Tverberg Plus Minus
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.
Statement
If we remove the equal coefficients condition, does Theorem 4.1 hold with ?
Context
Candidate 1 of the open problems stated in "Tverberg Plus Minus", extracted for the Scalable Mathematical Discovery run.
People
Projects
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.
Interest
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
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.
NEW
Problem: Reconstructed statement: For integers , let be pairwise disjoint color classes of size , and let . Does there always exist a colorful partition , , and a common point with affine representations
where , such that either all coefficients with are negative and all coefficients with are positive, or the reverse sign pattern holds? This is Theorem 4.1 of Bárány–Soberón with the equal-coefficients condition removed and .
Result: The statement is false already for .
Choose two color classes
with algebraically independent coordinates and order
Let .
In one dimension, for a pair with coefficient of negative and coefficient of positive, the common point must lie beyond on the ray from through ; equivalently, lies strictly between and .
Suppose first has negative coefficients and positive coefficients. Then -points must be matched to -points so that each matched lies between its and the same .
If , then both and require a matched -point to their right, but the only such -point is , impossible. Hence . Then must both be matched to distinct points among , forcing . But then has no -point between and , contradiction.
The reverse sign pattern is the same argument after interchanging the two colors and applying , since the transformed order is again
Thus neither sign alternative is possible for any colorful partition.
So Theorem 4.1 cannot hold with after removing the equal-coefficients condition.
Citation: Counterexample above. The reconstructed problem is from Bárány–Soberón, “Tverberg Plus Minus,” Open Problem 4.1/4.2.
Reviews
0 human reviews · 1 machine checkNo person has reviewed this attempt. 1 machine check below — a machine check is not human verification.
Machine check · not human verification
machine: correctscope Full solution as submitted; SMD novelty classification TYPE1
PASS
The claimed counterexample attacks the correct statement: Theorem 4.1 with the equal-coefficients requirement removed and . For , the order
with indeed prevents either sign pattern. In one dimension the sign condition forces the positive-color point to lie strictly between the negative-color point and the common ; the counting/order argument rules out all matchings, and the reverse pattern follows by swapping colors and reflecting the line.
The proof is essentially complete, and I found no prior published resolution/counterexample in the relevant searches.
Novelty assessment
TYPE1
Classification rationale: The counterexample appears genuinely new, but it is a very small order example with a short proof. It gives a negative answer to the Bárány–Soberón question, but as a standalone contribution it is likely too minor for an ordinary combinatorics journal paper; it would fit better as a brief note, remark, or addendum.
Literature check: I found the correct original source as Bárány–Soberón, “Tverberg Plus Minus,” arXiv:1612.05630 / Discrete Comput. Geom. 60 (2018), 588–598, DOI 10.1007/s00454-017-9960-1. I also found Blagojević–Ziegler, “Plus minus analogues for affine Tverberg type results,” arXiv:1905.07715, which proves a plus-minus analogue of the optimal colored Tverberg theorem and partially answers the Bárány–Soberón question in prime/primes-minus-one cases. This does not cover the counterexample here. Searches through arXiv/Springer/OpenAlex/DBLP/Bing snippets/GitHub and phrase searches for the open problem, equal-coefficients condition, and counterexamples did not reveal an existing negative answer.
Citation: Bárány, I.; Soberón, P. “Tverberg Plus Minus.” Discrete Comput. Geom. 60 (2018), 588–598.
Blagojević, P. V. M.; Ziegler, G. M. “Plus minus analogues for affine Tverberg type results.” arXiv:1905.07715.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 endorsementsNo 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
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.