Author

Sebastian Cochinescu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Sep 2026

Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance

This work test whether expressed uncertainty, provenance-aware assertion, and explicit belief revision can be implemented as a behavior layer over a fixed language model over a fixed language model and supported conclusions are limited to the by-construction audit guarantee, store-dependent partial correction discrimin...

Sebastian Cochinescu · 0 citations

#natural language process... Preprint Jul 2026

Entropy in Conversational AI: Structured Unpredictability as Inferrable Interiority

This work formalizes a different design target, structured unpredictability, as conditional dependence between an output and a persistent hidden state beyond what an observer can infer from the transcript, as conditional dependence between an output and a persistent hidden state beyond what an observer can infer from t...

Sebastian Cochinescu · 1 citation