Not evaluated
Perceptron free energies and microscopic jamming (family 222)
The gist
On October 6, 2026, OpenAI announced, from an unreleased internal model, 4 manuscripts dated September 24, 2026 on perceptrons.
DiscoverIA status on October 12, 2026: not evaluated, meaning no third-party evaluation found.
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.
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
BibTeX @misc, key discoveria-oai-fam-222-perceptron-free-energies-microscopic-jamming-r1
@misc{discoveria-oai-fam-222-perceptron-free-energies-microscopic-jamming-r1,
author = {{DiscoverIA}},
title = {Perceptron free energies and microscopic jamming (family 222)},
howpublished = {DiscoverIA registry, entry oai-fam-222-perceptron-free-energies-microscopic-jamming},
note = {Status “Not evaluated”, snapshot 1, recorded on October 12, 2026. New result},
year = {2026},
url = {https://discoveria.ai/entry/oai-fam-222-perceptron-free-energies-microscopic-jamming#releve-1},
urldate = {2026-10-12}
}Dated link opens this snapshot in the history
To understand ≈ 30 s reading time, estimated
What it changes
A perceptron is a simple model that classifies data, and free energy is a quantity from statistical physics. If the manuscripts were correct, they would bring results on the free energy of the Ising and spherical random perceptrons, on the spherical perceptron with bi-orthogonally invariant disorder, and on microscopic jamming in the negative spherical perceptron.
What remains unclear
The Lean (a language in which a computer checks every step of a proof) is supplied by OpenAI only; formalization.yaml carries the note “review: status: unchecked”, and no third-party assessment is recorded. The sources read do not say which part of the 4 manuscripts the 3 Comparator statements cover.
For experts
Sources, method, key facts, status history, report an error
Status
Not evaluated
Recorded on · github.com · 222.md
Step 1 of 4 on the scale: not evaluated. Next step: under review.
- Announced
- Recordednot 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.
Sources
- Main sourcegithub.com · CONTENTS.mdlink only, reading not recorded
- Repositorygithub.com · …Ising-random-perceptron…link only, reading not recorded
- Repositorygithub.com · Microscopic-jamming-in…link only, reading not recorded
- Repositorygithub.com · The-spherical-perceptron…link only, reading not recorded
- Repositorygithub.com · …spherical-random…link only, reading not recorded
- Lean proofgithub.com · 222.mdpage read word for word
- Lean proofgithub.com · IsingFiniteness.leanlink only, reading not recorded
- Lean proofgithub.com · PerceptronFreeEnergy.leanlink only, reading not recorded
- Lean proofgithub.com · SphericalField.leanlink only, reading not recorded
Method
The openai/math repository contains 4 manuscripts: “The free energy of the Ising random perceptron”, “Microscopic jamming in the negative spherical perceptron”, “The spherical perceptron with bi-orthogonally invariant disorder” and “The free energy of the spherical random perceptron”. OpenAI supplies lean/docs/222.md and 3 Comparator files: lean/ComparatorChallenges/IsingFiniteness.lean, lean/ComparatorChallenges/PerceptronFreeEnergy.lean and lean/ComparatorChallenges/SphericalField.lean. According to history.md, no revision is reported. DiscoverIA status: not evaluated, meaning that no third-party evaluation has been found in the sources read. Set on October 12, 2026 from github.com (page read, quotation checked word for word: “describes the scope of the Lean formalization”).
Limits
No named third party: the recorded checks come from the claimant or from a platform tool. The claimant supplies a Lean proof; as of this date, DiscoverIA has found no independent verification of this proof or of the result.
Key facts
- Claimed by
- OpenAI (unreleased internal model)
announced on Oct 6, 2026 - Nature
- new result
- Field
- Mathematics (Probability and statistical mechanics)
- In openai/math
- family 222, section “Probability and statistical mechanics”, 4 manuscripts dated Sep 24, 2026
- Lean proof
- supplied by the claimant, marked “unchecked” (not reviewed) in its repository
- Revisions
- none reported by the claimant
- Checked by
- claimant (Lean supplied, not checked by a third party)
- Sources
- 9 : 1 read word for word, 8 links only
- This entry
- AI draft, not reviewed
Status history
Only one observation so far.
- 01
First observation:Not evaluatedCurrent status
Family with a Lean proof supplied by the claimant. No third-party check read; the source marks this proof as not reviewed (“unchecked”).
Source: github.comread word for word
An observation is added; none is ever erased.
In the same set
openai/math: 719 manuscripts in 372 families from an unreleased internal model · entry 216 of 372, by family number
- Not evaluated : GOE universality for random regular graphs with weak disorder (family 219)
- Not evaluated : Directional zero–one laws and ballisticity in random environments (family 220)
- Not evaluated : The Mézard–Parisi formula for diluted spin glasses (family 221)
- Not evaluated : Perceptron free energies and microscopic jamming (family 222)
- Not evaluated : Conformal limits of square-lattice random-cluster interfaces (family 223)
- Not evaluated : Critical and near-critical universality for Voronoi percolation (family 224)
- Not evaluated : Gaussian free field limits for the balanced six-vertex model (family 225)
Report an error or suggest a source
Thank you, your message was sent.
Sending failed. Try again, or write to contact@discoveria.ai.
Is your result listed?What each status requires, correcting this entry, replying to it.