ExperimentEXP-2026-0002v0.1

R1 — deterministic semantics comparison against four baselines

Two facts (one stable, one changing at hours 8 and 16), eight queries over 17 simulated hours. B1 stateless recomputes every query; B2 fixed 6-hour TTL; B3 adds workflow memory; B4 an evented compound agent with event-driven invalidation. AER-0 matches B4 on zero stale answers, zero stable refreshes and workflow reuse, needs one more recomputation (3 vs 2) because its tension policy refreshes proactively, and is alone in blocking a no-provenance fact and catching a conflicting write.

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: AER's different ownership and update semantics survive into observable runtime behaviour when compared with progressively stronger baselines.

Setup

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

Runs

run_count

controls

B4 deliberately stronger than B3 so ordinary event invalidation and external memory are not attributed to AER.

metrics

verdict

AER_DISTINCT_ON_TESTED_SEMANTICS

table

B1_stateless

stale: 0
recomputation: 8
stable_refresh: 0
volatile_refresh: 0
workflow_reuse: 0
model_swap_preserves_state: false
blocks_no_provenance: false
catches_conflict: false

B2_fixed_ttl

stale: 2
recomputation: 4
stable_refresh: 2
volatile_refresh: 2
workflow_reuse: 0
model_swap_preserves_state: true
blocks_no_provenance: false
catches_conflict: false

B3_memory_tools

stale: 2
recomputation: 4
stable_refresh: 2
volatile_refresh: 2
workflow_reuse: 6
model_swap_preserves_state: true
blocks_no_provenance: false
catches_conflict: false

B4_evented_agent

stale: 0
recomputation: 2
stable_refresh: 0
volatile_refresh: 2
workflow_reuse: 6
model_swap_preserves_state: true
blocks_no_provenance: false
catches_conflict: false

AER-0

stale: 0
recomputation: 3
stable_refresh: 0
volatile_refresh: 3
workflow_reuse: 6
model_swap_preserves_state: true
blocks_no_provenance: true
catches_conflict: true

Interpretation

interpretation: Not a dominance result. Persistent memory across model swap, workflow reuse and selective event-driven refresh are not unique to AER once the baseline is strengthened; the measured difference collapses to state-mutation semantics (provenance gate, optimistic version conflict, candidate/verify/commit authority).

Limitations

limitations: B4 is a reference implementation of event-driven behaviour, not a real production framework (structural closure PARTIAL).
Says nothing about intelligence, speed, cost in other environments, or whether an attractor exists.

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.

Results

Source	Relation	Target	Status	ID
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`produces`	`RST-2026-0001` R1 comparison table	`ACTIVE`	`REL-2026-0112`

Recorded fields

completed_at: 2026-09-08

Relations

Source	Relation	Target	Status	ID
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`runs_on`	`SYS-2026-0001` AER-0 — Adaptive Epistemic Runtime MVP	`ACTIVE`	`REL-2026-0105`
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`uses_benchmark`	`BEN-2026-0002` AER-0 architecture-comparison suite (R1–R6)	`ACTIVE`	`REL-2026-0106`
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`tests`	`THY-2026-0001` Asymmetric spacetime tension: temporally heterogeneous world knowledge	`ACTIVE`	`REL-2026-0107`
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`tests`	`THY-2026-0002` Canonical symbolic state and candidate → verify → commit authority	`ACTIVE`	`REL-2026-0108`
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`tests`	`THY-2026-0003` Intelligent architecture attractor	`ACTIVE`	`REL-2026-0109`
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`extends`	`EXP-2026-0001` AER-0 MVP v0.1 closure: are the invariants executable?	`ACTIVE`	`REL-2026-0110`
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`produced`	`ART-2026-0015` AER-0 MVP v0.1 Architecture Comparison R1 `artifact://evemisslab/adaptive-epistemic-systems/AER-0_MVP_v0.1_Architecture_Comparison_R1.zip`	`ACTIVE`	`REL-2026-0111`
`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`produces`	`RST-2026-0001` R1 comparison table	`ACTIVE`	`REL-2026-0112`
`EXP-2026-0003` R2 — source-grounded structural comparison with LangGraph 1.2.11	`extends`	`EXP-2026-0002` R1 — deterministic semantics comparison against four baselines	`ACTIVE`	`REL-2026-0121`

History and provenance

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0002/

Machine-readable

/ai/experiments/EXP-2026-0002/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