Latvia Gold Reserves

The serving forecast made larger errors than the no-change baseline in these tests.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive

-81%Trails the no-change baseline over 8 tests (8 tests, 1 won)

Direction

n/aToo few tests (2 direction calls, 8 needed) (2 of 2 calls right in 1 test)

Turning points

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

Error vs baseline

81% higherError ratio 1.81; 1.00 is a tie.

Tests won

1 / 8Complete rolling backtests; ties count as no win.

Test period

2018-09-01 to 2026-06-014 observations ahead per test.

80% band coverage

88%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.
• Evaluated 2026-11-14 against the cached history through 2026-06-01.
• This is an evaluation of the serving model; it does not establish a winner across four model classes.