Rival: the debutant lift is the yard's chase-debut skill, not misread hurdle form

Reasoning

Why this hypothesis exists: what the lab saw, the question it asked, the mechanism it proposed, what it predicted, and the result that would prove it wrong. Written before the test was run.

1. Observed
   • H-448cb451 (Rival: chase debutants after any heavy hurdle beating beat their price): the country 'GB' carries the effect (A/E 1.43) while the rest score IRE 0.91. O-69d892e9
   • H-448cb451 (Rival: chase debutants after any heavy hurdle beating beat their price) passed discovery as a niche: A/E 1.24 on 335 bets (p 0.116), same-race control 0.97. O-7628ef4c
2. AskedIs the chase-debutant lift after a heavy hurdle beating carried by yards that are good at chase debuts, so that it is really the published yard effect (H104, SYS-chase-debut-from-a-good-yard) and not a misread of form? answered
3. MechanismIf the cause is the market over-reading bad hurdle form, the lift should appear whoever the trainer is. If it disappears outside the good chase-debut yards, the published yard effect is the real driver.
4. Why the market misses itBad hurdle form puts the horse out of the betting regardless of the yard. If the lift survives in ordinary yards, the misread is about the form and not about the trainer's schooling.
5. Predictedpositive, A/E 1.15 to 1.30 on 200+ bets if the form-misread story holds
6. Falsified ifA/E at or below 1.05 on 150+ bets, which would mean the yard carries the effect and the story adds nothing
7. Rule sketchlast_race_type = 'Hurdle' AND race_type = 'Chase' AND COALESCE(chase_runs, 0) = 0 AND last_beaten_lengths >= 20 AND tx_chase_debut_runs >= 15 AND tx_chase_debut_wins < 1.3 * tx_chase_debut_exp

The question's answer so far: No. The yard-skill cut (H-2e457254) scored only 1.09 on 296 (p 0.35), below the yard-free debutant niche at 1.24 on 335. The good-yard effect does not carry the debutant lift.

Mechanism and rationale

If the cause is the market over-reading bad hurdle form, the lift should appear whoever the trainer is. If it disappears outside the good chase-debut yards, the published yard effect is the real driver.

The rule

last_race_type = 'Hurdle' AND race_type = 'Chase' AND COALESCE(chase_runs, 0) = 0 AND last_pulled_up = 0 AND last_beaten_lengths >= 20 AND (COALESCE(tx_chase_debut_runs, 0) < 15 OR tx_chase_debut_wins < 1.3 * tx_chase_debut_exp)

Reads: last_race_type, race_type, chase_runs, last_pulled_up, last_beaten_lengths, tx_chase_debut_runs, tx_chase_debut_wins, tx_chase_debut_exp

Pre-registration

Spec hash (sha256 of the canonical pre-spec)

1f3806447282e18afb08cddfa8171b7704b455710b52259ade7012b19217d24a

Frozen

not frozen

The definition can still change.

Confounders

• Yards with small samples (under 15 chase-debut runs, or no history) were left out by the sketch's runs filter. The broad rule puts them back in as 'no strong record', and refinement 1 isolates the established ordinary yards.
• GB/IRE mix: the parent lift came from a scan and sat in GB (1.43 against 0.91 in IRE). Report it by region, but do not slice the rule on it.
• Handicap status: a heavy hurdle beating can drop the mark for a handicap chase debut, so a handicap-mark effect could pass for a form misread. Report handicaps and non-handicaps separately.
• Price band: lifts in this family sit under 16/1, so a band effect could look like a form effect (refinement 2).
• The yard's chase-debut record is measured against market expectation (tx_chase_debut_exp). Ordinary yards may still contain capable yards whose sample is noisy, and that weakens the separation.
• Pull-ups are excluded to match the parent finding, since pull-ups belong to a separate story that is already measured.

