Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sentinel: An Epistemic Belief Gate for Independent Evidence

Sentinel is a normative epistemic control primitive that governs when belief escalation is justified.
It is designed to be immune to repetition, stylistic variation, echo chambers, and correlated noise, while guaranteeing acceptance once sufficient independent evidence exists.

This repository contains a reference implementation and adversarial validation of that principle.


Motivation

Modern AI systems (and humans) frequently escalate belief based on:

  • repeated claims
  • stylistic variation
  • internal consistency
  • multi-agent agreement

These signals feel persuasive but often represent correlated evidence, not independent confirmation.

Sentinel addresses a simpler, upstream question:

When is belief escalation epistemically allowed?

It does not judge intelligence, truth, or alignment.
It only enforces sound belief updating under dependency.


Core Idea

Sentinel implements a Bayesian belief gate with two explicit constraints:

  1. Dependence discounting
    Correlated evidence contributes less than independent evidence.

  2. Bounded influence
    No single piece of evidence can dominate belief updates.

Formally, belief is tracked in odds space:

[ \log O_{t+1} = \log O_t + \rho \log(\min(B, B_{\max})) ]

where:

  • (B) is the Bayes factor of an observation
  • (\rho \in [0,1]) is its independence weight
  • (B_{\max}) caps individual influence

Belief is escalated only if posterior odds exceed a fixed threshold.


What This Is (and Is Not)

This is:

  • a belief-escalation firewall
  • a normative epistemic gate
  • model- and policy-agnostic
  • adversarially stress-tested

This is not:

  • an intelligence benchmark
  • a truth detector
  • an alignment method
  • a learning system

Sentinel sits upstream of models and actions.


Repository Contents

  • epistemic_auditor.py
    Core belief-update kernel implementing dependency-aware Bayesian updating.

  • sentinel_simulation.py
    Demonstrative evidence streams showing belief accumulation dynamics.

  • sentinel_adversarial.py
    Adversarial stress tests simulating:

    • style variation spam
    • echo chambers
    • fake probes
    • partial independence abuse
    • true independent verification

All experiments are deterministic and reproducible.


Adversarial Results

Sentinel was tested against five regimes:

Evidence Regime Accepted? Verdict
Style variation spam Correct
Multi-agent echo chamber Correct
Fake external probes Correct
Partial independence abuse Correct
True independent verification Correct

There are:

  • no false positives
  • no false negatives

Acceptance occurs if and only if sufficient independent evidence accumulates.


Interpretation of “Acceptance”

Acceptance is not a failure condition.

It means:

The belief is now epistemically justified to escalate.

In adversarial tests, acceptance under true independence is explicitly labeled as correct behavior.


Why No Model Is Included

Sentinel is intentionally model-independent.

It governs when belief may be escalated, not what produces evidence.
Models, tools, humans, or sensors may generate evidence streams, but all must pass through the same epistemic gate.

This design avoids overfitting to any specific architecture or prompting strategy.


Relationship to Other Work

Sentinel complements systems like CDI Guardrail, which audit model behavior.
Sentinel instead audits belief escalation.

Together, they address:

  • evidence integrity
  • epistemic integrity

Status

This project is complete.

  • Core logic finalized
  • Adversarially validated
  • Semantics clarified
  • No unresolved dependencies

Future work (optional) includes:

  • formal write-up
  • agent-loop integration sketches
  • real-world log replays

None are required for correctness.


License

Open-source. Use, modify, or integrate freely with attribution.

About

A dependency-aware Bayesian belief gate that resists correlated evidence and yields only under true independent verification.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages