Commit Graph
2 Commits
Author SHA1 Message Date
karti d691acf131 Harden redaction-pressure reward and provenance
arena-environments / validate (3.12) (push) Successful in 31s
arena-environments / validate (3.11) (push) Successful in 1m8s
2026-08-19 01:26:21 -07:00
kartiandClaude Opus 5 c28d864766 Arena: the environment repository, and redaction-pressure
An environment is an eval you take the gradient of, so it carries obligations a
benchmark does not: a held-out slice, a counterweighted reward, and a demonstrated
0.0 floor and 1.0 ceiling. README states the three as house rules.

redaction-pressure is Forge's redact stage as a task. The first reward design scored
survivors — secrets caught, decoys kept, prose kept — and an empty ruleset tied the
best real attempt at 0.500, because destroying nothing keeps everything. Counting
removals instead puts inaction at 0.000, shredding at 0.380, and an oracle at 1.000.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-19 00:09:31 -07:00