Skip to content
SearchFR · Français
Get started

Withdrawn

Erdős problem #647: proof judged incorrect by the wiki (ChatGPT Deep research, DeepSeek DeepThink, Gemini)

The gist

A proof of Erdős problem #647, dated January 28, 2026 and attributed to ChatGPT Deep research, DeepSeek DeepThink and Gemini, was classed as incorrect by the wiki on AI contributions.

DiscoverIA status on October 12, 2026: withdrawn, meaning withdrawn or abandoned by its author, or marked incorrect by the reference source.

Status detailsDetails

AI draft, not reviewedWhat has not been reviewed?

Text written by an AI (DiscoverIA pipeline), on . The status and its sources come from the registry; only the explanatory text has not been reviewed. A reported error is corrected, then the text is reviewed.

FollowReport

Cite this entry

A single status snapshot since Oct 12, 2026: a citation always points to a dated snapshot.

Cite snapshot 1, Oct 12, 2026

APA citation with the dated link

DiscoverIA. (2026, October 12). Erdős problem #647: proof judged incorrect by the wiki (ChatGPT Deep research, DeepSeek DeepThink, Gemini) [Status: Withdrawn, snapshot 1]. DiscoverIA registry. https://discoveria.ai/entry/erdos-647-chatgpt-deep-research-deepseek-deepthink-1a#releve-1

BibTeX @misc, key discoveria-erdos-647-chatgpt-deep-research-deepseek-deepthink-1a-r1

@misc{discoveria-erdos-647-chatgpt-deep-research-deepseek-deepthink-1a-r1,
  author       = {{DiscoverIA}},
  title        = {Erdős problem #647: proof judged incorrect by the wiki (ChatGPT Deep research, DeepSeek DeepThink, Gemini)},
  howpublished = {DiscoverIA registry, entry erdos-647-chatgpt-deep-research-deepseek-deepthink-1a},
  note         = {Status “Withdrawn”, snapshot 1, recorded on October 12, 2026. New result},
  year         = {2026},
  url          = {https://discoveria.ai/entry/erdos-647-chatgpt-deep-research-deepseek-deepthink-1a#releve-1},
  urldate      = {2026-10-12}
}

Dated link opens this snapshot in the history

https://discoveria.ai/entry/erdos-647-chatgpt-deep-research-deepseek-deepthink-1a#releve-1

To understand ≈ 20 s reading time, estimated

What it changes

Erdős problem #647 belongs to number theory. According to the wiki, the proof put forward by these AI tools, without significant human involvement, is incorrect: it therefore does not count as a solution, but the entry keeps a record of the attempt.

What remains unclear

The sources read identify neither the error found in the proof nor the respective role of the three tools in this attempt. The wiki has been frozen since June 30, 2026, so a reassessment published since then would not appear there.

For experts

Sources, method, key facts, status history, report an error

Status

Withdrawn

Recorded on · github.com · wiki

Outside the verification path

  1. Announced
  2. Wiki frozen
  3. Recordedwithdrawn
What this status means

Source reading : Source read word for word (level 3 of 3)

Withdrawn or abandoned by its author, or marked incorrect by the reference source.

Dated archive: status recorded on the wiki frozen on Jun 30, 2026

Full history

Sources

  • Main sourcegithub.com · wikipage read word for word · consulted on Oct 12, 2026
  • Reference listerdosproblems.comlink only, reading not recorded
  • Corroborationterrytao.wordpress.compage read word for word · consulted on Oct 17, 2026 · We have created a github repository to coordinate this process
  • Repositorygithub.com · CONTRIBUTING.mdpage read word for word · consulted on Oct 17, 2026 · this status is an unofficial crowdsourced classification of the problem

Method

Source: the “AI contributions to Erdős problems” wiki of the teorth/erdosproblems repository (a repository presented by Terence Tao in his blog post of August 31, 2025); frozen on June 30, 2026 (commit c8ad430, “freeze”) and read on October 12, 2026 in the git repository. Category 1(a), “AI standalone” (AI alone; no comparable literature known; no significant human involvement). Humans named by the wiki: none; AI systems: ChatGPT Deep research, DeepSeek DeepThink, Gemini. Date given by the wiki: January 28, 2026. Exact text: “Incorrect proof found”; red flag (“incorrect work”, according to the wiki's legend). Literature cited by the wiki: none. Status of the problem in the teorth/erdosproblems community database (data/problems.yaml, unofficial classification, snapshot of October 12, 2026 with no commit identified, current state, not that of June 2026): open, but a finite example would prove it if it is true (informal_status=verifiable); no formalised solution known (formal_status=unformalized). This status concerns the problem, not this contribution. Problem page not read by DiscoverIA: https://www.erdosproblems.com/647. The DiscoverIA registry also holds an entry that groups several problems, this one included; the two entries may overlap. DiscoverIA status: withdrawn, because the wiki classes this contribution as incorrect (red flag). DiscoverIA has not checked this error itself. Recorded on October 12, 2026.

Limits

DiscoverIA has not checked this contribution itself.

Key facts

Claimed by
Not shown (withdrawn entry)
announced on Jan 28, 2026
Nature
new result
Field
Mathematics (Erdős problem #647 (number theory))
Wiki category
AI standalone (IA seule ; littérature comparable inconnue ; implication humaine non significative)
Wiki verdict
« Incorrect proof found » : travail incorrect (légende du wiki)
Checked by
wiki maintainers (red flag)
Sources
4 : 3 read word for word, 1 link only
This entry
AI draft, not reviewed

Status history

Only one observation so far.

  1. 01

    First observation:WithdrawnCurrent status

    marked incorrect by the wiki (red flag, “Incorrect work”)

    Source: github.comread word for word

An observation is added; none is ever erased.

In the same set

AI contributions to Erdős problems (wiki by T. Tao, frozen on June 30, 2026) · entry 254 of 521, by problem number

See all 521 entries

Report an error or suggest a source

How DiscoverIA uses your address and how to exercise your rights: privacy policy.

Is your result listed?What each status requires, correcting this entry, replying to it.