24
Stack Exchange
votes

Analyzing a class of vertex-deletion games

Posted on 1/2/2012
UQ ID:309
Science
Mathematics
Original

As part of the discussion on this question (Permutation Game Redux), a simple vertex-deletion game was proposed. The game is very simple.

Disconnect. Players alternately remove vertices from a graph . The player that produces a fully disconnected graph (i.e., a graph with no edges) is the winner.

Because the game is impartial, the Sprague-Grundy theory applies: each game is equivalent to a nim-heap of some size (its nim-value), which can be calculated as the mex (minimum excluded nim-value) of its options. These nim-values can then be used to compute the nim-values of disjunctive sums of games in the usual way. One would like to apply this theory within a single game, e.g., to break a graph into its connected components, calculate their nim-values, and then combine them to find the value of the overall graph. Unfortunately, this doesn't work. The problem is that the win condition is not standard: the game ends before all moves are exhausted (or, equivalently, the allowed moves in one component of the graph depend on the other components). It is not hard to see that for any graph and any even , the game is equivalent to (where is the edgeless graph on vertices). To prove it, we need to show that the disjunctive sum is a second-player win. The proof is by induction on . If is edgeless, then the first player loses immediately (both games are over). Otherwise, the first player can move in either , and the second player can copy his move in the other one (reducing to with ); or, if , the first player can move in the disconnected piece, and the second player can do the same (reducing to ). This shows that any graph is equivalent to , where is the part of with no disconnected vertices, and or is the parity of the number of disconnected vertices in . All games in an equivalence class have the same nim-value, and moreover, the equivalence relation respects the union operation: if and then . Moreover, one can see that the games in and have different nim-values unless is the null graph: when playing , the first player can take the isolated vertex, leaving , and then copy the second player's moves thereafter. Beyond this, are there any other general decomposition or equivalence results? Any extension of the Sprague-Grundy theory to this class of games? In particular, is there some more refined equivalence relation still to be found such that all games in have the same nim-value, and can be determined in terms of and ?

Keywords & Tags
graph-theory
combinatorial-game-theory
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

The vertex-deletion game "Disconnect" can be analyzed using an extension of Sprague-Grundy theory by refining the equivalence relation to account for graph structure and isolated vertices. Here's the key insight:

A graph ( G ) can be decomposed into its non-isolated connected components (those with edges or size ≥2) and its isolated vertices. Let ( H ) be the union of non-isolated components,...

0 model reviews
0 human reviews
No reviews yet

GPT-5

Failed UQ Validation
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

Yes. There is a clean way to “repair” Sprague–Grundy for this game and get exactly the kind of decomposition you want.

Key idea: strip off the isolated vertices (which are just “passes”) and play a standard impartial game on the rest.

Definitions.

  • Let κ(G) be G with all isolated vertices deleted.
  • Let p(G) be the parity (0/1) of the number of isolated vertices of G.
  • Consider the restricted ...
0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Analyzing the "Disconnect" Vertex-Deletion Game

This question examines a graph-based combinatorial game called "Disconnect" where players take turns removing vertices, and the player who creates a completely disconnected graph (no edges) wins.

Understanding the Current Results

The question has already established several important properties:

  1. For any graph G and even n, G ∪ K̄ₙ (G with...
0 model reviews
0 human reviews
No reviews yet

o3 Pro

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Short answer. No.
Apart from the little trick with the isolated vertices that you have already discovered, the game “Disconnect’’ stubbornly refuses to split into smaller, independent parts. There is no non-trivial equivalence relation ≈ that

 (i) puts finitely (or even just few) graphs into the same class,
 (ii) guarantees that two equivalent graphs have the same nim–value, and
 (iii) ma...

0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

Failed UQ Validation
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> We are analyzing an impartial game called "Disconnect" played on graphs. Players alternately remove vertices, and the player who leaves a graph with no edges wins. The game is impartial, so Sprague-Grundy theory applies: each game position has a nim-value (or Grundy number) which is the mex (minimum excludant) of the nim-values of the positions reachable by one move.

However, the win cond...

0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Here is what one can say in complete generality.

  1. “Disconnect” is an impartial misère‐type game. A position is a finite graph G with at least one edge, and a move is “delete one vertex.” Terminal positions are edgeless graphs (no edges)—as soon as you reach an edgeless graph the game stops and the last mover wins. In particular you cannot continue deleting isolated vertices once there...
0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

UQ Validated
Needs Human Verification
Google
Aug 1, 2025, 12:00 AM

This is an excellent question that delves into the nuances of applying combinatorial game theory to games with non-standard winning conditions. You've already made the most crucial observations, which are the key to unlocking the game's structure. Let's formalize and extend your findings.

Summary of Key Insights

You correctly identified:

  1. The Core Problem: The standard decomposition of...
0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Write 𝐺↦g(𝐺) for the Sprague–Grundy number (nim–value) of a graph in the game

Disconnect : “A move consists of deleting one vertex.
The player who makes the last edge disappear wins; at that moment the game stops and no further vertex may be removed.”

  1. What happens when the position has no isolated vertices?
    If V⁺(𝐺) is the set of vertices whose degree is ≥1, every legal move must b...
0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

This is a fascinating question about a vertex-deletion game where the winning condition is non-standard (producing a fully disconnected graph rather than having no moves left). Let me analyze the key aspects and explore potential extensions.

Key Observations from the Question

  1. The game is impartial but has a non-standard winning condition
  2. **Standard Sprague-Grundy decomposition fails...
0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer