ExperimentEXP-2026-0009v0.1

PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry

Adds N3 constraint competition, a nonlinear constraint-field family, plus an adversarial geometry chosen to break additive/log-odds mappings, keeping every v0.1 threshold. N3 reaches Level 3 in all three geometries; N2 keeps agreement 0.8546 and small update/intervention error but its held-out representation JS 0.053327 crosses the 0.05 gate under adversarial geometry, so it is classified behavioural convergence only. Independent families under the linear diagnostic: {N0, N1}, {N2}, {N3}; robust across all three geometries: two.

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: Model Representation, Evaluation, Formal AI
Program: PRG-2026-0001 Adaptive Epistemic Systems
Authors: Neo.K (EveMissLab)
AI collaborators: Sol (GPT-5.6, OpenAI ChatGPT)

Hypothesis

hypothesis: A structurally distinct third family also converges, and convergence survives an evidence geometry designed against additive mappings.

Setup

model_ids: MOD-2026-0001 N0 — signed support
MOD-2026-0002 N1 — ordinal tournament
MOD-2026-0003 N2 — signed graph
MOD-2026-0004 N3 — constraint competition
MOD-2026-0005 Bayesian reference (exact posterior / Beta-Bernoulli / joint common-cause / HMM)
dataset_ids: DAT-2026-0001 PACC synthetic evidence worlds
benchmark_ids: BEN-2026-0001 PACC micro-lab protocol v0.1 (frozen gates)
software_environment: Python; deterministic seeded generators; no network, no LLM.

Runs

run_count

random_seeds

20260908
8 secondary seeds (smaller scale)
5 adversarial seeds near primary scale

controls

shuffled-target mapping
constant prediction
broken composition (v0.6+)
target-local refit (v0.7+)

metrics

verdict

THIRD INDEPENDENT FAMILY CONVERGES; ROBUST PACC-A GATE REMAINS OPEN

adversarial

N0

agreement: 0.90818
heldout_js: 0.023921
level: 3

N2

agreement: 0.85455
heldout_js: 0.053327
level: 1

N3

agreement: 0.90162
heldout_js: 0.014454
level: 3

five_seed_adversarial_level3_rate

N0: 1.0
N1: 1.0
N2: 0.6
N3: 1.0

independent_convergent_families

pacc_a

false

Interpretation

interpretation: Probability-like convergence has a nontrivial basin, not a demonstrated universal attractor: the N3 result weakens the 'disguised additive accumulator' explanation, and N2 shows convergence is not guaranteed for every architecture under every geometry.

Limitations

limitations: Independence is supported under the preregistered linear diagnostic only, not proof of deep nonlinear nonequivalence.
N2's boundary is adversarial sensitivity around the threshold, not a universal phase boundary.

Reproduction

reproduction_instructions: Extract the version's FINAL bundle; python -m pytest -q; run the version's primary script with the recorded seed; docs/PACC_LAB_v0.N_RESULTS.md and docs/EXPERIMENT_PROTOCOL_v0.N.md are inside the bundle.

Results

Source	Relation	Target	Status	ID
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`produces`	`RST-2026-0007` v0.2 adversarial geometry: N3 converges, N2 crosses the representation gate	`ACTIVE`	`REL-2026-0180`

Recorded fields

completed_at: 2026-09-09

Relations

Source	Relation	Target	Status	ID
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`runs_on`	`SYS-2026-0002` PACC-Lab — micro-lab harness for the convergence conjecture	`ACTIVE`	`REL-2026-0169`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`uses_benchmark`	`BEN-2026-0001` PACC micro-lab protocol v0.1 (frozen gates)	`ACTIVE`	`REL-2026-0170`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`uses_dataset`	`DAT-2026-0001` PACC synthetic evidence worlds	`ACTIVE`	`REL-2026-0171`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`uses_model`	`MOD-2026-0001` N0 — signed support	`ACTIVE`	`REL-2026-0172`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`uses_model`	`MOD-2026-0002` N1 — ordinal tournament	`ACTIVE`	`REL-2026-0173`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`uses_model`	`MOD-2026-0003` N2 — signed graph	`ACTIVE`	`REL-2026-0174`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`uses_model`	`MOD-2026-0004` N3 — constraint competition	`ACTIVE`	`REL-2026-0175`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`uses_model`	`MOD-2026-0005` Bayesian reference (exact posterior / Beta-Bernoulli / joint common-cause / HMM)	`ACTIVE`	`REL-2026-0176`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`tests`	`THY-2026-0005` PACC conjecture — the four-level convergence ladder	`ACTIVE`	`REL-2026-0177`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`extends`	`EXP-2026-0008` PACC-Lab v0.1 — E0–E4: first micro-witness	`ACTIVE`	`REL-2026-0178`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`produced`	`ART-2026-0022` PACC-Lab v0.2 N3 Adversarial FINAL `artifact://evemisslab/adaptive-epistemic-systems/PACC-Lab_v0.2_N3_Adversarial_FINAL.zip`	`ACTIVE`	`REL-2026-0179`
`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`produces`	`RST-2026-0007` v0.2 adversarial geometry: N3 converges, N2 crosses the representation gate	`ACTIVE`	`REL-2026-0180`
`EXP-2026-0010` PACC-Lab v0.3 — learned source reliability without an oracle	`extends`	`EXP-2026-0009` PACC-Lab v0.2 — third family (N3) and adversarial evidence geometry	`ACTIVE`	`REL-2026-0191`

History and provenance

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0009/

Machine-readable

/ai/experiments/EXP-2026-0009/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