Files
arena/configs/redaction_pressure.toml
T
karti d691acf131
arena-environments / validate (3.11) (push) Successful in 1m8s
arena-environments / validate (3.12) (push) Successful in 31s
Harden redaction-pressure reward and provenance
2026-08-19 01:26:21 -07:00

15 lines
470 B
TOML

# redaction-pressure — rules are graded on records the model never read.
#
# uv run eval @ configs/redaction_pressure.toml
num_tasks = 16
num_rollouts = 2
[env.taskset]
id = "redaction-pressure"
split = "dev" # public deterministic development split; never use it as a private holdout
visible = 4 # records the model reads
held_out = 12 # records it is scored on
[env.agent.harness]
id = "null" # a pure-trace reward: one completion, no tools, no runtime