IQ56: failed to finish good jumper normal day

The notebook

In order: what the lab saw, what it asked, what it proposed and why, what the tests said, and what an investigator concluded. Numbers are aggregates on the discovery data unless a step says otherwise.

1. Hypothesised15 Oct, 23:10

   IQ56: failed to finish good jumper normal day SHADOW

   because A: failed to finish last time in today's code; earlier runs averaged in the better half of its fields on Jump Index, and this run was no more than 0.15 below its own average.

   race_type IN ('Chase', 'Hurdle') AND last_position IS NULL AND l_same_code = 1 AND s_jump_index_pct_prev >= 0.5 AND l_jump_index - s_jump_index_prev >= -0.15

   made by import

2. Tested15 Oct, 23:10

   HOLDOUT 2023-25, all: A/E 1.22 on 838 bets, by period 1.22. info

   Every period above 1.00 (spread 0.00). Zone: all. On IQ56: failed to finish good jumper normal day

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago8381.22

   Last year0–

3. Tested15 Oct, 23:10

   Britain: A/E 1.19 on 667 bets, by period 1.19. info

   Every period above 1.00 (spread 0.00). Zone: all. On IQ56: failed to finish good jumper normal day

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago6671.19

   Last year0–

4. Tested15 Oct, 23:10

   Ireland: A/E 1.33 on 171 bets, by period 1.33. info

   Every period above 1.00 (spread 0.00). Zone: all. On IQ56: failed to finish good jumper normal day

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago1711.33

   Last year0–

5. Tested15 Oct, 23:10

   discovery year (reference): A/E 1.02 on 552 bets, by period 1.02. info

   Betfair SP return +30.3%. Every period above 1.00 (spread 0.00). Zone: all. On IQ56: failed to finish good jumper normal day

   By period

   betsA/E0.71.01.3

   2020-220–

   2023 to a year ago0–

   Last year5521.02

6. Promoted15 Oct, 23:10

   IQ56: failed to finish good jumper normal day Falsification → FROZENimport: frozen

7. Promoted15 Oct, 23:10

   IQ56: failed to finish good jumper normal day Vault → SHADOWimport: holdout SUPPORTIVE: A/E 1.219 on 838 (GB 1.193, IRE 1.334), p 0.0468 against BH 0.003448 over 29 tests

8. Tested15 Oct, 23:21

   forward vs bar {'min_bets': 100, 'min_ae': 1.0, 'max_p': 0.2} on 0 bets. info

   Zone: forward. On IQ56: failed to finish good jumper normal day

9. Observed16 Oct, 10:10

   IQ56-failed-to-finish-good-jumper-normal-day (IQ56: failed to finish good jumper normal day) pointed the predicted way (positive) on the sealed holdout but too weakly to prove it: A/E 1.219 on 838 bets (p 0.047, false-discovery threshold 0.0034); tracked forward in SHADOW.

   result0.35waiting for a reasoning passfrom IQ56-failed-to-finish-good-jumper-normal-day

10. Tested16 Oct, 23:21

    forward vs bar {'min_bets': 100, 'min_ae': 1.0, 'max_p': 0.2} on 0 bets. info

    Zone: forward. On IQ56: failed to finish good jumper normal day