# drop-table-inference — the estimate is graded on the kills the model never saw.
#
#   uv run eval @ configs/drop_table_inference.toml --model <model-id>
num_tasks = 16
num_rollouts = 2

[env.taskset]
id = "drop-table-inference"
visible_kills = 1200     # kills the model reads, as a tally
held_out_kills = 40000   # kills it is scored on

[env.agent.harness]
id = "null"    # pure-trace reward: one completion, no tools, no runtime