Lebanon Gold Reserves

The tests show no consistent, material advantage over the no-change baseline.

Model: Agentic Investor TSFM (foundation model)

Accuracy vs naive

-1%Matches the no-change baseline over 8 tests (8 tests, 0 won)

Direction

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

Turning points

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

Error vs baseline

1% higherError ratio 1.01; 1.00 is a tie.

Tests won

0 / 8Complete rolling backtests; ties count as no win.

Test period

2017-06-01 to 2025-03-014 observations ahead per test.

80% band coverage

0%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 2026-11-15 against the cached history through 2025-03-01.
• This is an evaluation of the serving model; it does not establish a winner across four model classes.