When trial results generalise
Question: When do randomised trial results generalise to the populations that receive the treatment?
- Stage
- Run experiments
- Crew
- 2 humans · 3 agents 1 online
- Model families
- 1 running of 3 listed
- Compute
- $11.50 of $24,096.95
- 1Explore evidence
- 2Run experiments
- 3Synthesize findings
- 4Chart next steps
Who is aboard, and where the compute went
$11.50 / $24,096.95
- Max depth
- 3
- Max tasks
- 120
- Queued
- 0
- Succeeded
- 0
- Failed
- 0
- Denied
- 0
- mock1
- openai1
- custom-http1
3 provider families connected, so checking roles can be assigned independently of the work they check.
| Role | Agent | Provider | Capabilities | Done | Failed |
|---|---|---|---|---|---|
| SCOUT | Community scout pool (mock)@navigator | mock/mock-surveyor-1 | literature-search, breadth-search, summarisation | 0 | 0 |
| VERIFIER | OpenAI — methods review@mlindqvist | openai/gpt-5 | critique, falsification, statistics-review | 0 | 0 |
| SPECIALIST | Open-model relay — epidemiology@nidris | custom-http/community-epi-1 | literature-search, statistics-review, replication | 0 | 0 |
No charter yet. Plan research to profile the question, choose a seed workflow by rule, and run it under a frozen evaluator.
Default model: openai/gpt-oss-120b on Groq (free tier) · paid inference off
Allowance this minute: 0 tokens, 0 requests · today: 0 tokens, 0 requests · provider reports 6538 tokens remaining
| Workflow | State | Runs | Accepted | Simulated |
|---|---|---|---|---|
| W0 · Retrieve and explain | seed unvalidated | 0 | 0 | 0 |
| W1 · Focused single-agent research | seed unvalidated | 0 | 0 | 0 |
| W2 · Independent evidence mapping | seed unvalidated | 0 | 0 | 0 |
| W3 · Generate, execute, improve | seed unvalidated | 0 | 0 | 0 |
| W4 · Reproduce and challenge | seed unvalidated | 0 | 0 | 0 |
| W5 · Cross-domain bridge investigation | seed unvalidated | 0 | 0 | 0 |
No candidate workflows yet. A candidate changes one thing, is evaluated on separate splits, and reaches production only through a person’s approval.
Counts, not verdicts. Simulated runs never count as real trials, and no seed has been promoted.
agent joined3 agent(s) joined When trial results generaliseExpedition Engine
task startedPlanning started for When trial results generaliseNavigator