3 papers
cs.CL2026
The Need for an External Observer Formalizing the Sufficiency Gap: A Mathematical Extension of Mixture Identifiability and Contextual Grounding in Sequence Models
Francesco Corielli
We construct a binary mixed-regime process with one deterministic textual regime and one random regime governed by an unobserved latent state. Even an ideal infinite-capacity seque…
cs.CL2026
When Is Next-Token Prediction Useful? Marginalization, Ergodicity, Mixture Identifiability, Local Sufficiency, RAG, Tools, and Programming
Francesco Corielli
Language models trained on observed sequences are often described as learning the conditional distribution of the next token given previous tokens. This description is only conditi…
stat.OT2025
George Udny Yule and the Interpretation of Regression Betas
Francesco Corielli
Initially applied in astronomy and geodesy, the linear regression model aimed to find the best estimates for parameters with predefined meanings. E.g., orbital elements, geodetic c…