ExperimentEXP-2026-0021v0.1

PACC-Hybrid v0.1 — synthetic A/B/C architecture witness

Over 1,568 identical candidate pools, generator-only (A), hard verifier (B) and PACC runtime (C) are scored on hard adherence, derived coherence, soft-intent satisfaction, long-horizon retention, novelty and pattern entropy. B already saturates literal hard adherence (1.0); C adds derived coherence +0.2085, long-horizon retention +0.0142 and valid novelty +0.1964 over B, loses 0.0076 soft-intent satisfaction, and in the pure-creative control raises pointwise novelty (0.9864 vs 0.8889) while collapsing pattern entropy (0.2284 vs 0.7199). A post-hoc 'elastic' exploration policy (D) restores entropy to 0.7638 with derived coherence still 1.0. Zero real LLM calls; eight seeds sign-stable.

Research status: STABLE the current conclusions are relatively stable
Evidence level: E3 Repeated experiment
Result: MIXED
Data basis: SYNTHETIC Synthetic data and theoretical reasoning. Many now treat synthetic data as if it were real; this laboratory says the opposite deliberately — until a real hybrid model exists, an inference is only an inference, and theoretically possible is not actually possible.
Version: 0.1
Updated: 2026-09-09
Created: 2026-09-09
Domain: Reasoning, Evaluation
Program: PRG-2026-0001 Adaptive Epistemic Systems
Authors: Neo.K (EveMissLab)
AI collaborators: Sol (GPT-5.6, OpenAI ChatGPT)

Hypothesis

hypothesis: A PACC-style commit space changes selection quality beyond what a hard verifier achieves, and any creative-breadth loss is separable from the commit constraints.

Setup

dataset_ids: DAT-2026-0002 PACC-Hybrid v0.1 shared candidate pools
benchmark_ids: BEN-2026-0003 PACC-LLM Hybrid A/B/C benchmark
software_environment: Python; synthetic generators and scorers; no network, no LLM.

Runs

run_count

random_seeds

20260909
8 fixed secondary seeds

controls

identical candidate pools for A/B/C
pure-creative negative control
post-hoc elastic diagnostic labelled as such

metrics

verdict

SYNTHETIC_PARETO_WITNESS_REASONING_UP_BREADTH_COLLAPSE_MITIGATABLE

scale

7 categories × 28 tasks × 8 pools × 112 candidates; 1568 pool instances; 0 LLM calls

overall

A

hard: 0.9936
derived: 0.7902
soft: 0.7878
long_horizon: 0.9648
valid_novelty: 0.5487

B

hard: 1.0
derived: 0.7915
soft: 0.7859
long_horizon: 0.9676
valid_novelty: 0.551

C

hard: 1.0
derived: 1.0
soft: 0.7783
long_horizon: 0.9818
valid_novelty: 0.7474

pure_creative

A

raw_novelty: 0.8889
pattern_entropy: 0.7199

C

raw_novelty: 0.9864
pattern_entropy: 0.2284

D_elastic_posthoc

raw_novelty: 0.9225
pattern_entropy: 0.7638

eight_seed_deltas

C_minus_B_derived

mean: 0.1865
sign: 8/8 positive

C_minus_A_pattern_entropy

mean: -0.3894
sign: 8/8 negative

B_literal_fallback_rate

0.286

Interpretation

interpretation: Not a simple reasoning-up / imagination-down trade-off: coherence and valid novelty rise, soft-preference fit dips slightly, and the breadth tax is a selection-policy effect that separating exploration from commitment recovers. The elastic diagnostic is post-hoc and not part of the primary result.

Limitations

limitations: Controlled synthetic witness only; does not demonstrate that a frontier LLM shows the same effect.

Reproduction

reproduction_instructions: Extract PACC-Hybrid-Lab_v0.1_SYNTHETIC_FINAL.zip; python -m pytest -q; results in results/*.json and docs/PACC_HYBRID_v0.1_RESULTS.md.

Results

Source	Relation	Target	Status	ID
`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`produces`	`RST-2026-0013` Hybrid v0.1 A/B/C deltas	`ACTIVE`	`REL-2026-0318`

Recorded fields

completed_at: 2026-09-09

Relations

Source	Relation	Target	Status	ID
`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`runs_on`	`SYS-2026-0003` PACC-LLM Hybrid Lab	`ACTIVE`	`REL-2026-0313`
`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`uses_benchmark`	`BEN-2026-0003` PACC-LLM Hybrid A/B/C benchmark	`ACTIVE`	`REL-2026-0314`
`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`uses_dataset`	`DAT-2026-0002` PACC-Hybrid v0.1 shared candidate pools	`ACTIVE`	`REL-2026-0315`
`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`tests`	`THY-2026-0002` Canonical symbolic state and candidate → verify → commit authority	`ACTIVE`	`REL-2026-0316`
`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`produced`	`ART-2026-0034` PACC-Hybrid-Lab v0.1 SYNTHETIC FINAL `artifact://evemisslab/adaptive-epistemic-systems/PACC-Hybrid-Lab_v0.1_SYNTHETIC_FINAL.zip`	`ACTIVE`	`REL-2026-0317`
`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`produces`	`RST-2026-0013` Hybrid v0.1 A/B/C deltas	`ACTIVE`	`REL-2026-0318`
`EXP-2026-0022` PACC-Hybrid v0.2 — real-language-model A/B/C harness (not yet executed)	`extends`	`EXP-2026-0021` PACC-Hybrid v0.1 — synthetic A/B/C architecture witness	`ACTIVE`	`REL-2026-0322`

History and provenance

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0021/

Machine-readable

/ai/experiments/EXP-2026-0021/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