---
title: State curriculum
family: oracle-curriculum
summary: Keep the deep, mature boards a future-reading planner reaches, throw away everything privileged about them, and hand them to other experiments as practice positions.
status: support-only
evidence: task-record only
reads: teacher
---

Keep the deep, mature boards that a future-reading planner reaches after fifty
or a hundred moves, strip away everything privileged about how it got there, and
hand the bare positions to other experiments as practice starting points.

<EvidenceLabel status="support-only" evidence="task-record only" reads="teacher" />

This is infrastructure, not a policy. Nothing here plays a game to win one; it
manufactures a dataset that several later experiments consumed.

## The intuition

A learner that always starts from an empty board spends nearly all of its
experience on easy, early positions. The interesting decisions: the ones that
decide whether a game reaches move 200 — happen on crowded boards with tall
columns, buried gray discs and a rise about to land. Ordinary play reaches those
positions rarely and briefly; the
[perfect-information oracle](/approaches/oracle-curriculum/perfect-information-oracle)
reaches them constantly and survives inside them for hundreds of moves.

So: use the oracle as a *tour guide* to interesting positions, then delete the
guide. What is exported is a board, not a trajectory.

## Where the privilege stops

The C++ converter states the rule in one line: **oracle privilege terminates at
the public-state constructor.** An exported record contains a canonical board,
the visible next disc, and the five-drop rise phase. It does not contain the
seed, the future tape, the hidden values behind any gray disc that was still
covered, the score, the level, or the move index.

More than that, the diagnostics attached to each record are *not* the oracle's
own outcome. Each exported position is re-played forward under **seven
independent futures derived from the public state itself**, using a fair depth-1
search, over a 25-move horizon. So the numbers stored next to a position — mean
moves survived, survival rate, clears and reveals per move, and a coarse flow
band — describe what an ordinary player can expect from that board, not what the
cheating planner achieved from it.

## How it works, step by step

1. Play 64 games with the privileged beam planner (depth 4, beam 128, 500-move
   cap) on a training-only seed family.
2. From move 50 onward, sample positions along those games.
3. Convert each to the public encoding, canonicalize it by reflection, and
   deduplicate, keeping at most 4,096 states.
4. Re-score each state under seven public-derived futures with fair depth-1
   play, at a 25-move horizon, and attach the flow diagnostics.
5. Write the file. A separate TypeScript generator produces a sibling format
   that tags each record by where it came from — oracle play, a combined
   policy, or a safety policy, and stores remaining moves and remaining score
   as targets.

## What happened

The generator worked and its isolation checks passed: 4,096 restart states were
produced, and the privilege-isolation tests confirmed that nothing privileged
crossed into the exported records. That is the whole retained result. It is a
support artifact, recorded as task-record only, with no ledger entry.

What the curriculum was *used for* is where the outcomes are, and those are all
negative so far: a value network trained on these states plateaued well below
fair search; a reinforcement learner that began half of its episodes from these
positions failed every one of its absolute floors; an option-based policy
learner using the same 50/50 mix improved on the shallowest search and stayed
far below depth-4; and the
[curriculum long-outcome network](/approaches/d4-long-outcome/long-outcome)
predicted survival usefully while ordering moves worse than exact search. None
of those failures is attributed to the curriculum itself; none of them
vindicates it either.

<Callout title="The measurement that would settle it was never taken" tone="warn">
The converter computes exactly what is needed to answer "is an oracle-visited
board actually worth more to a fair player?", and the aggregate was never
reported. [`audit-05`](/docs/exploratory/audit-05-optimistic-curriculum) §5.4
calls this "the single missing measurement" and estimates it at about an hour of
compute: if oracle boards re-labelled fairly are barely better than ordinary
boards matched on phase, occupancy and height, then practising from them has
nothing to teach.
</Callout>

<TechnicalDetails>

- Native converter, `oracle-curriculum.cpp`: **completed; task-record only
  support**; "4,096 restart states were generated and privilege-isolation checks
  passed" ([experiment index](/docs/research/experiment-index)). No ledger entry
  exists for it.
- TypeScript generator, `generate.ts`: **support-only; repository-verified**.
  Emits `D7CURR1` records tagged by source (oracle, combined, phase-safety) with
  remaining-moves and remaining-score targets.
- Read from the source: 64 generation games from `0x3d660000`, oracle depth 4 /
  beam 128, 500-move cap, first sample at move 50, at most 4,096 states, seven
  restart scenarios at horizon 25, separate reveal and visible-disc random
  domains for the restart futures, and a static assertion that the level bonus
  is **17,000**, so the restart diagnostics are on corrected Hardcore scoring.
- Downstream consumers and their recorded outcomes are listed in
  [`audit-05`](/docs/exploratory/audit-05-optimistic-curriculum) §2.1 and §2.4;
  the corpus fingerprints appear there too. §2.5 of the same audit records that
  the generated corpora themselves lived under `/tmp` and are **gone from this
  machine**, so any experiment that wants them must regenerate them from a
  leased training range.

</TechnicalDetails>

## What this taught us, and what is still open

- **Isolation can be made structural.** Terminating privilege at a constructor,
  and recomputing every diagnostic from public-derived randomness, is a pattern
  worth copying: it makes the information boundary a property of the type system
  rather than a promise in a comment.
- **A dataset is not a result.** Four thousand positions exist, were used four
  or five times, and have not yet produced a policy improvement.
- **Still open:** the one-hour measurement above; and, separately, whether a
  training *pool* drawn from oracle-visited boards but labelled *fairly* helps —
  which [`audit-05`](/docs/exploratory/audit-05-optimistic-curriculum) identifies
  as untested in this repository, as distinct from the optimistic *labels* that
  have already failed.