SPECTER LABS

Wonton Soup

MCTS search over Lean tactic proofs: an intervention harness for proof structures and basins, and a study of distributed MCTS as a search algorithm in its own right.

SPCTR D-002status activeactivity 2026-06-15license Mixedscope expansion

We solve a theorem with Monte Carlo tree search, then block a tactic it used or stall the scheduler, and run it again. The same goal can come back through a different proof, take a longer route, fail, or solve faster once a wasteful step is gone.

From the paper

When the baseline solved a theorem, a lesion still reaches a proof often enough, and many of those recoveries are different proofs.

preserve reachability
34.0%
1,754 of 5,161 solve after lesion
strict reroutes
602
solved on a different proof hash
nonzero GED
730
structural drift among strict solves

Resilience

A lesioned run still solves. The minimum sign of goal-directed recovery.

Reroute

The lesion solves but lands in a different proof family or shows graph distance. The change is structural.

Rescue

The baseline fails but the damaged run solves. The block removed a path that was leading search astray.

wild type
16/16

ReProver solves the theorem when linarith is available.

block linarith
lesioned
0/16

Block linarith and it collapses completely.

The theorem is an endpoint, not the object.

The object is the fiber of histories and proof structures that can realize that endpoint.

A block tests whether a tactic was necessary.

If a block recovers, the removed resource was substitutable. If it collapses, that resource carried the basin.

Some damage makes search better.

Some constraints prune bad branches, so a lesion can sharpen the search instead of breaking it.