Sigreg

Skill Tibsfox/gsd-skill-creator/src/sigreg

Sketched Isotropic Gaussian Regularization primitive. Scalar loss matching the embedding distribution to a standard-normal target via Cramér-Wold slicing and the Epps-Pulley empirical characteristic function test. Port of rbalestr-lab/lejepa (MIT). Default-off in v1.49.571.From its SKILL.md

Install

npx -y skills add Tibsfox/gsd-skill-creator --skill sigreg

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

1.9 KB, 407 tokens by cl100k_base, as published. Nobody here has run it

SIGReg — Sketched Isotropic Gaussian Regularization

Port of SIGReg from Balestriero & LeCun (2025, LeJEPA) arXiv:2511.08544v3. The primitive computes a scalar loss measuring how far an embedding distribution is from the standard-normal target, using Cramér-Wold slicing plus the Epps-Pulley empirical characteristic function test. Linear O(N·M·K) time, naturally differentiable, multi-GPU friendly (all_reduce over ECF averages).

Public API

import { sigreg } from './src/sigreg/index.js';

const loss = sigreg(embeddings);  // embeddings: number[num_samples][num_dims]
// scalar loss; use as L_total = L_pred + λ · loss

For telemetry:

import { sigregWithBreakdown } from './src/sigreg/index.js';

const { loss, perSliceStatistic, maxSliceStatistic, runTag } = sigregWithBreakdown(embeddings);

Configuration

Default matches the LeJEPA reference implementation:

const LEJEPA_DEFAULT_CONFIG = {
  numSlices: 1024,
  univariateTest: { numPoints: 17, sigma: 1.0 },
};

Feature flag

Default-off. Opt-in via .claude/gsd-skill-creator.json:

{
  "heuristics-free-skill-space": {
    "sigreg": { "enabled": true }
  }
}

Attribution

Ported from https://github.com/rbalestr-lab/lejepa under the MIT license. © Randall Balestriero and LeJEPA Contributors. See ../../license_notices.md.

Related modules

src/skill-isotropy/ — Skill Space Isotropy Audit (Phase 728) — read-only audit use case

What ships with it: 5 files

18.1 KB alongside SKILL.md, 5 of them executable

tests/

sigreg.test.tsruns10.6 KB

epps-pulley.tsruns2.5 KB
index.tsruns742 B
sigreg.tsruns2.3 KB
types.tsruns2.0 KB