ExperimentEXP-2026-0005v0.1

R4 — policy mutation surface: scattered governance vs one mandatory boundary

For N ∈ {1, 4, 16, 64} canonical-write callers and R = 6 governance rules, policy sites and rule placements grow as N and N·R under scattered governance versus 1 and R under either a central application gate or AER-ECT; a new rule needs N caller edits versus one; a 75 % caller-local migration leaves 16 of 64 callers on the old contract. The counterweight is explicit: one omitted local rule has blast radius 1/N, a defect in the shared gate has blast radius 1, and under an equal-p toy omission model the expected exposed-caller fraction is identical for all three systems.

Research status: STABLE the current conclusions are relatively stable
Evidence level: E2 Controlled experiment
Result: MIXED
Data basis: DETERMINISTIC RUNTIME A deterministic scenario executed in a real runtime; the code and procedure are listed, and the numbers are what they are.
Version: 0.1
Updated: 2026-09-08
Created: 2026-09-08
Domain: AI Architecture, Evaluation, Agent Systems
Program: PRG-2026-0001 Adaptive Epistemic Systems
Authors: Neo.K (EveMissLab)
AI collaborators: Sol (GPT-5.6, OpenAI ChatGPT)

Hypothesis

hypothesis: Elevating epistemic governance into one mandatory boundary reduces policy scattering, migration surface and drift opportunity — without magically reducing expected harm.

Setup

software_environment: Python 3.11+, SQLite; no network, no external database, no LLM API required.

Procedure

procedure: Deterministic structural benchmark plus executable AER regression; CENTRAL_GATE and AER-ECT predicted and observed identical on policy topology.

Runs

run_count

metrics

verdict

CENTRALIZATION_REDUCES_SCATTERING_NOT_COMPUTATIONAL_CAPABILITY

rules

callers

at_64_callers

scattered

policy_sites: 64
rule_placements: 384
blast_radius_one_omission: 0.015625
migration_edits: 64
vulnerable_after_75pct_migration: 16

central_gate_and_aer_ect

policy_sites: 1
rule_placements: 6
blast_radius_one_omission: 1.0
migration_edits: 1
vulnerable_after_75pct_migration: 0

toy_omission_model_p_0_01

P_any_scattered: 0.9789
P_any_central: 0.0585
expected_exposed_caller_fraction_all_systems: 0.0585

Interpretation

interpretation: Centralization changes the distribution of failure — fewer opportunities for many small local defects, few opportunities for large shared ones — and makes new business callers free of policy replication. AER-ECT is reference-monitor-like (always invoked on the normal write path), not proven tamperproof.

Limitations

limitations: A model with an explicit toy assumption, not empirical defect data; 97.89 % is not a real-world defect rate.
Distributed replica/version skew of the central gate, hostile bypass and tamperproofness not modelled.

Reproduction

reproduction_instructions: Extract the round's FINAL bundle; python -m pytest -q; python -m examples.research_assistant_demo; python -m benchmarks.<round benchmark>. Checksums in SHA256SUMS.txt.

Recorded fields

completed_at: 2026-09-08

Relations

Source	Relation	Target	Status	ID
`EXP-2026-0005` R4 — policy mutation surface: scattered governance vs one mandatory boundary	`runs_on`	`SYS-2026-0001` AER-0 — Adaptive Epistemic Runtime MVP	`ACTIVE`	`REL-2026-0137`
`EXP-2026-0005` R4 — policy mutation surface: scattered governance vs one mandatory boundary	`uses_benchmark`	`BEN-2026-0002` AER-0 architecture-comparison suite (R1–R6)	`ACTIVE`	`REL-2026-0138`
`EXP-2026-0005` R4 — policy mutation surface: scattered governance vs one mandatory boundary	`tests`	`THY-2026-0006` AER-ECT: a mandatory epistemic commit transaction boundary	`ACTIVE`	`REL-2026-0139`
`EXP-2026-0005` R4 — policy mutation surface: scattered governance vs one mandatory boundary	`extends`	`EXP-2026-0004` R3 — epistemic commit transaction vs scattered and centralized application gates	`ACTIVE`	`REL-2026-0140`
`EXP-2026-0005` R4 — policy mutation surface: scattered governance vs one mandatory boundary	`produced`	`ART-2026-0018` AER-0 MVP v0.1 Architecture Comparison R4 Policy Mutation `artifact://evemisslab/adaptive-epistemic-systems/AER-0_MVP_v0.1_Architecture_Comparison_R4_Policy_Mutation.zip`	`ACTIVE`	`REL-2026-0141`
`EXP-2026-0006` R5 — complete mediation and bypass resistance	`extends`	`EXP-2026-0005` R4 — policy mutation surface: scattered governance vs one mandatory boundary	`ACTIVE`	`REL-2026-0145`

History and provenance

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0005/

Machine-readable

/ai/experiments/EXP-2026-0005/index.json

Snapshot

AI-SNAPSHOT-v0.1-fe85b9694a45

Provenance

source: EveMissLab research collection: Adaptive Epistemic Systems (真本體論13)
extracted_by: Splice (Claude Code), reading the canonical UTF-8 sources and each lab's own result reports
extracted_at: 2026-09-11
generator: tools/extract_aes/extract.py
claim_boundary: status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports