Author

Gaston Besanson

h-index 3 View on Semantic Scholar

We have 3 of 12 papers

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.

#artificial intelligence Preprint Sep 2026

Compiling Sufficient Governance Context from Declared Losses and Reachable States: Exact Observation-Contract Synthesis with Cardinality and Cost Objectives

We call the object this paper derives and certifies a minimal sufficient governance context: given a finite reachable-state model, a deterministic declared verdict, and candidate observable attributes, we compute sufficient observation sets, distinguish attributes that are individually indispensable from contracts that...

Gaston Besanson · 1 citation

Jul 2026

SARC-DQ: Runtime Data-Quality Gating for Agentic AI: Silent Evidence Defects, the Incompetence Shield, and Downstream-Only Remediation

Evidence integrity is a systems axis distinct from model capability; mitigation depends on enforcement placement and predicate coverage; mitigation depends on enforcement placement and predicate coverage.

Gaston Besanson · arXiv.org · 2 citations

#artificial intelligence Preprint Aug 2026

One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI

A remediation-induced control coupling is formalized and a remediate-and-regate protocol is given that restores per-action soundness in the current bounded, idempotent setting under its stated assumptions.

Gaston Besanson · 0 citations