Frozen pilot explorer · no live model calls

One world.
Private views.
Auditable change.

A research engine for persistent social agents that advances one canonical history, keeps user-owned context isolated, and lets deterministic code—not a language model— decide what becomes true.

Completed artifact/pilot study. It does not claim an emergent society, human-like memory, validated security, or a deployed blockchain integration.

Conceptual architectural model of one shared neighborhood beneath two separate private view layers
Conceptual representation · the scientific diagrams and measurements are reproduced from the tracked pilot data.

Read the same world through two context policies.

The event remains in canonical history under both conditions. What changes is whether fact-bearing memory can enter the resident’s scoped observation at the terminal probe.

Context policy
Day 3 · evening
ledger · 8f1a…6c3e
Canonical world information trace Twenty-five residents connected by a sparse public event trail. Color and shape show exposure and grounded answering.
exposed grounded answer no grounded answer

The artifact is complete. The scientific claim remains bounded.

Forty-five seven-day worlds crossed three scenarios, five architecture conditions, and three seeds. A second evaluation held nine terminal histories fixed and reran the same 25 interviews under all five context policies.

45
complete longitudinal worlds
11,807
recorded model calls across both stages
90 / 90
world and controlled artifacts verified
401 / 401
private-overlay isolation checks passed

The model proposes.
The engine commits.

Residents receive a scoped observation and propose a typed action. Deterministic validation rejects invalid transitions before a hash-linked event is appended. Exact replay means replaying those recorded transitions—not asking the provider to regenerate the same prose.

  1. 01
    ObserveCanonical state + permitted private context
  2. 02
    ProposeTyped language-model action
  3. 03
    ValidateRules, scope, time, place, provenance
  4. 04
    CommitAppend-only transition + before/after hashes
event_04f1 { "actor": "mira-sol", "type": "post", "accepted": true } before 3a78…19c2 → after 8f1a…6c3e

Prior exposure stayed equal. Grounded answering did not.

This is an operational provenance endpoint—not a validated measure of human memory. The no-memory condition also bundles observation-memory and reflection-retrieval removal.

full context no memory · nine worlds per condition

Large descriptive separation: full minus no-memory = 0.742, bootstrap 95% interval [0.533, 0.853].

Not confirmatory: only three paired seed blocks; randomization p = 0.2496 and no targeted comparison survived Holm correction.

Negative findings retained: planning did not improve attendance; full worlds produced no reflections and no new reciprocal relationships.

Public commitments. Private composition. Selective proof.

Canonical world Shared commitments

Accepted transitions, public consequences, ordering, and integrity hashes.

User-owned overlay Private context

Conversation, preferences, private memories, and personalized composition.

Future verification Selective disclosure

Prove an authorized transition or policy result without publishing the private input.

Architectural fit, not implementation claim. The pilot does not run on a blockchain and does not prove a zero-knowledge circuit. A next phase could map selected ledger commitments and policy predicates onto Midnight’s public/private state model.

Midnight documentation ↗ Network overview ↗

What this work earns the right to claim.

A reproducible substrate for studying persistent social agents; deterministic transition authority and replay; isolated private overlays; and a bounded result that persistent context access separated prior exposure from delayed grounded answering in this pilot.

Not claimed

Believable human behavior

Emergent society

General security

Planning benefit

Blockchain deployment

Inspect the method, every result, and all 45 runs.

Read the full paper