Daily verification: 2026-09-01
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 3747ms, median 1916ms.
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.
8. pg_net stalls
PASS -- 0 timed-out HTTP response(s) at the :07 slots.
Equity vs the -15% floor
- Equity: $1,017,737.13
- Floor baseline: 1017330.61
- Floor price: $864,731.02
- Headroom: 15.0%
Findings
None.
Changed since the previous verified day
- Max latency: 5102ms -> 3747ms
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.
ac2966c9-e823-4b80-a6ca-d7fe0908f9e7 -- SPY LONG
- Detectors: hammer, bullish_pin_bar
- Entry: 761.4800 @ 2026-09-01T18:07:03.804982+00:00 (slippage 0.39bps)
- Exit: 760.8188 @ 2026-09-01T18:34:06.562213+00:00 (hourly_bracket_exit -> stop, slippage -0.51bps)
- Nominal R: -1.00 -- Realized R: -0.99 (deviation: slippage)
- Counterfactual target 1.0R: exit stop, r=-1.61
- Counterfactual target 1.5R: exit stop, r=-1.61
- Counterfactual stop 1.25x: stopped out, exit stop, r=-1.86
- Counterfactual stop 1.5x: stopped out, exit stop, r=-2.11
- Counterfactual no-flatten: not applicable
- MAE beyond stop: 1.94R
Cost check
n=6 fill(s), median |slippage| 0.45bps vs 5.00bps model (ratio 0.09x)
Trailing-20 (n=3)
| metric | live (2R) | target 1.0R | target 1.5R |
|---|---|---|---|
| cumulative R | -0.61 (n=3) | -1.44 (n=3) | -1.44 (n=3) |
| metric | stop 1.25x | stop 1.5x |
|---|---|---|
| stop-out survival | 0% (0/1) | 0% (0/1) |
cost ratio: 0.09x
Triggers
- stop-width survival: 0% (threshold 60%, n=1) -- not fired
- closer R-target: best -1.44R vs live -0.61R (n=3) -- not fired
- cost divergence: 0.09x (n=6) -- FIRED
- suggested hypothesis: re-examine the frozen 5bps cost model (realized median slippage is below it by 0.09x)