Gold vs US-Dollar

At least 6 complete tests are required; 3 are available.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive

n/aToo few tests (3 tests, 6 needed) (3 tests, 2 won)

Direction

n/aToo few tests (3 tests, 6 needed) (21 of 36 calls right in 3 tests)

Turning points

n/aToo few tests (3 tests, 6 needed) (8 turns in 3 tests, 0 without a turn)

Error vs baseline

3% lowerError ratio 0.97; 1.00 is a tie.

Tests won

2 / 3Complete rolling backtests; ties count as no win.

Test period

2023-11-01 to 2026-10-0112 observations ahead per test.

80% band coverage

50%Observed outcomes inside the band across all stored test windows.

• Band coverage uses all stored test windows, including model-selection windows when present; it does not determine the confidence label.
• The 80% band held too few outcomes; interpret its width with care.
• Evaluated 2026-11-14 against the cached history through 2026-10-01.
• This is an evaluation of the serving model; it does not establish a winner across four model classes.