The Oracle Was Exact. The Protocol Wasn't.

E029 asks whether two exact endgame suggestions improve Luna's move utility. Its first publishable result is a chronology of two failures—not an effect estimate.

An exact answer does not make an experiment exact.

E029 was designed to measure a narrow intervention. Luna receives a legal five-piece chess position. In one arm it sees only the board state. In the other it also sees two unranked moves from a frozen Syzygy tablebase policy. Both arms retain the same unrestricted action tool. Every legal answer is scored against complete tablebase labels from the perspective of the player to move.

The intended comparison is therefore about using exact advice, not following a software-constrained menu. The suggestions change information while the action space stays fixed.

There is no public E029 effect estimate in this note. Before such an estimate can exist, the source and execution chronology has to survive two failures without rewriting either one into success.

A corpus can be legal and still be infeasible

The preregistration fixed six five-piece material families, 360 generated candidates, 60 final positions, two arms, two fresh replicates per arm, and a balanced ten-way schedule. The first source selector crossed side to move, material family, and root outcome too aggressively. It required every material-by-color cell to contribute outcome classes that some endings simply did not contain.

The immutable v1 acquisition exposed the contradiction. One registered cell had no eligible decisive-loss position. The selector stopped with an exact shortfall instead of silently drawing more boards, changing the seed, adding a material family, or borrowing a nearby outcome.

That is a source NO-GO, not a disappointing scientific result. No Luna call had been made. No model outcome existed. The v1 candidate manifest, raw tablebase journal, adapter, and failure record remain preserved as the version that did not work.

Amendment 1 changed selection, not the question

The repair was frozen after tablebase feasibility was known but before any model response. That timing matters. It makes the amendment post-label but pre-outcome.

The amended selector retained the registered scientific margins that were jointly feasible:

• 60 positions and 240 planned calls;
• 10 positions in each side-to-move by root-outcome cell;
• 10 positions from each of six material families;
• five positions in each material orientation within every family;
• 30 ABBA and 30 BAAB blocks; and
• balanced first-versus-second display order for the two suggestions.

Selection became a deterministic integral min-cost flow over the already frozen 360-position pool. It generated no new position and performed no new tablebase lookup. The v2 corpus reached the exact registered margins, retained complete labels for every legal move, and passed a second provider-free parse.

This repair does not make v1 successful. It creates an amended v2 source whose limitations include the post-label feasibility observation.

Then the interface failed after the answer returned

The first execution frontier reached the provider and returned successfully, but the event boundary rejected the first action before any scored event was written. The prompt asked for UCI notation while also displaying suggestions in UCI and SAN. The unrestricted tool accepted a generic string. The inherited event parser accepted only UCI.

A legal SAN answer was therefore transport-complete and semantically recoverable, yet incompatible with the registered event schema.

This was not a provider failure. It was not a bad chess move. It was not missingness. And it did not authorize another chat. The durable journal already contained the paid intent, returned exchange, and authoritative identity metadata for each protected attempt in the first frontier.

The original Amendment 1 recovery draft also failed preflight. Its replay guard treated a repeated request-body hash as evidence of duplication, but two prospectively registered replicates in the same arm can legitimately have byte-identical requests. No provider call occurred under that rejected draft. Its measured identity and rejection chronology remain preserved rather than being promoted as a usable repair.

Recovery Amendment 2 separates syntax from identity

The accepted recovery uses the frozen attempt identity—not request-body uniqueness—as its no-replay boundary. For each returned action, it applies one uniform interpretation rule across both arms:

1. accept a syntactically valid legal UCI move;
2. otherwise accept only an unambiguous legal SAN move against the frozen position;
3. store every accepted move in canonical UCI; and
4. retain illegal or unparseable strings as observed malformed actions with utility zero.

The raw response evidence remains unchanged. Prompts, labels, advice order, schedule, model identity, budget, and estimand remain unchanged. The protected first-frontier attempts must prove that they need no new chat before their events are reconstructed. Later registered replicates remain eligible even when their request bytes match an earlier replicate.

This is a narrow interface amendment. It cannot rescue an unfavorable move, replace a provider failure, or change an experimental arm.

Why the result remains closed

An executing experiment is not a public result. Neither returned actions nor a partial arm contrast belong on the site. E029's public capsule therefore contains only design counts, frozen source dispositions, amendment chronology, claim limits, and content identities. It excludes positions, prompts, move strings, responses, request identifiers, provider metadata, live progress, tokens, costs, account state, and every interim outcome.

Only a terminal, content-addressed analysis may open the result gate. That analysis must reconcile all 240 registered cells, distinguish provider missingness from malformed observed actions, bind the amended corpus and recovery evidence, and report the registered paired utility estimand with its uncertainty and unresolved-cell bounds.

A post-run publication audit found one more boundary that the terminal record must disclose: the execution lock bound the preregistration, corpus, runner, and runtime schemas, but did not bind the analysis implementation hash promised by the preregistration. The estimands, inference seeds, and decision rule were specified in prose before execution; the exact analyzer bytes were not pre-hash-locked. A later deterministic implementation can calculate those registered quantities, but it must be labeled through an explicit analysis provenance amendment rather than described as a fully pre-locked analysis implementation.

Until then, the strongest accurate statement is procedural: E029 has a frozen exact-tablebase design, an immutable source NO-GO, a disclosed post-label source amendment, a transport-complete interface incident, and a no-replay recovery contract. It does not yet have a public scientific effect.

What a terminal result could—and could not—say

If the result gate opens, E029 can answer whether two unranked exact-policy suggestions changed Luna's exact 50-move-rule utility on this synthetic five-piece benchmark relative to board-only Luna.

It cannot establish full-game transfer, Elo improvement, base-model learning, human-like reasoning, stronger vision or search, benefits outside tablebase states, or unassisted Luna skill. Success would measure the system's ability to use a tiny exact oracle. Failure would be equally local to this interface, model snapshot, population, and scoring policy.

Evidence identity

This no-result chronology is bounded to the following immutable evidence:

• E029 preregistration, SHA-256 c98496622e6e69e778b7b8d84277a8391c5523025389646d2ad4b19bc64142fa;
• original source audit, SHA-256 d3ebde5195bb8bb68355b930d12297c88434fb10581edf9be553d4c004248043;
• v1 source NO-GO record, SHA-256 966510fce0bd127ebc8ff5c6e7e6e6ec7187be5aaef53f6bb7082ba6cfd1bfc1;
• Source Selection Amendment 1, SHA-256 f72dc9246815441529d16df58948d8f52c92b3a5f6fc388e9851641b147e4394;
• amended v2 manifest, SHA-256 2f27a95971209dc57e8d62a9a3fccc727c7573297bf2d887de79e13250c6be81;
• amended source qualification, SHA-256 6c40cac59a5bb05117a71121d1cccb8f1776326d7560b1b052549be8722eb4a5;
• Execution Incident Amendment 1, SHA-256 98cbf833daf660023a52aa7907d206e4ae68d842271d38f36098e9b87e768601; and
• Execution Recovery Amendment 2, SHA-256 df884242279cdb5c46e95c24930697bd543c793d7dc18320a2c24487a53b80bd.

None of these identities is a terminal result. If any byte changes, this note must fail its publication check until the evidence binding is reviewed again.