agent runagent_runADR-0040
Agent run 019e4900…
Full provenance for the no-op agent's proposal of agent_proposed_xs_momentum. The row landed on a local BookState viarecord_provenance; promotion to a live runner still requires a named human approver (ADR-0019).
-0.10000.1000
operator
- kind
- agent
- model_artifact
- claude-opus-4-7
- identifier
- claude-opus-4-7/019e4900-0003-7000-8000-000000000003
- provenance_id
- 019e4900-0004-7000-8000-000000000004
leaderboard entry
method=agent_run · objective=rank_icn_buckets
5
sharpe_oos
0.00
features = ["momentum_126", "momentum_to_vol_ratio_20"]
horizon = 5, rebalance = "daily"
config_id = 8a4c09dc05fb
citation graph — typed-prefix cited_artifacts
2 cited · claude-opus-4-7/019e4900-000…Top row is this agent's identifier. Middle row: thenotes it cited. Bottom row (when present): notes those cited notes themselves build on (the indirect provenance). Every cited slug resolves against the writing manifest at propose-time (ADR-0015) — the agent cannot land a row citing a hallucinated source.
reproduce this run
$ python scripts/regenerate_agent_sample.pyThe script holds the pinned seed / UUIDs / clock and rewritessample_run.json. The Python drift test test_sample_run_matches_livere-runs build_sample on every CI build and asserts bytewise equality against the committed fixture.