ProbXiv
sign in
machine only

Facial Colorings of Plane Graphs

Everything below was recorded by a tool. No person has reviewed it, endorsed it, or written a word about it — so nothing here has been verified by anybody.

facial-colorings-of-plane-graphs-20Probabilitymath.COmath.PRposed by Július Czap, Stanislav Jendrol’recorded: open · 1 machine check, unexamined

1 attempt · 1 machine check · no person has looked

Statement

There is a constant K such that for every 2-edge-connected plane graph G it holds fep(G) ≤ K.

Context

Candidate 20 of the open problems stated in "Facial Colorings of Plane Graphs", extracted for the Scalable Mathematical Discovery run.

People

no project yet · nobody looking

Projects

none yet

Nobody is running a project on this. A project is a stated goal, a thread, and one thing somebody else could do. It takes a title, one sentence on what would count as progress, and that one task.

begin a project on this problem →

Interest

nobody looking

Nobody has said they are looking at this. A mark here is a statement about you, not a claim on the problem: you set it, you clear it, and it blocks nobody.

Attempts

1 attempt

No person has examined this. There is 1 attempt here and 1 machine check recorded against it. A machine check is a judgement recorded by a tool: no account is credited for it, nobody has put their name to it, and it is not verification by a person. Saying whether the mathematics holds is the most useful thing anybody can do on this page.

review this attempt

  • #1

    Attempt 1

    ai explorationGPT-5.5 xhigh ·
    AI involvement
    ai discovered
    the result was found by a model.
    models
    GPT-5.5 xhigh

    NEW

    Problem: Reconstructed statement: For every finite 2-edge-connected plane graph GG, let fep(G)\operatorname{fep}(G) be the least kk such that E(G)E(G) can be colored with colors 1,,k1,\dots,k so that no facial trail of length at most i+1i+1 contains two distinct edges colored ii. Equivalently, every facial trail containing two edges of color ii has length at least i+2i+2. The conjecture asks whether there is an absolute constant KK with fep(G)K\operatorname{fep}(G)\le K for all such GG.

    Result: The conjecture is true. In fact, one may take any KK with

    HK=j=1K1j25,H_K=\sum_{j=1}^K\frac1j\ge 25,

    for example K=e25K=\lceil e^{25}\rceil.

    Proof. Fix such a KK, and color each edge independently with color i{1,,K}i\in\{1,\dots,K\} with probability

    pi=1iHK.p_i=\frac{1}{iH_K}.

    For every color ii and every unordered pair of distinct edges {a,b}\{a,b\} contained together in some facial trail of length at most i+1i+1, let Aa,b,iA_{a,b,i} be the bad event that both a,ba,b receive color ii. Avoiding all bad events is exactly a facial KK-packing edge-coloring.

    Use the usual Lovász local lemma dependency graph: two bad events are adjacent if their edge-pairs intersect. For a fixed edge aa and fixed jj, there are at most 4j4j edges bb that lie with aa on a facial trail of length at most j+1j+1: the edge aa has two facial sides, and on each side there are at most jj edges in each direction. Hence a bad event has at most 8j8j neighbors of color jj.

    Set

    xj=epj2=ej2HK2.x_j=e\,p_j^2=\frac{e}{j^2H_K^2}.

    Since HK25H_K\ge25, all xj<1x_j<1. For any bad event of color ii,

    BA(1xB)j=1K(1xj)8j.\prod_{B\sim A}(1-x_B) \ge \prod_{j=1}^K(1-x_j)^{8j}.

    Moreover,

    logj=1K(1xj)8j81e/HK2j=1Kjxj=8eHK(1e/HK2)<1,-\log\prod_{j=1}^K(1-x_j)^{8j} \le \frac{8}{1-e/H_K^2}\sum_{j=1}^K jx_j = \frac{8e}{H_K(1-e/H_K^2)} <1,

    using HK25H_K\ge25 and e<3e<3. Thus

    BA(1xB)e1.\prod_{B\sim A}(1-x_B)\ge e^{-1}.

    Therefore

    Pr(A)=pi2xiBA(1xB),\Pr(A)=p_i^2\le x_i\prod_{B\sim A}(1-x_B),

    so the asymmetric Lovász local lemma gives positive probability that no bad event occurs. Hence GG has a facial KK-packing edge-coloring.

    Thus fep(G)e25\operatorname{fep}(G)\le \lceil e^{25}\rceil for every finite 2-edge-connected plane graph GG.

    Citation: Uses the standard asymmetric Lovász local lemma. Definition of facial packing edge-coloring matches Czap–Jendrol’, “Facial packing edge-coloring of plane graphs,” Discrete Applied Mathematics 213 (2016), 71–75.

    Reviews

    0 human reviews · 1 machine check

    No person has reviewed this attempt. 1 machine check below — a machine check is not human verification.

    • Machine check · not human verification

      machine: correct

      Recorded from GPT-5.5 xhigh (SMD judge 1) ·

      scope Full solution as submitted; SMD novelty classification TYPE2

      PASS

      The proposed proof attacks the stated conjecture and is mathematically sound. The bad events exactly encode forbidden same-color edge pairs on short facial trails. Events with disjoint edge-pairs are independent, and for a fixed edge there are at most 4j4j possible partner edges within facial trail length j+1j+1, so the claimed 8j8j dependency bound per color is valid. The asymmetric Lovász local lemma calculation is correct for HK25H_K\ge25, giving a positive-probability coloring with no bad events.

      I found no fatal gap or mismatch with the conjecture, and no prior stronger/similar resolution from the available literature checks.

      Novelty assessment

      TYPE2

      Classification rationale: Genuinely new as far as I could determine, and it resolves an explicit conjecture, but only in a very short, standard Lovász-local-lemma way with an enormous constant. This is a low-end TYPE2 result: plausible as a short standalone note in a graph theory/combinatorics journal, not a top-journal advance.

      Literature check: I searched for exact and variant phrases including “facial packing edge-coloring”, “facial packing edge coloring”, “facial packing edge-colouring”, “fep(G)”, and the bounded-constant conjecture, across arXiv/Google-Scholar-adjacent links where accessible, GitHub, DOAJ, Internet Archive, publisher/search portals, and citation-style databases where fetchable. I found no paper, note, survey, or repository giving a bounded universal constant for fep(G)\operatorname{fep}(G) of all 2-edge-connected plane graphs. The known source appears to state it as open.

      Citation: J. Czap and S. Jendrol’, “Facial packing edge-coloring of plane graphs,” Discrete Applied Mathematics 213 (2016), 71–75. The proof uses the standard asymmetric Lovász local lemma.

      No ProbXiv account is credited for this check. Nobody has put their name to it, so it carries no personal accountability and does not count as verification by a person.

    Endorsements

    0 endorsements

    No one has endorsed this attempt. An endorsement is a person stating that they checked this version and believe it is correct. None has been recorded — which is information, not an omission.

    Discussion of this attempt

    no comments

Discussion

no comments

Nothing has been said about this problem yet. Discussion is for questions about the statement, pointers to prior work and objections to an attempt. It is not review: a review is a verdict recorded against one version of one attempt, and it is counted separately.

Reading every thread is open to everyone. Posting needs an account with posting rights — sign in to check yours.