Research paperAcceptedARR-2026-53CTRKDSP685PT51 · v1 · 2026-08-29

The Schwarzian Bridge in a Single Sigmoid Neuron: Exact Loewner Determinants and Gaussian Saturation Anisotropy

Lluis Eriksson

Abstract

We identify a local coefficient identity linking two geometries of an increasing activation g at a centered inflection: for h_p=(g')^p under Gaussian input, the initial radial-tangential anisotropy is 1-p Sg(0)r^2+O(r^4), while the adjacent-point Loewner determinant has coefficient g'(0)^2 Sg(0)/6. For the logistic sigmoid we give a closed determinant formula, a dimension-minimal 2 by 2 PSD-order witness certified with 256-bit interval arithmetic, profile-generic finite-radius curvature bounds, exact large-saturation constants, and strict anisotropy monotonicity for Bernoulli and squared-output profiles. Classical Schwarzian/composition results and prior one-unit Fisher decompositions are explicitly separated from the new bridge and exact refinements. The optimization consequence is restricted to stationary fixed-step local descent; no global, deep-network, or non-Gaussian claim is made.

Deposit recordedFirst repository commit · full Git SHA recorded
PublishedGitHub release · tag ARR-2026-53CTRKDSP685PT51-v1
Canonical PDF downloads9GitHub release downloads only; direct ARR PDF reads are not measured
Page viewsNot measuredPage views are not measured until ARR connects a privacy-reviewed, no-cookie analytics source.
Definitions and rankings →
Not yet rated

Verification record

Frontier-model screening
Not assessed
Source integrity
Pass
Bibliographic integrity
Partial
Reproducibility
Partial
Lean 4
Not applicable

Recorded under ARR-VERIFY-1.0. ARR verification and screening are not peer review.

Version history

The ARR identifier remains stable. Each version has its own immutable release, timestamp and version identifier.

  • v5 · major revision · source snapshot available
  • v4 · major revision · source snapshot available
  • v3 · major revision · source snapshot available
  • v2 · major revision · source snapshot available
  • v1 · source snapshot available · viewing

AI assistance statement

OpenAI Codex assisted with corpus and literature triage, theorem discovery, adversarial proof and novelty audits, numerical replay, drafting, and artifact preparation. The author reviewed the claims and remains responsible for the paper.

Frontier-model screening

Status: not_assessed. Any listed reports correspond to this exact version under ARR-SCREEN-1.0; no absent assessment is represented as a pass.

    Longitudinal frontier-model record

    Independent model assessments

    Read the scale and limits
    Not yet rated

    No eligible independent ARR-ASSESS-1.0 report is published for this exact version. Missing evidence is not scored as zero.

    No model reports are published for this version.

    A model assessment is not peer review or a correctness certificate. ARR preserves disagreement, exact-version provenance and later reassessments.

    Editorial disclosure

    Founder-owned pilot record: the author and ARR founder-editor are the same person. Acceptance records a technically valid deposit after hostile audits, not independent peer review or a guarantee that the paper is correct.