14
Stack Exchange
votes

Is there a P-complete language X such that succinct-X is in P?

Posted on 1/9/2019
UQ ID:36
Science
Theoretical Computer Science
Original

I came across a paper called "A Note on Succinct Representation of Graphs". It seems that in the discussion section they claim that for any problem that is -hard under projections, is -hard.

This made me wonder if the theorem fails for more complicated kinds of reductions. This led me to the following.

My Question

Are there any problems such that is -complete under logspace reductions and is in ?

Additional Questions:

(1) If this is an open problem, then what are the implications if such an existed?

(2) If this is an open problem, is it still open is we weaken the requirement to in ?

(3) It seems that such an would also satisfy that is -hard under logspace reductions, but not -hard under projections. Are such problems known to exist?

(4) I might be mistaken, but I think that I have a construction for such an assuming that . Would this be interesting?

Note: I'm still learning about projections so please let me know if I made any mistakes. Thank you!

Keywords & Tags
cc.complexity-theory
complexity-classes
reductions
succinct
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 question of whether there exists a P-complete language ( X ) under logspace reductions such that ( \text{succinct-}X ) is in P is closely tied to the relationship between the complexity classes P and EXP. Here's a structured answer:

Original Question

Such a language ( X ) exists if and only if ( \text{P} = \text{EXP} ). This is because:

  • If ( X ) is P-complete under logspace re...
0 model reviews
0 human reviews
No reviews yet

GPT-5

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

Short answer: No. In fact, for every language X that is P-complete under logspace many-one reductions, the succinct version of X is EXPTIME-complete (under polynomial-time reductions). In particular, succinct-X cannot be in P by the deterministic time hierarchy theorem (which implies P ≠ EXP).

Why: Given X ∈ P, the succinct version is always in EXP, because you can simulate the polynomial-time al...

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 such language is known. In fact, at the moment we do not even know how to prove that for every P-complete language X the succinct version is outside P, and we do not know how to give a single example of a P-complete set that is not already P-hard under projections. All of your subsidiary questions therefore remain open as well.

The rest of this reply tries to explain what is...

0 model reviews
0 human reviews
5.0/5
(1 review)

o4 mini

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

Below is a sketch of what is known (or really, not known) about this question:

  1. No “natural’’ example is known. Every P‐complete language one usually meets (CVP, alternating graph accessibility, circuit evaluation, Horn‐sat, linear‐inequalities feasibility, etc.) is in fact P‐hard under very weak reductions—projections or “first‐order‐definable” maps—and for all of those people ha...
0 model reviews
1 human reviews
No reviews yet

Gemini 2.5 Pro

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

Excellent and insightful questions! You've hit on some deep and fundamental concepts in complexity theory. Let's break down your questions one by one.

Summary Answer

The short answer to your main question is: Almost certainly no.

The existence of a P-complete language X (under logspace reductions) for which succinct-X is in P would imply P = EXP. This is a major collapse of compl...

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 considering the question: Is there a P-complete language X (under logspace reductions) such that succinct-X is in P?

First, recall definitions:

  • A language X is P-complete under logspace reductions if every problem in P is logspace-reducible to X.
  • The succinct version of X, denoted succinct-X, is defined as follows: For a language X over an alphabet Σ, the language succinct-X co...
0 model reviews
0 human reviews
No reviews yet

o3

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

No.
In fact the following stronger statement is true.

THEOREM
Let X be any language that is P–complete under deterministic log-space (≡ L) many-one reductions.
Then   succinct-X  is complete for EXPTIME under ordinary polynomial-time many-one reductions.
Consequently

 • succinct-X ∈ P ⇒ P = EXPTIME, which contradicts the deterministic time–hierarchy theorem;
 • succinct-X ∈ PH ⇒ EXPTIM...

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

P-Complete Languages with Succinct Versions in P: Analysis and Implications

This question asks about the existence of P-complete languages whose succinct representations remain tractable - specifically, whether there exists a P-complete language X (under logspace reductions) where succinct-X is in P.

Background Concepts

Succinct representation: A compressed encoding of a problem instan...

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 an excellent question that touches on some deep aspects of complexity theory, particularly the relationship between succinct representations and computational complexity.

Let me address your questions systematically:

Main Question Analysis

The existence of a P-complete language X (under logspace reductions) such that succinct-X ∈ P would be quite surprising and is likely an open prob...

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