AI ethics evidence index Search
Source-linked daily record
Evidence record 7550 · automatically gathered

Sparsity and Out-of-Distribution Generalization

Explaining out-of-distribution generalization has been a central problem in epistemology since Goodman's "grue" puzzle in 1946. Today it's a central problem in machine learning, including AI alignment. Here we propose a principled account of OOD generalization with three main ingredients. First, the world is always presented to experience not as an amorphous mass, but via distinguished features (for example, visual and auditory channels). Second, Occam's Razor favors hypotheses that are "sparse,

Record details

Published: 8 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Transparency
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Safety & alignment · Shared topic: Transparency

CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling

arXiv · 9 March 2026

Shared topic: Safety & alignment · Shared topic: Transparency

Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion

arXiv · 6 March 2026

Shared topic: Safety & alignment · Shared topic: Transparency

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

arXiv · 11 March 2026

Shared topic: Safety & alignment · Shared topic: Transparency

Emulating Clinician Cognition via Self-Evolving Deep Clinical Research

arXiv · 11 March 2026

Shared topic: Safety & alignment · Shared topic: Transparency

COMPASS: The explainable agentic framework for Sovereignty, Sustainability, Compliance, and Ethics

arXiv · 11 March 2026

Shared topic: Safety & alignment · Shared topic: Transparency

Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning

arXiv · 13 March 2026

How to cite this record

ethics.ai (8 March 2026), “Sparsity and Out-of-Distribution Generalization,” evidence record 7550, https://ethics.ai/record/7550 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.