Move 37 → Move 42 · print complete

The next move is an algorithm.

Move 37 answered a Go position with one coordinate no human expected. Move42 asks the same question in a larger action space: when the board is a requirement, can the move be a complete executable algorithm?

A requirement is a board. The contract defines legal play. The referee decides what worked.

01 · Same abstraction, different action space

State becomes a move; consequence becomes experience.

A requirement is a board. The contract defines legal play. The referee decides what worked.

state → legal action → external consequence → preserved experience.

The proposed output changes from an answer or score to an independently runnable method. The learning target is the distribution of later executable proposals across requirements.

02 · Different output

An independently runnable method.

The proposed output changes from an answer or score to an independently runnable method. The learning target is the distribution of later executable proposals across requirements.

The claim is a shift in output type and learning target—not merely a better prediction, benchmark score, or task-time loop.

03 · AutoResearch contrast

Where does search occur, and what persists?

Where search occurs

Search now. Learn for later. Or combine both.

Current requirement

AutoResearch improves through a proposal–execution–inspection–retry loop on the current requirement.

Across requirements

Move42 aims to improve the proposal distribution across requirements, so the first executable move itself becomes learnable.

Hybrids remain possible; the distinction is where search occurs and what persists between tasks.

Evidence boundary. The current record does not measure superiority over research agents, task-time speedup, or an admitted prospective strict first move.

04 · Five-part blueprint

Board. Move. Rules. Referee. Memory.

  1. 01

    Board

    The requirement plus every permitted input, state transition, and resource boundary.

    Encode the requirement and permitted state before any proposal is made.
  2. 02

    Move

    One complete executable algorithm whose outputs can be independently reproduced.

    Define the runnable artifact, interface, and terminal outputs that count as a move.
  3. 03

    Rules

    The legality contract that rejects shortcuts, leakage, hidden state, and invalid resources.

    Close shortcut and leakage paths before play, then make every violation an explicit failure.
  4. 04

    Referee

    An external consequence-based evaluator that executes the move and records success or a named failure.

    Build the referee outside model self-assessment and bind its identity to every outcome.
  5. 05

    Memory

    Canonical success and failure receipts that can supervise later proposals across requirements.

    Preserve receipts, train later proposals, and separately freeze a true one-proposal prospective evaluation.

05 · Current evidence

600 valid runs. 353 wins. 247 losses. 58.8%.

The result is measured against TabFM Ensemble and uses only the 600 identities in the corrected atlas.

Four-model Elo ranking over 600 valid runsThe final computed four-model Elo ranking from the corrected 600-run evidence.90095010001050jope-prime1038.1TabPFN v31028.9TabFM Ensemble996.5TabFM936.6
Final computed Elo ranking
RankModelFinal Elo
1jope-prime1038.1
2TabPFN v31028.9
3TabFM Ensemble996.5
4TabFM936.6
TabFM, TabFM Ensemble, TabPFN v3, and jope-prime from the jAIn foundation family.Simulated learning path from 900 Elo; only the final four-model Elo ranking is computed from the 600 valid runs.Source: move42.elo-600.v1.

Boundary: the 58.8% result describes these 600 runs and is not a prospective universal success rate.

06 · Concrete algorithmic moves

CPU, greenhouse, and spectrometer.

Cpu

6.66× vs TabFM · 5.13× vs TabFM Ensemble · 11.34× vs TabPFN v3

Greenhouse

3.40× vs TabFM · 4.66× vs TabFM Ensemble · 5.03× vs TabPFN v3

Spectrometer

5,434.54× vs TabFM · 4,373.89× vs TabFM Ensemble · 4,530.65× vs TabPFN v3

Each factor is a labeled within-dataset RMSE comparison. Exact programs remain in marked verbatim-evidence disclosures on the atlas.

07 · Receipts become memory

Successes and failures train later proposals.

The external referee preserves the program, requirement, split, resources, outcome, clocks, and named failures. Stored supervision can update a later challenger; gradients do not pass through arbitrary executed code.

08 · What does this mean?

Four design horizons, all labeled vision.

Vision · Compiler game

Board
A source program, target semantics, architecture, and optimization contract.
Move
A complete transformation or optimization algorithm that produces executable output.
Referee
Correctness suites, resource limits, and consequence-based performance measurements.

A design horizon, not a finding of the current regression study.

Vision · Control game

Board
A control requirement, observable plant state, hard constraints, and permitted actuators.
Move
A complete control algorithm that can be executed against the declared interface.
Referee
Constraint violations, stability, resource use, and measured physical consequence.

A design horizon, not evidence of autonomous control performance.

Vision · Experimental game

Board
An apparatus, measurement protocol, budget, safety envelope, and experimental objective.
Move
A complete executable experiment schedule and analysis method.
Referee
Predeclared measurements, explicit failure outcomes, and independently preserved receipts.

A design horizon, not an experimental result reported here.

Vision · Scientific-design game

Board
A scientific question, admissible evidence, interventions, and falsification criteria.
Move
A complete executable design for collecting and analyzing the next evidence.
Referee
Preregistered consequence tests that can reject as well as support the proposed method.

A design horizon, not a claim of causal or scientific discovery.

09 · Separate scales, visible limits

317,156,096 generated algorithms.

This hash-bound generation-scale fact is separate from the 600 valid performance runs. It is not another run, game, dataset, file, finalist, cohort, or campaign result.

The prospective first-move study is still required.

A future study must predeclare its cohort and proposal budget, retain complete failures, match hardware and timing, and freeze comparators.

Limitations: no expected future win rate, focal-case causality, matched comparator speed, universal superiority, or safe autonomous use is established.

Download the designed ten-page PDF · Open the complete Move 37 comparison · Inspect all 600 runs · Build the game · Inspect evidence

Evidence claim

Claim detail

Status
Source
Pointer
Limitation

Open the normalized ledger