May 17, 2026 Not evaluated

Erdős problem #603: formalisation by Codex, GPT-5.5 (proof: Chojecki and GPT-5.4 Pro (2026))

The gist

The wiki of AI contributions to Erdős problems credits Codex and GPT-5.5, dated May 17, 2026, with the formalisation of the proof by Chojecki and GPT-5.4 Pro (2026) for problem #603.

DiscoverIA status on October 12, 2026: not evaluated, meaning no third-party evaluation found.

Status detailsDetails

AI draft, not reviewedWhat has not been reviewed?

Text written by an AI (DiscoverIA pipeline), on Oct 14, 2026. 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.

Follow Report

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 #603: formalisation by Codex, GPT-5.5 (proof: Chojecki and GPT-5.4 Pro (2026)) [Status: Not evaluated, snapshot 1]. DiscoverIA registry. https://discoveria.ai/entry/erdos-603-codex-gpt-5-5-2b#releve-1

BibTeX @misc, key discoveria-erdos-603-codex-gpt-5-5-2b-r1

@misc{discoveria-erdos-603-codex-gpt-5-5-2b-r1,
  author       = {{DiscoverIA}},
  title        = {Erdős problem #603: formalisation by Codex, GPT-5.5 (proof: Chojecki and GPT-5.4 Pro (2026))},
  howpublished = {DiscoverIA registry, entry erdos-603-codex-gpt-5-5-2b},
  note         = {Status “Not evaluated”, snapshot 1, recorded on October 12, 2026. Formalisation of a known result},
  year         = {2026},
  url          = {https://discoveria.ai/entry/erdos-603-codex-gpt-5-5-2b#releve-1},
  urldate      = {2026-10-12}
}

Dated link opens this snapshot in the history

https://discoveria.ai/entry/erdos-603-codex-gpt-5-5-2b#releve-1

To understand ≈ 30 s reading time, estimated

What it changes

The wiki sees a formalisation here: the proof is that of Chojecki and GPT-5.4 Pro (2026), and according to the wiki Codex and GPT-5.5 reportedly wrote a computer-checkable version of it. The wiki marks this proof as a full resolution (the legend of its flag). Problem #603 belongs to combinatorics and set theory.

What remains unclear

The sources read do not say which formal language the formalisation is written in, nor who has checked it. The October 12, 2026 record from erdosproblems.com gives the problem as “unformalized” (current state); the sources read do not say what this implies for this formalisation.

For experts

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

Status

Not evaluated

Recorded on Oct 12, 2026 · github.com · wiki

Step 1 of 4 on the scale: not evaluated. Next step: under review.

May 17, 2026Announced
Jun 30, 2026Wiki frozen
Oct 12, 2026Recordednot evaluated
nextTo follow

What this status means

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

The result is declared neither right nor wrong.

To move to “Under review”: a public review under way. To “Peer reviewed”: a journal publication or a review by named experts.

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 2(b), “Formalization” (secondary contribution). Humans named by the wiki: none; AI systems: Codex, GPT-5.5. Date given by the wiki: May 17, 2026. Exact text: “Formalization”. Proof to formalise: Chojecki and GPT-5.4 Pro (2026); wiki flag on this proof: green (“full resolution”, according to the wiki's legend); the wiki does not name the formal language on this line. 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): resolved other than by a yes-or-no answer (informal_status=solved); 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/603. DiscoverIA status: not evaluated (only the wiki's classification exists). Recorded on October 12, 2026.

Limits

Nature: formalisation (an already known result translated into a language a machine can check), not a discovery. DiscoverIA has not checked this contribution itself.

Key facts

Claimed by: Codex, GPT-5.5, according to the AI-Erdős wiki
announced on May 17, 2026
Nature: formalisation of a known result
Field: Mathematics (Erdős problem #603 (combinatorics ; set theory))
Wiki category: Formalization (contribution secondaire : formalisation)
Proof formalised: Chojecki and GPT-5.4 Pro's
Checked by: no verifier identified
Sources: 4 : 3 read word for word, 1 link only
Part of: AI contributions to Erdős problems (wiki by T. Tao, frozen on June 30, 2026)
This entry: AI draft, not reviewed

Status history

Only one observation so far.

01Oct 12, 2026
First observation:Not evaluatedCurrent status
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 238 of 521, by problem number

See all 521 entries

Report an error or suggest a source

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