2,200 crude oil trials.
Zero promotions. Zero survivors.
The same sibling registry that closed 1,100 gold trials at one promotion and zero survivors ran the identical vocabulary a third time, on a third instrument: micro crude oil futures. Eleven strategy families, 200 seeds each, native one-minute bars, 2,200 real registered trials. Not one candidate reached the statistical promotion bar at all, the only one of this registry's three instrument legs where nothing did.
What this leg is
This page is not one of our own experiments. It reports on the same sibling research instrument behind our earlier MES registry piece and gold leg, extended to a third live instrument: MCL, the micro crude oil futures contract. Same registry, same discipline, same promotion bar, a third market. If a null result is durable, it should hold when the instrument changes and not just when the strategy vocabulary does.
Every trial in this leg was registered (the rule, the constraint set, and the running trial count) before the backtest that judges it ever ran, and benchmarked against a coin-flip twin sharing the identical structure, differing only in whether its trade direction comes from a signal or a hash. A promotion bar (a deflated Sharpe ratio, corrected for every trial the registry had already run, not just the one in front of it) decides whether a result is even worth a second look. Across this whole leg, nothing cleared it.
The leg, by the numbers
Eleven strategy families, the same vocabulary already tested on gold and on the original MES catalog, 200 seeds each, on native one-minute crude oil bars, against a fixed cost floor of 0.04 points round-trip.
| Metric | Value |
|---|---|
| Strategy families tested | 11 |
| Seeds per family | 200 |
| Real registered trials | 2,200 |
| Bar resolution | 1 minute (native) |
| Cost floor | 0.04 pts round-trip |
| Trials statistically promoted | 0 |
| Trials that reached a holdout | 0 |
| Trials that survived | 0 |
All eleven families closed clean: 200 of 200 seeds each, no trial in any of them reached the promotion bar. There was no candidate to hold for a sealed holdout and no candidate for a disposition rule to act on, because nothing in this leg ever cleared the first bar.
The cleanest leg of the three
This same registry has now run this eleven-family vocabulary on three instruments. On the original catalog, one candidate reached a sealed holdout and failed it. On gold, one candidate cleared the statistical bar and was killed by a standing cost-floor rule before its holdout was ever spent. On crude oil, nothing reached the bar at all: no promotion, no holdout question to ask, no disposition rule to apply. Of the registry's three instrument legs run under this eleven-family vocabulary, this is the only one where zero trials, out of every one registered, crossed the promotion bar.
What this is not
- Not our own research. This page reports a sibling instrument's results as a source of record; it is not a strategy Trade Agent Lab built, ran, or endorses.
- Not a live result. Every number above comes from a historical simulation against recorded price data, not real order fills.
- Not a recommendation. Nothing on this page is investment advice or a signal to trade MCL or any instrument. No candidate on this leg reached even a statistical promotion, let alone a holdout.
- Not evidence crude oil is unpredictable forever. Only that 2,200 pre-registered, trial-corrected attempts at this strategy vocabulary produced zero candidates worth a second look, under this specific window, resolution, and cost floor.
Provenance
Source: a sibling research instrument's trial registry (strategy-lab lineage), not Trade Agent Lab's own experimentation
Instrument: MCL (Micro WTI Crude Oil futures), 1-minute bars (native)
Training window: 2024-07-15 to 2025-12-31 (holdout window untouched by this leg)
Promotion bar: excess deflated Sharpe ratio > 0.95 at the honestly corrected effective trial count
Result: 0 of 2,200 registered trials promoted; 11 of 11 families closed clean