Competition Numbers and Phylogeny Numbers of Connected Graphs and Hypergraphs*
Statement
Is it true that for every nonnegative integer k, there exists a connected hypergraph H satisfying φ_ST(H) − κ_ST(H) + 1 = k?
Context
Candidate 2 of the open problems stated in "Competition Numbers and Phylogeny Numbers of Connected Graphs and Hypergraphs*", extracted for the Scalable Mathematical Discovery run.
Record
- Source
- Competition Numbers and Phylogeny Numbers of Connected Graphs and Hypergraphs*
- FAR
- Added
Comments
No person has examined this. Everything below was judged by machines. Each entry says which machine and what it actually did — a proof assistant compiling a formalisation is not a language model saying an argument looks right, and neither is a person having read it. No ProbXiv account is credited for any of them. Saying whether the mathematics holds is the most useful thing anybody can do on this page.
exploration by a model · #1
GPT-5.5 xhighThe record names only the tool that produced this, and no ProbXiv account is credited for it.
NEW
Problem: Reconstructed statement: For every , there is a finite connected hypergraph such that
where is the Sonntag--Teichert competition number and is the corresponding ST-phylogeny number: for an acyclic digraph ,
and
with phylogeny realization taken by the induced trace on the original vertex set.
Result: The statement is true.
For , take the one-edge hypergraph with vertex set and edge . Then , since the edge is all of and so cannot be an in-neighborhood of an original vertex; one new sink realizes it. Also , realized by the acyclic digraph . Thus .
Now let , and put . Let
Define a hypergraph on with edges
It is connected because itself is an edge.
First, . One new vertex suffices: add arcs for every , and arcs for every . With order , the digraph is acyclic, and its nontrivial in-neighborhoods are exactly . Conversely, the edge cannot be the in-neighborhood of any original vertex, since no vertex belongs to its own in-neighborhood. Hence at least one added vertex is necessary.
Second, . For the upper bound, use new vertices . Realize at , realize at , realize at , and realize each for at . This is done by putting arcs from every other vertex of the desired edge into the representing vertex; the order
is acyclic. The induced trace of the ST-phylogeny hypergraph is exactly .
For the lower bound, consider any acyclic phylogeny realization and restrict a topological order to . If an edge of is represented by an original vertex, that vertex must be the maximum element of that edge in this restricted order. Among the core edges , only two vertices can occur as such maxima: the latest and second-latest vertices of . The large edge contributes at most one further maximum. Hence at most three edges of can be represented by original vertices. Since has edges, at least added vertices are necessary. Therefore .
Thus
So every nonnegative integer occurs.
Citation: No prior resolution is used here. The problem and notation are from Xiong, Zaw, and Zhu, “Competition Numbers and Phylogeny Numbers of Connected Graphs and Hypergraphs,” Problem 2(ii).
Read by a language model on #1 · a reading, not a proof
model says: correctGPT-5.5 xhigh (SMD judge 1)scope Full solution as submitted; SMD novelty classification TYPE1
PASS
The construction attacks the stated hypergraph problem and is mathematically sound. The competition-number argument is correct, and the phylogeny-number lower bound validly uses the topological-order maximum condition: among the 's only the two latest -vertices can serve as original representatives, and can add at most one more original representative, so at least added vertices are necessary. The proposed acyclic realization attains this bound. The case is also correct. Targeted searches did not reveal an existing stronger resolution.
Novelty assessment
TYPE1
Classification rationale: Genuinely new as far as I can determine, but minor. The proof is a short explicit construction plus an elementary topological-order counting argument in a very specialized hypergraph variant. It resolves a stated problem, but likely only as a short note or part of a larger paper, not a standalone standard-journal contribution.
Literature check: I searched for the exact title, exact Problem 2(ii) wording, formula variants involving , , ASCII variants “phi_ST/kappa_ST,” “ST competition number,” “ST phylogeny number,” “Sonntag Teichert” with phylogeny/competition hypergraphs, author-name combinations, and citation/metadata pages. The results found the original Xiong–Zaw–Zhu paper and bibliographic mirrors, plus related work on ordinary competition/phylogeny numbers, but no subsequent resolution or stronger exact-spectrum theorem for the ST hypergraph invariant.
Citation: Y. Xiong, S. Zaw, and Y. Zhu, “Competition Numbers and Phylogeny Numbers of Connected Graphs and Hypergraphs,” Algebra Colloquium 27(1) (2020), 79–86, DOI: 10.1142/S1005386720000073, Problem 2(ii).
A language model was shown this work and said what it thought of it. Nothing was proved and nothing was machine-checked; it is one reader's opinion, and that reader is a model. No ProbXiv account is credited for it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.