Control

{
  "description": "Same-race other runners should score about par (the parent finding had 0.97), which shows the lift is not a property of novice or beginners' chases. The main comparison is the complementary group: heavily beaten chase debutants from strong chase-debut yards (at least 15 debut runs and wins at 1.3x expected or better). If the ordinary-yard rule is near 1.0 while the strong-yard control carries the parent's 1.24, the yard explains the lift. If both are above par, the form misread stands on its own.",
  "rule": "last_race_type = 'Hurdle' AND race_type = 'Chase' AND COALESCE(chase_runs, 0) = 0 AND last_pulled_up = 0 AND last_beaten_lengths >= 20 AND tx_chase_debut_runs >= 15 AND tx_chase_debut_wins >= 1.3 * tx_chase_debut_exp"
}

Discovery result

fail broad rule · 17 Oct, 02:43

Bets

296

29 winners

A/E

1.09

95%: 0.73 to 1.56

SP return

-29.2%

level stakes

Betfair SP return

-15.8%

293 bets with a BSP

Strike rate 9.8%. p = 0.35. Same-race control: the other runners in these races had A/E 0.99, so the selection beat its own races. Zone: discovery. Evaluator eval-1.0, data 6a4e98be18e83933

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

No forward record. Shadow tracking starts after the vault and counts only races run after the freeze.

Lineage

Agent runs

• designer v1ok · 43s · 17 Oct, 02:39

  Output (schema-checked)

  {
    "rule": "last_race_type = 'Hurdle' AND race_type = 'Chase' AND COALESCE(chase_runs, 0) = 0 AND last_pulled_up = 0 AND last_beaten_lengths >= 20 AND (COALESCE(tx_chase_debut_runs, 0) < 15 OR tx_chase_debut_wins < 1.3 * tx_chase_debut_exp)",
    "refinements": [
      {
        "label": "established ordinary yards only (the rule sketch)",
        "rule": "last_race_type = 'Hurdle' AND race_type = 'Chase' AND COALESCE(chase_runs, 0) = 0 AND last_pulled_up = 0 AND last_beaten_lengths >= 20 AND tx_chase_debut_runs >= 15 AND tx_chase_debut_wins < 1.3 * tx_chase_debut_exp"
      },
      {
        "label": "under 16/1, where this family's lifts sit",
        "rule": "last_race_type = 'Hurdle' AND race_type = 'Chase' AND COALESCE(chase_runs, 0) = 0 AND last_pulled_up = 0 AND last_beaten_lengths >= 20 AND (COALESCE(tx_chase_debut_runs, 0) < 15 OR tx_chase_debut_wins < 1.3 * tx_chase_debut_exp) AND sp_decimal < 17"
      }
    ],
    "control": {
      "description": "Same-race other runners should score about par (the parent finding had 0.97), which shows the lift is not a property of novice or beginners' chases. The main comparison is the complementary group: heavily beaten chase debutants from strong chase-debut yards (at least 15 debut runs and wins at 1.3x expected or better). If the ordinary-yard rule is near 1.0 while the strong-yard control carries the parent's 1.24, the yard explains the lift. If both are above par, the form misread stands on its own.",
      "rule": "last_race_type = 'Hurdle' AND race_type = 'Chase' AND COALESCE(chase_runs, 0) = 0 AND last_pulled_up = 0 AND last_beaten_lengths >= 20 AND tx_chase_debut_runs >= 15 AND tx_chase_debut_wins >= 1.3 * tx_chase_debut_exp"
    },
    "pass_criteria": {
      "min_bets": 150,
      "min_ae": 1.05,
      "max_p": 0.05
    },
    "forward_bar": {
      "min_bets": 100,
      "min_ae": 1,
      "max_p": 0.2
    },
    "confounders": [
      "Yards with small samples (under 15 chase-debut runs, or no history) were left out by the sketch's runs filter. The broad rule puts them back in as 'no strong record', and refinement 1 isolates the established ordinary yards.",
      "GB/IRE mix: the parent lift came from a scan and sat in GB (1.43 against 0.91 in IRE). Report it by region, but do not slice the rule on it.",
      "Handicap status: a heavy hurdle beating can drop the mark for a handicap chase debut, so a handicap-mark effect could pass for a form misread. Report handicaps and non-handicaps separately.",
      "Price band: lifts in this family sit under 16/1, so a band effect could look like a form effect (refinement 2).",
      "The yard's chase-debut record is measured against market expectation (tx_chase_debut_exp). Ordinary yards may still contain capable yards whose sample is noisy, and that weakens the separation.",
      "Pull-ups are excluded to match the parent finding, since pull-ups belong to a separate story that is already measured."
    ],
    "mechanism": "A heavy hurdle beating (20 lengths or more, completed) prices a chase debutant on form that may say little about how well it jumps fences. If the market's mistake is over-reading that bad hurdle form, the lift should appear whoever the trainer is. That includes yards with no strong or established chase-debut record. If the lift only shows up in the strong chase-debut yards, the published yard effect drives it and the form story adds nothing.",
    "market_miss": "Punters and compilers price a debutant by its last hurdle run, so a 20-length beating pushes it out in the betting whatever the yard. Without a well-known yard record to prompt a second look, nothing corrects that markdown. So if the edge from misread form exists, it should be clearest in ordinary yards.",
    "prediction": {
      "direction": "positive",
      "size": "A/E 1.15 to 1.30 on 200+ bets if the form-misread story holds",
      "falsified_if": "A/E at or below 1.05 on 150+ bets in the broad rule, especially if the strong-yard control keeps the parent's lift (above 1.2). That would mean the yard carries the effect and the story adds nothing."
    },
    "notes": "I changed the sketch in two ways. (1) Pull-ups are excluded (last_pulled_up = 0) to match the parent finding, which was 'pull-ups excluded'. (2) The yard condition now covers every yard without a strong chase-debut record, including yards with fewer than 15 debut runs or with NULL history. This fixes the listed confounder that small yards were dropped. The sketch's version (at least 15 runs, ordinary record) is kept as refinement 1. tx_chase_debut_wins is only available from Nov 2020 in GB and Sep 2020 in IRE. Rows from established yards before that date drop out of the OR condition because it evaluates to NULL. The GB-only cut is deliberately not used as a refinement because it came from a scan."
  }

