FUURAA AI Knowledge Library · Browser-local verification tool

AI Claim Evidence Record Verifier

Check a FUURAA AI-claim evidence-record JSON locally in your browser for rule identity, claim, source, evaluation design, artefacts, applicability boundary, evidence state and review chronology. The file is not uploaded to FUURAA.

Tool statusPublicly usable · browser-local processingVerification rulefuuraa.ai-claim-evidence-record/v1Sources checked4 August 2026

Verification workspace

Load a record, then close eight structural checks.

Choose a local JSON file, paste content, or load a blank template or clearly marked complete fictional example. Verification reads only the text in this page.

AI-claim evidence-record JSON

Privacy boundary: this tool does not submit, store or transmit the selected file. Continue to handle sensitive or restricted material under your organisation's rules.

Applicability boundary

This tool checks whether the record is structurally reviewable—not whether the claim is true.

It can check

Whether JSON parses and declares the exact v1 record rule
Whether claim, source, evaluation, artefact, boundary or judgment fields are missing
Whether source and review dates contain an obvious reversal

It cannot prove

That linked content is true, publisher identity valid or artefacts untampered
That study design is valid, results reproducible or the evidence-state judgment sound
That a system is safe, deployment-ready or legally, audit or certification compliant

FUURAA analysisAutomated verification should first reject records that omit identity, comparison design, excluded uses or accountability. Real evidence judgment still requires a reviewer to open primary sources, inspect raw artefacts, repeat consequential measurements, seek contrary evidence and limit the conclusion to the tested population, language, geography and workflow.

Standards and method sources

Verification rules connect to primary specifications while preserving each source's own boundary.

Internet Standard · December 2017IETF RFC 8259 · JSON Data Interchange Format

Defines the JSON grammar and interoperable representation parsed by this browser-local tool.

Boundary: Syntactically valid JSON says nothing about the truth, origin or completeness of its contents.

↗Internet-Draft · 16 June 2022JSON Schema 2020-12 · Validation Vocabulary

Provides the structural-validation concepts behind required fields, types, enumerations and formats.

Boundary: This page applies a focused FUURAA v1 rule set; it is not a general JSON Schema implementation.

↗W3C Recommendation · 30 April 2013W3C PROV-DM · The PROV Data Model

Frames provenance through entities, activities, agents, derivations and responsibility.

Boundary: The FUURAA record borrows provenance concepts but is not a normative PROV serialisation.

↗Published 26 January 2023NIST AI RMF 1.0

Connects review to context, affected people, measurement, governance and continuing risk management.

Boundary: Voluntary and use-case agnostic; it does not prescribe this record or confer certification.

↗Published 26 July 2024 · page updated 8 April 2026NIST AI 600-1 · Generative AI Profile

Adds generative-AI concerns including provenance, measurement, information integrity and human oversight.

Boundary: Its actions still need prioritisation for the actual system, people and decision context.

↗

Open the AI claim record builder →Enter AI Evidence Atlas →Return to AI Knowledge Library →