When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design

[2608.01378] When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2608.01378 (cs) [Submitted on 2 Aug 2026 ( v1 ), last revised 24 Aug 2026 (this version, v2)] Title: When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design Authors: Shuangxiu (Max)Ma, Wenhe (Zachary) Zhao View PDF HTML (experimental) Abstract: Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensive evaluation - an experiment, a first-principles simulation, or a full training run. Machine-learning surrogates that predict these outcomes are increasingly used not only to propose candidates but to grade them, and even to feed their own predictions back into the search as though they were measurements. Through mathematical analysis validated on three exhaustively ground-truthed design tasks, we establish when this practice is safe, what any certificate of safety must cost, and when the substitution provably pays. Predictive accuracy cannot anchor trust: near-perfect R^2 is compatible with worst-possible selections, and screening N candidates inflates the over-prediction at the selected candidate by a quantifiable "selection tax" with matching upper and lower bounds. Safety follows instead from an architectural rule - predictions may propose and train without restriction, but every certified conclusion must rest on true evaluations - which is sufficient with no assumptions on the surrogate, and necessary, since admitting predictions into certification with the standing of measurements opens a deterministic self-confirmation failure mode. We derive the minimal criterion under which a model may act as an oracle (rank preservation, not accuracy), show that trust must be purchased through selection-aware audits that are optimal in query complexity, and prove a dichotomy fixing when audited surrogates cut certified evaluation cost. Across 432 surrogate fits over six task-regime conditions, the audit statistic tracks deployed search performance at Spearman rank correlation 0.80-0.99, while the rank correlation of R^2 with deployed regret falls as low as 0.33; audited screening reduces certified oracle cost by a measured factor of 25. Comments: 47 pages (18 pages main text, 29 pages Supporting Information), 9 figures, 2 tables, 70 references. SI contains complete proofs of all theorems, extended experiments, and the verification methodology Subjects: Machine Learning (cs.LG) MSC classes: 62G15, 68T05, 62L05 ACM classes: G.3; I.2.6 Cite as: arXiv:2608.01378 [cs.LG] (or arXiv:2608.01378v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.01378 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Shuangixu(Max) Ma [ view email ] [v1] Sun, 2 Aug 2026 16:59:29 UTC (1,759 KB) [v2] Mon, 24 Aug 2026 22:09:05 UTC (1,776 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation 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)

Related documents

• When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design#670714
• Why Model Credibility Isn't Enough: -Rethinking Trust in Simulation Architectures#282853
• Exploring the design approach to embedding ethics in technology#30003
• From static oversight to distributed corrigibility#696675
• Traditional and Experimental Approaches to Free Will and Moral Responsibility#701791