Timeline

1. Job 2489 finished

   17 Oct, 02:43 · engine:compute-1

2. H-2e457254 Discovery → KILLED fails: p 0.3518, needs 0.05 or lower; periods [1.43, 0.81], each needs 1.0 (not a niche pass: a period points the other way [1.43, 0.81])

   17 Oct, 02:43 · engine:evaluator

3. discovery result for H-2e457254 (broad rule): fail

   17 Oct, 02:43 · engine:evaluator

4. H-2e457254 Designed → RESEARCHdiscovery measuring on the discovery zone

   17 Oct, 02:43 · engine:orchestrator

5. compute-1 took job 2489 (evaluate, attempt 1)

   17 Oct, 02:43 · compute-1

6. Job 2487 finished

   17 Oct, 02:40 · engine:ai-1

7. Queued evaluate on the compute lane: discovery run of the broad rule

   17 Oct, 02:40 · engine:scheduler

8. H-2e457254 Proposed → RESEARCHdesigned pre-spec written and hashed

   17 Oct, 02:40 · agent:designer@v1

9. ai-1 took job 2487 (design, attempt 1)

   17 Oct, 02:39 · ai-1

10. Queued design on the ai lane: write the pre-spec

    17 Oct, 02:39 · engine:scheduler

11. New idea H-2e457254: Rival: the debutant lift is the yard's chase-debut skill, not misread hurdle form (rival-explanation)

    17 Oct, 02:39 · agent:investigator@v1

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