LAB / WMSI-EXP-083
Research Reproduction Number (R_research).
When does an agent research system generate more useful follow-up work than the human/agent effort needed to sustain it?
01 / QUESTION
Agent Ecology and Environmental Persistence
When does an agent research system generate more useful follow-up work than the human/agent effort needed to sustain it?
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
Define research units, track each result’s downstream tasks/results, and estimate branching reproduction over time.
Controls
Different memory/routing/verification conditions; fixed-budget baselines.
What we would measure
R_research, useful-child fraction, depth, duplication, verification debt.
Access and instruments
Ordinary software or API access. This describes access requirements, not verified readiness on our Spark.
Task ledger; provenance graph; cost accounting.
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
Hidden shared memory, incomplete reset, accidental internet access, duplicate artifacts.
What would weaken the idea
If branching is mostly low-value duplication or R remains below one after costs, autocatalytic research is unsupported.
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
Environment snapshot, artifact provenance, agent identities, reads/writes, lineage, reset logs.
Planned visual evidence
Branching-process plot; research lineage graph.
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