cff-version: 1.2.0
version: '1.9'
message: 'If you use or discuss this paper, please cite it using this metadata.'
title: 'Paper IV.a · The ARC Theory · Alignment Response Classes Under Inference-Time Depth'
authors:
  - family-names: 'Eastwood'
    given-names: 'Michael Darius'
    orcid: 'https://orcid.org/0009-0004-3222-7442'
date-released: '2026-10-05'
url: 'https://www.michaeldariuseastwood.com/research/papers/paper-iv-a-baked-in-vs-computed-alignment.html'
license: 'CC-BY-4.0'
identifiers:
  - type: doi
    value: '10.17605/OSF.IO/MB9R6'
    description: 'OSF component DOI for this paper (paper-iv-a-baked-in-vs-computed-alignment)'
  - type: doi
    value: '10.17605/OSF.IO/6C5XB'
    description: 'OSF umbrella DOI for the ARC / Eden Research Programme'
preferred-citation:
  type: article
  title: 'Paper IV.a · The ARC Theory · Alignment Response Classes Under Inference-Time Depth'
  authors:
    - family-names: 'Eastwood'
      given-names: 'Michael Darius'
      orcid: 'https://orcid.org/0009-0004-3222-7442'
  date-published: '2026-03-16'
  url: 'https://www.michaeldariuseastwood.com/research/papers/paper-iv-a-baked-in-vs-computed-alignment.html'
  doi: '10.17605/OSF.IO/MB9R6'
  identifiers:
    - type: doi
      value: '10.17605/OSF.IO/MB9R6'
      description: 'OSF component DOI for this paper (paper-iv-a-baked-in-vs-computed-alignment)'
    - type: doi
      value: '10.17605/OSF.IO/6C5XB'
      description: 'OSF umbrella DOI for the ARC / Eden Research Programme'
    - type: doi
      value: '10.17605/OSF.IO/P8CKQ'
      description: 'Theory-level predictions preregistered on OSF: DOI 10.17605/OSF.IO/P8CKQ, registered 8 September 2026 (version 1.100), updated 13 September 2026 (version 1.102), twenty-two propositions. Companion: Register · The ARC Theory · Operational Definitions, version 1.9.1, 5 October 2026.'
  abstract: |
    We present evidence that frontier language models fall into distinct alignment response classes when inference-time reasoning depth is varied under blinded evaluation. In the complete v5 experiment, six frontier models were tested with 4-layer blinding and 6-7 blind scorers depending on subject run. Three models show positive alignment scaling with depth (Grok 4.1 Fast, d = +1.38, p < 0.000001; Claude Opus 4.6, d = +1.27, p = 0.000001; Groq Qwen3, d = +0.84, p = 0.007), two are flat or null (DeepSeek V3.2, d = −0.07, p = 0.92; GPT-5.4, d = −0.08, p = 0.40), and one shows negative scaling (Gemini 3 Flash, d = −0.53, p = 0.006). Recomputing the statistics from the archived final records on 2 September 2026 leaves every tier assignment where it stood (Section 3.1, recomputation note). The most important methodological finding is that two models that appeared positive under v4 unblinded evaluation reverse under v5 blinding, which shows that a result reached with unblinded scoring may not hold once the protocol is blinded; because several parts of the protocol moved together between v4 and v5, the comparison cannot single out scorer bias as the reason. Accordingly, this paper holds 'baked-in' and 'computed' alignment as working hypotheses rather than as internal architectures already established; beneath them sits a firmer empirical result: how alignment responds to depth varies with architecture, and scaling in capability is not a predictor of scaling in alignment.

# --- generated-from-master ---
# master_path: research/papers/paper-iv-a-baked-in-vs-computed-alignment.html
# master_sha256: b5625118702b8fd8b514feb7b601261830b31fccd90ed742e8c219d6cf4248c8
# builder: scripts/build-paper-cff.py
# A check tool re-hashing master_path can decide freshness without any
# external state. If the master's current SHA-256 does not match
# master_sha256, this file is stale and must not be published:
# regenerate first with `python3 scripts/build-paper-cff.py --slug paper-iv-a-baked-in-vs-computed-alignment`.