EXP-000002

Stop-loss share denominator — data-integrity check

Accepted Data integrity Research source: Hybrid 19 Aug 2026

System: Platform / methodology research — not tied to a single system.
Git commit: c101f55

Hypothesis

An observed stop-loss share above 100% indicates the denominator excludes some closed trades.

Controlled change

Closed-trade count switched from wins+losses to all closed trades including break-even; win/loss rates kept on decided trades only.

Dataset & conditions

Extracted deal lists, all 14 systems.

Before / After

Before

SUPREMACY stop-loss share: 100.05%

After

After including 9 break-even trades in the denominator: 100.00%

Validation

Out-of-sample, walk-forward, Monte Carlo and forward results are shown only where they exist as data. None exist for this entry.

Decision

Accepted

Share can no longer exceed 100%; extracted totals now match each report header exactly.

AI involvement

Model: Claude (Anthropic)
What AI did: Traced the >100% share to break-even trades missing from the denominator and drafted the fix; totals were re-verified against every report header.
Human review: Reviewed and approved by a human

AI-assisted entries are published only after human review; entries generated by AI without that review are withheld by the build pipeline. AI does not predict markets, and no entry claims otherwise.

Backtest improvement does not imply future improvement. The more experiments run, the more likely some succeed by chance — this log exists partly so that multiple-testing risk stays visible instead of hidden.