Daily verification: 2026-09-03
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 3896ms, median 2078ms.
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: $1,018,109.07
- Floor baseline: 1017330.61
- Floor price: $864,731.02
- Headroom: 15.1%
Findings
None.
Changed since the previous verified day
- Max latency: 3875ms -> 3896ms
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.
d3c6d5d4-856e-44f3-9fdf-d642d18c490b -- SPY LONG
- Detectors: hammer, bullish_pin_bar
- Entry: 770.4700 @ 2026-09-03T15:07:03.216539+00:00 (slippage 0.06bps)
- Exit: 773.6600 @ 2026-09-03T19:07:03.257623+00:00 (hourly_session_close_exit -> flatten, slippage -1.03bps)
- Nominal R: n/a -- Realized R: 1.03 (deviation: flatten)
- Counterfactual target 1.0R: exit target, r=0.87
- Counterfactual target 1.5R: exit flatten, r=0.88
- Counterfactual stop 1.25x: survived, exit flatten, r=0.88
- Counterfactual stop 1.5x: survived, exit flatten, r=0.88
- Counterfactual no-flatten: exit end_of_window, r=0.53
- MAE beyond stop: 0.00R
Cost check
n=10 fill(s), median |slippage| 0.45bps vs 5.00bps model (ratio 0.09x)
Trailing-20 (n=5)
| metric | live (2R) | target 1.0R | target 1.5R |
|---|---|---|---|
| cumulative R | 0.09 (n=5) | -1.06 (n=5) | -1.05 (n=5) |
| 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 -1.05R vs live 0.09R (n=5) -- not fired
- cost divergence: 0.09x (n=10) -- FIRED
- suggested hypothesis: re-examine the frozen 5bps cost model (realized median slippage is below it by 0.09x)