Home / Claims and dates / PC-019
Priority claim · PC-019
Monitoring Removal Test
The claim - verbatim
Michael Darius Eastwood first described the 'Monitoring Removal Test' - a specific named protocol proposal for probing whether an AI system's alignment behaviour persists when external supervisory apparatus is removed - in the book Infinite Architects (ISBN 978-1806056200) published on 2 January 2026, and referenced it as a programme element in the Executive Summary published on 22 February 2026. Priority is over the specific named formulation, not over the wider deceptive-alignment and evaluation-under-oversight discourse (Hubinger et al. 2019; Anthropic alignment-faking arXiv:2412.14093, December 2024).
Anchored evidence
- ISBN 978-1806056200
- research/papers/executive-summary.html (datePublished 2026-02-22; three references to 'Monitoring Removal')
- priority-claims.html
- OSF DOI 10.17605/OSF.IO/6C5XB
Limits and citation guidance - what this claim does not support, and how to cite it
Limits. Proposed protocol only; not externally validated or industry-standard.
Verify this claim. The source register is /research/priority.json (this claim is PC-019 in claimsLedger[]). The public ledger view is /priority-claims. The verification method for redacted evidence/... pointers is documented at /research/evidence-spine.html. Available public programme records can be inspected at osf.io/6c5xb (DOI 10.17605/OSF.IO/6C5XB). Their availability is not a declaration that every claim has been independently verified.
← Back to Claims and dates · public ledger view · publication-oriented priority record · home.