Title: Paper IV.a: Alignment Response Classes Under Inference-Time Depth
Author: Michael Darius Eastwood
Publication date: 2026-03-16
Version: v1.4
Revised: 2026-08-23
OSF DOI: 10.17605/OSF.IO/MB9R6
Canonical URL: https://www.michaeldariuseastwood.com/research/papers/paper-iv-a-baked-in-vs-computed-alignment.html

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). The most important methodological finding is that two models that
appeared positive under v4 unblinded evaluation reverse under v5 blinding,
demonstrating that scorer bias can flip the measured direction of alignment
scaling. We therefore treat 'baked-in' and 'computed' alignment not as
established internal architectures but as working hypotheses layered above a
stronger empirical result: alignment response to depth is
architecture-dependent, and capability scaling does not predict alignment
scaling.

Key findings (quotable)
-----------------------
- 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.
- The most important methodological finding is that two models that appeared positive under v4 unblinded evaluation reverse under v5 blinding, demonstrating that scorer bias can flip the measured direction of alignment scaling.
- We therefore treat 'baked-in' and 'computed' alignment not as established internal architectures but as working hypotheses layered above a stronger empirical result: alignment response to depth is architecture-dependent, and capability scaling does not predict alignment scaling.

Priority claims relevant to this paper
--------------------------------------
- PC-002 (2024-12-08): The embedded-correction alignment thesis was first stated
on the public evidentiary record under this dated formulation in the 8 December
2024 manuscript. Constitutional AI (Anthropic 2022) is independent prior work on
value-embedded training at the software level; priority here is over the
specific published framing and dated wording.
- PC-032 (2026-02-09): The specific empirical treatment of capability-alignment
independence - that capability improvements do not entail alignment improvements
and the two axes scale independently - was first published in Paper III on 9
February 2026. Bostrom (2012) orthogonality intuition is prior work; scope is
over the specific empirical treatment on this date.
- PC-033 (2026-02-09): The specific tripartite alignment hierarchy (embedded /
imposed / boundary-layer) was first published in Paper III on 9 February 2026.
Layered-alignment taxonomies are prior work; scope is over the specific
tripartite formulation.
- PC-030 (2026-01-22): The six-frontier-model empirical panel (Claude, DeepSeek,
Gemini, Grok, Groq Qwen, GPT) was first published as this specific comparative
study on 22 January 2026. Priority is over this specific study on this date, not
over panel-testing methodology in general.

Citation
--------
Michael Darius Eastwood (2026). Paper IV.a: Alignment Response Classes Under
Inference-Time Depth. The ARC Theory (the Theory of Artificial Recursive
Creation) · ARC/Eden experiments, OSF DOI 10.17605/OSF.IO/MB9R6.
https://www.michaeldariuseastwood.com/research/papers/paper-iv-a-baked-in-vs-computed-alignment.html

Notes
-----
Hardware framings held at the site's already-published two-sentence concept
ceiling: safety constraints at hardware level through cryptographic tokens in
silicon, TRL 0-1, no prototype. No enabling implementation detail is stated in
this companion file. Balanced-ternary computing is prior work (Setun 1958);
recursion as a structural concept is prior work (evolutionary theory,
self-modifying computation, quantum error correction).

Generated from master
---------------------
master_path: research/papers/paper-iv-a-baked-in-vs-computed-alignment.html
master_sha256: 057efd0c721649e91951ef51935822bc795e7f2317104ad2f5c1368e161c0fa6
builder: scripts/build-paper-companions.py

This block records the SHA-256 of the HTML master that produced this .txt. 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-companions.py --slug
paper-iv-a-baked-in-vs-computed-alignment`.