Paper III released - Alignment Scaling Problem formalisation

The claim - verbatim

Michael Darius Eastwood first published the formally named 'Alignment Scaling Problem' framing - together with the architecture-dependent measured claim that external alignment approaches produce a median alignment scaling exponent alpha_align of approximately zero across the tested models, though Tier-1 models scaled positively and three of six had alpha_align of less than or equal to zero - on 9 February 2026 in Paper III under OSF DOI 10.17605/OSF.IO/6C5XB. The result is single-lab and awaits external replication.

Anchored evidence

• research/papers/paper-iii-alignment-scaling-problem.html (Paper III, JSON-LD datePublished 2026-02-09)
• OSF DOI 10.17605/OSF.IO/6C5XB and sister DOI 10.17605/OSF.IO/8FJMA
• research/priority.json priorityChain position 7
• priority-claims.html (external alignment cannot scale; status needs-replication)
• research/data/priority-record.json claim_id 'paper-iii-alignment-scaling-problem'

Limits and citation guidance - what this claim does not support, and how to cite it

Limits. Use verbs 'argued', 'proposed', 'reported', 'provides evidence for'; not 'proved'. Precursor prose in the 8 Dec 2024 manuscript is convergent, not causal against Anthropic. Do not present as an established scaling law.