24 lines
987 B
TOML
24 lines
987 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
|
|
|
|
[env.agent.runtime]
|
|
# ⚠️ REQUIRED since verifiers 0.3.1, which changed the default agent runtime from
|
|
# `subprocess` to `prime` — a REMOTE sandbox. Without this the run exits
|
|
# `SystemExit: not authenticated with prime` before a single rollout, having already created
|
|
# its output directory and a zero-line traces.jsonl, so it reads as a failed eval rather than
|
|
# an unauthenticated one. Nothing here needs a sandbox: the reward is a pure function of the
|
|
# trace and the harness is `null`.
|
|
type = "subprocess"
|