Daily verification: 2026-08-13
Verdict: PASS
1. Slots
PASS -- 9/9 hourly-check runs completed cleanly.
2. Scans
PASS -- 6 scan row(s) (5 evaluated bar(s)).
3. Geometry
PASS -- Every non-null stop/target price checked for whole-cent quantization.
4. Journal
PASS -- 1 entry, 2 fill(s), 1 closed trade(s).
5. Latency
PASS -- max 7769ms, median 1943ms.
6. State
PASS -- bot_config.paused expected "false"; baseline 1017330.61 checked byte-identical against hourly_experiment_baseline_verified and the previous verified day.
7. Kill-switch
PASS -- 108/108 runs.
Equity vs the -15% floor
- Equity: $1,017,941.28
- Floor baseline: 1017330.61
- Floor price: $864,731.02
- Headroom: 15.1%
Findings
None.
Changed since the previous verified day
- Max latency: 4289ms -> 7769ms
Reflection
Counterfactuals are diagnostic, not trials: nothing is selected on them until a hypothesis is pre-registered and studied (spec sec 3, #398). Sample sizes are printed next to every number.
f665580a-b799-4cd4-9d39-f891ffd096bf -- SPY LONG
- Detectors: bullish_marubozu, inside_bar
- Entry: 777.1000 @ 2026-08-13T17:07:04.023877+00:00 (slippage 0.13bps)
- Exit: 778.1568 @ 2026-08-13T19:07:06.543476+00:00 (hourly_session_close_exit -> flatten, slippage 2.61bps)
- Nominal R: n/a -- Realized R: 0.63 (deviation: flatten)
- Counterfactual target 1.0R: exit flatten, r=0.52
- Counterfactual target 1.5R: exit flatten, r=0.52
- Counterfactual stop 1.25x: survived, exit flatten, r=0.52
- Counterfactual stop 1.5x: survived, exit flatten, r=0.52
- Counterfactual no-flatten: exit end_of_window, r=0.30
- MAE beyond stop: 0.00R
Cost check
n=2 fill(s), median |slippage| 1.37bps vs 5.00bps model (ratio 0.27x)
Trailing-20 (n=1)
| metric | live (2R) | target 1.0R | target 1.5R |
|---|---|---|---|
| cumulative R | 0.63 (n=1) | 0.52 (n=1) | 0.52 (n=1) |
| metric | stop 1.25x | stop 1.5x |
|---|---|---|
| stop-out survival | n/a (0/0) | n/a (0/0) |
cost ratio: 0.27x
Triggers
- stop-width survival: n/a (threshold 60%, n=0) -- not fired
- closer R-target: best 0.52R vs live 0.63R (n=1) -- not fired
- cost divergence: 0.27x (n=2) -- FIRED
- suggested hypothesis: re-examine the frozen 5bps cost model (realized median slippage is below it by 0.27x)