15 lines
470 B
TOML
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
|