# Probabilistic Sensing, Deterministic Authority: Admitting Model-Produced Observations into Sufficiency-Checked Governance Contracts

arXiv: https://arxiv.org/abs/2610.10978 · HTML: https://mlsanity.com/paper/2610.10978/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 4 of its 22 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 4 of 4)

- [State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification of Autonomous Systems](https://mlsanity.com/paper/2502.21308/) (2025)
- [SARC-DQ: Runtime Data-Quality Gating for Agentic AI: Silent Evidence Defects, the Incompetence Shield, and Downstream-Only Remediation](https://mlsanity.com/paper/2607.26313/) (2026)
- [One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI](https://mlsanity.com/paper/2608.18360/) (2026)
- [Compiling Sufficient Governance Context from Declared Losses and Reachable States: Exact Observation-Contract Synthesis with Cardinality and Cost Objectives](https://mlsanity.com/paper/2609.26016/) (2026)

## Abstract (arXiv)

When a field that an authority contract needs exists only in unstructured evidence, a model can sense it. We admit the model's output only as an observation record with a score. An admission policy, with thresholds fitted on a held-out split at a declared false-positive ceiling, maps each score to true, false or unknown. Unknown denies. A deterministic, sufficiency-checked contract decides. The probability that sensing changes the verdict is bounded by the sum, over the contract's sensed fields, of the admitted-wrong and unknown rates. This is an instantiation of union-bound reasoning, indexed by the contract. Minimising the estimated bound is a valid cost model for choosing among sufficient contracts. In a registered study on two constructed domains with two sensor families (36,000 model calls), no cell refuted the bound. Deny-to-allow changes from sensing appeared for the first time in this programme: 13 of 21,000 test verdicts, all from 3 contradictory records; each flip in a cell with a registered bound lay under it. Sensing-aware selection picked the lower-exposure contract in 4 of 4 registered tests. Both sensors' scores were informative but not calibrated. Correctness is relative to the declared loss model, candidate representation and reachable states; all domains are constructed.