agent-harness / configs /experiments /E11_study4_reliability.toml
cuber12's picture
Publish agent harness research code and paper artifacts
d61821a verified
Raw
History Blame Contribute Delete
542 Bytes
schema_version = 1
experiment_id = "E11"
name = "study4_stochastic_reliability"
mode = "protocol_interface"
description = "Reduced prespecified Study 4 stochastic reliability sensitivity over a sparse balanced manifest."
harness_ids = ["H000", "H007"]
edit_interface_ids = ["P002", "P003"]
repository_ids = ["R001", "R002", "R003"]
model_ids = ["M002", "M003", "M004"]
embedding_id = "EMB002"
task_split = "study4_fresh"
context_budgets = [65536]
seeds = [0, 1, 2]
repetitions = 1
max_tool_calls = 12
max_test_runs = 2
timeout_seconds = 1800