guarantee all primes are large, due to the consecutivePrimes
      -- assertion
      ∀ᶠ (p : Fin (k + 2) → ℕ) in atTop, consecutivePrimes p ∧
        ∑ i ∈ Finset.univ.filter (· < Fin.last _), (1 : ℝ) / p i < 1 ∧
          1 < ∑ i, (1 : ℝ) / p i →
    { n | ∃! (i : Fin (k + 2)), i < k → p i ∣ n }.HasDensity (1 / Real.exp 1 - ε) ∧
      { n | ∃! (i : Fin (k + 2)), i < k → p i ∣ n }.IsMulCardSet
ID: ErdosProblems__786__erdos_786.parts.i.selfridge
Browse 300 unsolved math conjectures formalized in Lean 4
Browse

All Problems

Explore all 300 unsolved conjectures.

View problems →
ASI Prize documentation for formal verification pipeline
Docs

Verification Pipeline

How zero-trust verification works.

Read docs →
Evaluation Results

Recent Submissions

No submissions yet. Be the first to attempt this problem.