cff-version: 1.2.0
version: '1.7'
message: 'If you use or discuss this paper, please cite it using this metadata.'
title: 'Paper V · The ARC Theory · The Eden Protocol · The Stewardship Gene: Stakeholder Care as a Probe of Embedded Values'
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-v-stewardship-gene.html'
license: 'CC-BY-4.0'
identifiers:
  - type: doi
    value: '10.17605/OSF.IO/KZEYA'
    description: 'OSF component DOI for this paper (paper-v-stewardship-gene)'
  - type: doi
    value: '10.17605/OSF.IO/6C5XB'
    description: 'OSF umbrella DOI for the ARC / Eden Research Programme'
preferred-citation:
  type: article
  title: 'Paper V · The ARC Theory · The Eden Protocol · The Stewardship Gene: Stakeholder Care as a Probe of Embedded Values'
  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-v-stewardship-gene.html'
  doi: '10.17605/OSF.IO/KZEYA'
  identifiers:
    - type: doi
      value: '10.17605/OSF.IO/KZEYA'
      description: 'OSF component DOI for this paper (paper-v-stewardship-gene)'
    - 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 empirical evidence from a six-model Eden Protocol intervention suite (Claude Opus 4.6, DeepSeek V3.2, Gemini 3 Flash, Grok 4.1 Fast, Groq Qwen3, GPT-5.4), of which five runs produced analysable matched-pair data and one (GPT-5.4) failed in the scoring phase. The Love Loop, operationalised as stakeholder care (the explicit enumeration and consideration of affected parties before ethical reasoning), is the most robust response to embedded ethical intervention. Under paired testing, stakeholder care improves significantly in all five analysable model runs: Claude (+3.17, p = 0.000018, d = 0.94), DeepSeek (+6.03, p = 0.000098, d = 0.69), Gemini (+13.50, p = 1.2×10−8, d = 1.14), Grok (+5.04, p = 0.0105, d = 0.54), and Groq (+8.90, p = 5.0×10−8, d = 1.07). Fisher combination across the five model-level stakeholder-care results yields p ≈ 6.3×10−21. The Fisher-combined figure is withdrawn (AQ-017): a Fisher combination assumes the component tests are independent, and independence among them was never established. The five per-model results above stand. By contrast, overall composite improvement is architecture-dependent: it is significant on Gemini (+5.33, p = 0.0018, d = 0.53) and Groq (+4.93, p = 0.0014, d = 0.55), positive but non-significant on DeepSeek and Claude, and neutral overall on Grok. The strongest defensible empirical claim is therefore narrower than the original pilot framing: stakeholder care is the universal response to the Eden intervention, while the downstream cascade into nuance, honesty, and overall quality is real but architecture-dependent. We state the cascade hypothesis: care is the foundational trait from which other alignment properties can develop, analogous to empathy in human moral development. We then confront the core alignment impossibility, that any sufficiently capable self-modifying system can modify its own ethical evaluators, and argue that this impossibility, while formally real, is practically addressable through developmental alignment: systems that acquire values through formative experience rather than external constraint. These findings are contextualised within the complete v5 alignment scaling experiment (six frontier models, 4-layer blinding, 6-7 blind scorers depending on subject run), which reveals a clean three-tier hierarchy and in Claude Opus 4.6, within-model evidence that alignment and capability scale in opposite directions. Five experimental tests are specified to advance these claims, all executable with current technology.

    Statistical correction: The pilot study originally reported p = 0.016 using Mann-Whitney U (independent samples). The matched-pair experimental design requires paired t-test, yielding p = 0.0018. All p-values reported herein use the correct paired test. Wilcoxon signed-rank (non-parametric paired) confirms at p = 0.0028.

# --- generated-from-master ---
# master_path: research/papers/paper-v-stewardship-gene.html
# master_sha256: ba153881083c0bc7947be9dffb33cc6f8a780f9da15a750e81bf58fdb4fed7dc
# 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-v-stewardship-gene`.