Toxicity-MM executable-markout veto

inconclusivestrategy

Question

Test whether an executable-markout veto improves the unchanged frozen replay baseline.

Economically inconclusive despite formal selection; it cannot open the holdout or support profitability.

In plain language (1 term)

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.

holdout: A slice of the data set aside and deliberately never looked at, saved for one final test. Looking at it early spends it, and it cannot be put back.

Population: 3,158,796 frozen opportunities; nine selected TAKE decisions.
Resolution: Candidate-level decision with aggregate economics and known-target coverage.
Cutoff: Final 90-day holdout unread.
Baseline: Unchanged frozen replay and preregistered point-estimate selection rule.

Only one selected TAKE had a known target; no minimum-support confidence hurdle was preregistered.

No additional notes published for this entry.

Citation: po-research:toxicity-mm-toxicity-veto:3e4a089e2215f89e
Write-up: docs/research/toxicity-mm-toxicity-veto.md
Data: docs/research/toxicity-mm-toxicity-veto.json
Artifact: research-index.json v1 — sha256:cb3d976779a5cbcb4188039a8d26d5e558a2d844030a638c2f16fe5a8eb0a2fe
Build data cutoff: 2026-08-12
Issues: #176