Daily verification: 2026-09-04
Verdict: FAIL
1. Slots
FAIL -- 9/9 hourly-check runs completed cleanly.
2. Scans
PASS -- 4 scan row(s) (3 evaluated bar(s)).
3. Geometry
PASS -- Every non-null stop/target price checked for whole-cent quantization.
4. Journal
PASS -- 2 entries, 4 fill(s), 2 closed trade(s).
5. Latency
PASS -- max 7318ms, median 1909ms.
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: $1,018,028.72
- Floor baseline: 1017330.61
- Floor price: $864,731.02
- Headroom: 15.1%
Findings
- slots: run started_at=2026-09-04T15:07:00.718+00:00 outcome=error:AlpacaError
- slots: run started_at=2026-09-04T16:07:00.425+00:00 outcome=error:naked_position_flattened
- slots: run started_at=2026-09-04T18:07:00.292+00:00 outcome=error:AlpacaError
- slots: run started_at=2026-09-04T19:07:00.295+00:00 outcome=error:naked_position_flattened
Changed since the previous verified day
- Max latency: 3896ms -> 7318ms
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.
445efd65-646d-4272-8e7a-cbc70107227f -- SPY SHORT
- Detectors: bearish_marubozu
- Entry: 769.4576 @ 2026-09-04T15:07:05.839589+00:00 (slippage -0.10bps)
- Exit: 770.0500 @ 2026-09-04T16:07:03.355049+00:00 (hourly_bracket_exit -> stop, slippage -31.72bps)
- Nominal R: -1.00 -- Realized R: -0.19 (deviation: slippage)
- Counterfactual target 1.0R: data unavailable
- Counterfactual target 1.5R: data unavailable
- Counterfactual stop 1.25x: data unavailable
- Counterfactual stop 1.5x: data unavailable
- Counterfactual no-flatten: not applicable
- MAE beyond stop: 0.00R
9b5d7a86-3e58-4f25-8536-9bfa09c10737 -- SPY SHORT
- Detectors: bearish_engulfing
- Entry: 769.3399 @ 2026-09-04T18:07:07.10421+00:00 (slippage 0.85bps)
- Exit: 769.6900 @ 2026-09-04T19:07:03.206816+00:00 (hourly_bracket_exit -> stop, slippage -17.38bps)
- Nominal R: -1.00 -- Realized R: -0.22 (deviation: slippage)
- Counterfactual target 1.0R: data unavailable
- Counterfactual target 1.5R: data unavailable
- Counterfactual stop 1.25x: data unavailable
- Counterfactual stop 1.5x: data unavailable
- Counterfactual no-flatten: not applicable
- MAE beyond stop: 0.00R
Cost check
n=14 fill(s), median |slippage| 0.68bps vs 5.00bps model (ratio 0.14x)
Trailing-20 (n=7)
| metric | live (2R) | target 1.0R | target 1.5R |
|---|---|---|---|
| cumulative R | -0.32 (n=7) | -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: 0.14x
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: 0.14x (n=14) -- FIRED
- suggested hypothesis: re-examine the frozen 5bps cost model (realized median slippage is below it by 0.14x)