Start with the output thesis
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.
Decide where search belongs
Where search occurs
Search now. Learn for later. Or combine both.
AutoResearch improves through a proposal–execution–inspection–retry loop on the current requirement.
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.
Build all five parts
- 01
Board
The requirement plus every permitted input, state transition, and resource boundary.
Encode the requirement and permitted state before any proposal is made. - 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. - 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. - 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. - 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.
A method that cannot execute under the declared contract is not a legal move.
Implementation sequence
- Encode the requirement and permitted state. Freeze inputs, interfaces, resources, transitions, and everything the proposal may observe.
- Define the executable move. Require one complete independently runnable method with reproducible terminal outputs.
- Close shortcut and leakage paths before play. Reject hidden state, contamination, invalid resources, and contract violations as named failures.
- Build an external consequence-based referee. Parse, execute, measure, and preserve explicit failures outside model self-assessment.
- Preserve memory, then freeze evaluation separately. Bind canonical success and failure receipts, train later proposals, and predeclare a true one-proposal prospective study.
How receipts become training
The program executes outside the differentiable model. Its score, rank, runtime, stability, resource use, and failure state return as stored supervision. Gradient updates happen afterward; frozen validation decides whether the later challenger persists.
Evaluation boundary
Historical top-one evidence does not establish prospective one-proposal performance. That study must predeclare its cohort and proposal budget, preserve all failures, match hardware and timing, freeze comparators, and prohibit task-time retry in the evaluated lane.
What could become a game?
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.
Compare Move 37 and Move42 · Inspect recorded moves · Open audit receipts