aliuyar1234/surgical-posttraining-diffing: Surgical Post-Training Diffing v0.1.0

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Author: Ali Uyar
Format: Recurso digital
Published: Zenodo 2026
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901078677651456
author Ali Uyar
author_facet Ali Uyar
contents <p>Initial public release of Surgical Post-Training Diffing.</p> <p>This release includes:</p> <ul> <li>source code for sparse PT-to-IT diffing, intervention masks, and evaluation</li> <li>experiment configs and test suite</li> <li>manuscript source in LaTeX</li> <li>final paper PDF</li> </ul> <p>Highlights:</p> <ul> <li>sparse answer-phase surrogate learning for PT-to-IT behavior shifts</li> <li>feature-mask intervention framework for capability and verbosity analysis</li> <li>evaluation code for fidelity, capability, verbosity, baselines, ablations, and bootstrap comparisons</li> <li>public-facing config cleanup with support for Hugging Face model IDs and relative local paths</li> </ul> <p>Included paper:</p> <ul> <li><code>paper/surgical-posttraining-diffing-ali-uyar.pdf</code></li> </ul> <p>Notes:</p> <ul> <li>this is a slim public source release</li> <li>large generated artifacts, caches, checkpoints, and internal planning documents are intentionally excluded</li> <li>some experiment configs reference artifacts that must be regenerated locally</li> </ul> <p>Author: Ali Uyar</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19347477
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle aliuyar1234/surgical-posttraining-diffing: Surgical Post-Training Diffing v0.1.0
Ali Uyar
<p>Initial public release of Surgical Post-Training Diffing.</p> <p>This release includes:</p> <ul> <li>source code for sparse PT-to-IT diffing, intervention masks, and evaluation</li> <li>experiment configs and test suite</li> <li>manuscript source in LaTeX</li> <li>final paper PDF</li> </ul> <p>Highlights:</p> <ul> <li>sparse answer-phase surrogate learning for PT-to-IT behavior shifts</li> <li>feature-mask intervention framework for capability and verbosity analysis</li> <li>evaluation code for fidelity, capability, verbosity, baselines, ablations, and bootstrap comparisons</li> <li>public-facing config cleanup with support for Hugging Face model IDs and relative local paths</li> </ul> <p>Included paper:</p> <ul> <li><code>paper/surgical-posttraining-diffing-ali-uyar.pdf</code></li> </ul> <p>Notes:</p> <ul> <li>this is a slim public source release</li> <li>large generated artifacts, caches, checkpoints, and internal planning documents are intentionally excluded</li> <li>some experiment configs reference artifacts that must be regenerated locally</li> </ul> <p>Author: Ali Uyar</p>
title aliuyar1234/surgical-posttraining-diffing: Surgical Post-Training Diffing v0.1.0
url https://doi.org/10.5281/zenodo.19347477