Certifying Compressed Language Models: An Audit and a Statistical Toolkit

[2608.15046] Certifying Compressed Language Models: An Audit and a Statistical Toolkit Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.15046 (cs) [Submitted on 15 Aug 2026] Title: Certifying Compressed Language Models: An Audit and a Statistical Toolkit Authors: Amogh Singh View a PDF of the paper titled Certifying Compressed Language Models: An Audit and a Statistical Toolkit, by Amogh Singh View PDF HTML (experimental) Abstract: A fraction of a point of benchmark accuracy is the usual evidence that a compressed model is equivalent to its original. That quantity is least informative when two models are most alike: a net delta is what survives cancellation between opposing per-item changes, and cancellation is most complete in the regime equivalence claims occupy. Across an atlas of 1,707 paired model-by-task cells mined from public per-item evaluation dumps (1.3B-405B), churn runs roughly five times the net accuracy delta, and cells scoring identically to their baseline still disagree on individual items. In a preregistered audit of 17 equivalence claims from three registered frames (method papers, model cards, vendor documentation), 16 are eligible. None states a prospective numerical equivalence margin, and none releases task-matched per-item outputs, though 3 release outputs for other tasks only; 5 report too little to assess numerically, so a reader cannot check them at any sample size. We audit evidential sufficiency, not truth: no claim is called false. We supply the missing instrument: paired equivalence testing at a declared margin, with certification tables giving the items an evaluation needs, computed from disagreement observed under compression, not from independent-binomial variance. A controlled experiment pairs GPTQ and AWQ on byte-identical calibration samples across five seeds. Under the frozen eight-cell decision rule H3 is supported: changing the calibration draw was sufficient to reverse the observed method ordering in 5 of 8 confirmatory cells. The reporting standard we propose is five lines: declare a margin, run the paired test, report churn beside net delta, cite the sample size you met, release per-item outputs. It applies to any comparison between two models alike enough to be worth comparing. All per-item outputs, protocols and code are released. Comments: 109 pages, 3 figures, 20 tables. Artifacts and per-item outputs: this http URL Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.15046 [cs.LG] (or arXiv:2608.15046v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.15046 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.5281/zenodo.21939143 Focus to learn more DOI(s) linking to related resources Submission history From: Amogh Singh [ view email ] [v1] Sat, 15 Aug 2026 05:15:35 UTC (164 KB) Full-text links: Access Paper: View a PDF of the paper titled Certifying Compressed Language Models: An Audit and a Statistical Toolkit, by Amogh Singh View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Certifying Compressed Language Models: An Audit and a Statistical Toolkit#611000
• LLM-CEG: Extending the Classification Error Gauge Framework for Privacy Auditing of Large Language Models#138851
• Natural Identifiers for Privacy and Data Audits in Large Language Models#303210
• Auditing large language models: a three-layered approach#335808
• Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique#1063794