LAB / WMSI-EXP-087
Executable World as Experimental Representation.
Can language-generated interactive worlds serve as scientifically useful representations rather than demos?
01 / QUESTION
Executable Worlds and Simulation
Can language-generated interactive worlds serve as scientifically useful representations rather than demos?
This is a protocol scaffold, not a completed experiment or a frozen execution plan. No measured effect or research conclusion is claimed here.
Hypothesis to test
The manipulation described below produces a reproducible, condition-specific change in the measured system behavior or internal state that is not explained by the ordinary controls.
Ordinary competing explanation
The observed pattern is explained by ordinary sampling variation, prompt/representation artifacts, surface lexical cues, evaluator bias, or the known product/runtime mechanics captured by the controls.
02 / PLANNED DESIGN
How we intend to test it
Ask a model to instantiate a toy system from a formal spec, perturb it interactively, and compare behavior with the reference equations/rules.
Controls
Hand-coded reference simulation; multiple generated worlds.
What we would measure
Rule fidelity, state persistence, causal consistency, intervention accuracy.
Access and instruments
Ordinary software or API access. This describes access requirements, not verified readiness on our Spark.
Browser/HTML runtime; generated simulation; test harness.
Before a full run
Feasibility=NOW; priority=P1. Before confirmatory execution, run a small pilot to estimate variance/cost, freeze the scoring rules, and assign a run-count target.
Model revisions, final prompts, sample sizes, cost limits, and scoring rules must be settled through the pilot and protocol-freeze process.
03 / INTERPRETATION
What could fool us
Unspecified rules, visual plausibility mistaken for causal fidelity, hidden state not exposed.
What would weaken the idea
If generated worlds routinely violate the source model, they are visualization toys rather than instruments.
Observation, inference, speculation, unknowns, and apparatus errors will be labeled separately. One striking transcript cannot establish a general effect.
04 / RECORD
Evidence we plan to preserve
World source/spec, generated code, state snapshots, intervention log, reference simulation outputs.
Planned visual evidence
State-trace comparison; intervention ledger.
No research runs or raw datasets are published for this experiment. The September 26, 2026 registry and protocol compendium (version 1.0) are the sources for this planning record.
Back to all 90 experiments