Toxicity-MM R1 terminal account
negative-resultstrategy
Question
Bind R1 to the preregistered fill-hazard result.
Verdict
R1 is a terminal non-candidate because the fill-hazard measurement is a negative stop.
In plain language (3 terms)
This site's own explanation of the words above. The verdict itself is published exactly as the research index records it and is not rewritten here.
- non-candidate
- Ruled out as something to build on. Later stages that depended on it do not get to run on a weaker substitute.
- fill-hazard
- An attempt to predict how likely a resting order is to fill in the next stretch of time, so that orders unlikely to fill could be skipped.
- negative stop
- The measurement came back negative and the work stopped there, by a rule agreed before the measurement ran. It was not retried under different settings until it came out differently.
- Population
- Exact frozen R1 account.
- Resolution
- One terminal account, no holdout run.
- Cutoff
- Final 90-day holdout unread.
- Baseline
- R1 promotion requires the upstream policy gate to survive.
Limitations
A terminal non-candidate cannot be combined or promoted.
Notes
No additional notes published for this entry.
Source
- Citation
- po-research:toxicity-mm-r1:018e1ba7049acfb8
- Write-up
- docs/research/toxicity-mm-r1.md
- Data
- docs/research/toxicity-mm-r1.json
- Artifact
research-index.jsonv1 — sha256:cb3d976779a5cbcb4188039a8d26d5e558a2d844030a638c2f16fe5a8eb0a2fe- Build data cutoff
- 2026-08-12
- Issues
- #175, #176