System: Pulled up last time, jumping as it usually does

Mechanism and rationale

A held-up horse that pulled up while jumping no worse than it normally does was looked after, not found out. The pulled-up horses to avoid are the good jumpers that jumped unusually badly: they won half as often as their prices implied. Found by cutting the pulled-up system with measured jumping figures. Twelve months of data and a small sample: 111 bets. Unproven until its live record says otherwise.

The rule

last_pulled_up = 1 AND last_run_style IN ('held_up', 'midfield') AND sp_decimal <= 15 AND usual_jump_index IS NOT NULL AND last_jump_index - usual_jump_index >= -0.15

Reads: last_pulled_up, last_run_style, sp_decimal, usual_jump_index, last_jump_index

Pre-registration

Spec hash (sha256 of the canonical pre-spec)

67903a6fe32888b153f9b60984e4bdbd36eb8f0211ecedb4854fb5f5a978473b

Frozen

15 Oct, 01:00

Nothing in the definition can change after this.

Backing

price-sensitive

Kind

system

Live from

2026-10-15

Matched

{
  "hypothesis_id": "H36-pulled-up-after-being-held-up",
  "similarity": 0.6,
  "variant": "14/1 or shorter"
}

Published

false

Rules

• Last time out the horse was held up or raced in midfield, and was pulled up.
• That run was in today's kind of race, and its Jump Index was no more than 0.15 below the horse's average over its two or more runs before it.
• It starts at 14/1 or shorter.

Source

Measured jumping figures, October 2026

System id

pulled-up-jumping-as-usual

Tier

none

Where

last_pulled_up = 1 AND last_run_style IN ('held_up', 'midfield') AND sp_decimal <= 15 AND usual_jump_index IS NOT NULL AND last_jump_index - usual_jump_index >= -0.15

Discovery result

Not measured yet.

Falsification

No attacks yet. Only promising ideas are attacked.

Sealed holdout (vault)

Not queried. Only a frozen idea can spend its one query against the 2020-25 holdout.

Forward record

• forward check refusederror

  · 15 Oct, 23:21

• forward vs bar {'min_bets': 100, 'min_ae': 1.0, 'max_p': 0.2}info

  0 bets · · 16 Oct, 23:51

  Breakdown

  betsA/E0.71.01.3

  forward0–

Lineage

Agent runs

No agent has worked on this yet.

Timeline

1. Job 2113 finished

   16 Oct, 23:51 · engine:compute-1

2. forward result for SYS-pulled-up-jumping-as-usual (forward vs bar {'min_bets': 100, 'min_ae': 1.0, 'max_p': 0.2}): info

   16 Oct, 23:51 · engine:evaluator

3. compute-1 took job 2113 (forward_check, attempt 1)

   16 Oct, 23:51 · compute-1

4. Queued forward_check on the compute lane: daily forward check of a shadow system

   16 Oct, 23:51 · engine:scheduler

5. Job 21 finished

   15 Oct, 23:21 · engine:compute-2

6. forward result for SYS-pulled-up-jumping-as-usual (forward check refused): error

   15 Oct, 23:21 · engine:evaluator

7. compute-2 took job 21 (forward_check, attempt 1)

   15 Oct, 23:21 · compute-2

8. Queued forward_check on the compute lane: daily forward check of a shadow system

   15 Oct, 23:21 · engine:scheduler

9. SYS-pulled-up-jumping-as-usual Frozen → SHADOW import: followed forward from 2026-10-15, not shown on the site; from H36-pulled-up-after-being-held-up [14/1 or shorter]

   15 Oct, 23:10 · importer

10. SYS-pulled-up-jumping-as-usual Falsification → FROZEN import: frozen

    15 Oct, 23:10 · importer

11. New idea SYS-pulled-up-jumping-as-usual: System: Pulled up last time, jumping as it usually does (import)

    15 Oct, 23:10 · importer

Every change is an event with an actor: an agent and its version, an engine, a human, or the importer. Current stage: Shadow.