The Graviteron: A Unit for the Weight of Independent Evidence

Status of This Memo

This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79.¶

Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet-Drafts is at https://datatracker.ietf.org/drafts/current/.¶

Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress."¶

This Internet-Draft will expire on 5 May 2027.¶

Copyright Notice

Copyright (c) 2026 IETF Trust and the persons identified as the document authors. All rights reserved.¶

This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (https://trustee.ietf.org/license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document.¶

Table of Contents

1. Introduction

Systems that check claims about AI outputs, data or actions often report a confidence score whose meaning differs from one system to the next. Scores are added when they should not be, keys of one party are counted as independent voices, old checks keep full weight forever, and contradictions disappear into an average.¶

The Graviteron addresses this by fixing the quantity being reported. It does not measure truth. It measures how far the available independent, signed evidence moves the odds of a claim, on a logarithmic scale whose zero means "no evidence either way". The quantity is the weight of evidence introduced by A. M. Turing and I. J. Good [GOOD1950], measured in decibans.¶

Two implementations conform to this document if they produce the same readings, within the stated tolerances, for the test vectors of Section 6. A unit is useful only when independent implementations agree; the vectors exist for that purpose.¶

This document is related to the Gravit Epistemic Verification Protocol [I-D.gravit-gevp], which defines signed evidence Records and grouping by independent source. The Graviteron can be computed from such Records, but it is defined independently of any product or protocol, and the decision of whether a claim may be called a fact is out of scope.¶

2. Conventions and Terminology

The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 [RFC2119] [RFC8174] when, and only when, they appear in all capitals, as shown here.¶

Claim:

A statement that can be true or false, for example that a payment occurred or that an output was produced by a given model.¶

Operator:

An independent party that checks claims. One operator may hold several signing keys; they remain one operator.¶

Verdict:

The signed result of an operator for a claim: true, false, or null (no result).¶

Sensitivity, specificity:

The measured probability that the operator returns true for a true claim, and false for a false claim. They are estimated from data, for example with the Dawid-Skene method [DAWID1979].¶

Deciban (dB):

Ten times the base-10 logarithm of a likelihood ratio or odds factor.¶

3. Definition

The Graviteron G of a claim, given the evidence E, is:¶

   G = 10 * log10( O(claim | E) ) - 10 * log10( O(claim) )

where O denotes odds. With independent operators this equals the sum of the operators' contributions:¶

   G = sum over operators i of  g_i

   g_i = 10 * log10( sens_i / (1 - spec_i) )   if verdict_i = true
   g_i = 10 * log10( (1 - sens_i) / spec_i )   if verdict_i = false

Implementations MUST clamp sensitivity and specificity to the interval [1e-6, 1 - 1e-6] before computing g_i.¶

4. Required Properties

A conforming implementation MUST satisfy all of the following.¶

1. Zero point: with no counted evidence, G = 0.¶
2. Sign: a confirmation by an operator better than chance gives a positive contribution; a contradiction gives a negative one.¶
3. Additivity: contributions of independent operators add.¶
4. Sybil invariance: adding keys to one operator does not change G.¶
5. Dynamics: with a half life, a contribution halves after one half life and is restored when the check is renewed.¶
6. No silent evidence: an operator with a null verdict, or without measured sensitivity and specificity, contributes nothing, and the reading MUST say so in its notes.¶
7. Never a bare point: every reading carries an interval (Section 5.2) that narrows as independent operators are added.¶
8. Visible contradiction: if any counted operator signed false, the reading MUST be flagged as contested, and the flag MUST NOT be removed by averaging.¶

5. The Reading

A Graviteron reading MUST contain: the value G in decibans; an interval; a verbal band; the number of independent operators that contributed; the contradiction flag; the contribution of each operator; and notes for every record that counted nothing.¶

   [ G + d(q_lo) - d(a / (a + b)),  G + d(q_hi) - d(a / (a + b)) ]

6. Test Vectors

Twenty-one test vectors, with inputs (records, operator parameters, ages, half life, interval level) and expected readings, are published as JSON [VECTORS]. Tolerances are 1e-6 dB for G and for each contribution, and 1e-4 dB for the interval bounds. Four of them, for operators with sensitivity and specificity of 0.9/0.9 and 0.8/0.95:¶

7. Implementation Status

One reference implementation exists (Python, Apache-2.0) [GRAVITERON]; it passes the test vectors in continuous integration. No independent implementation exists yet. An open call for independent implementations is made through the Open Verifiable AI Consortium. This section is to be removed before publication as an RFC.¶

8. Security Considerations

The Graviteron is only as sound as the independence of the operators and the measurement of their reliability. An attacker who controls several operators that appear independent inflates G; Sybil invariance protects only against several keys of one known operator. Deciding which operators are independent is out of scope and SHOULD follow a documented procedure, for example the grouping by independent source in [I-D.gravit-gevp].¶

Overstated sensitivity or specificity inflates every contribution of that operator. Reliability estimates SHOULD be published with their data and sample sizes.¶

A high G is not a proof. Presenting a reading without its interval, operator count and contradiction flag invites false precision and is not conforming.¶

9. IANA Considerations

This document has no IANA actions.¶

Author's Address