Peer reviewed AI-assisted

Two theorems found by machine pattern-spotting in knot theory and representation theory

Two theorems found by machine pattern-spotting in knot theory and representation theory is graded peer reviewed on whataifound.org, with the AI's role graded ai-assisted.

Networks trained to predict one mathematical invariant from another, then probed for which inputs mattered, pointed mathematicians to a proved theorem linking a knot's signature to a new geometric quantity, and to structure behind the combinatorial invariance conjecture.

Verification
Peer reviewed
Autonomy
AI-assisted
Lab
Google DeepMind (with Oxford and Sydney)
Model
Supervised networks with gradient-based attribution
Field
Mathematics
Date
2021-12-01
Human collaborators
Alex Davies, Marc Lackenby, Geordie Williamson

What was found

The recipe was to train a network to predict one invariant from another, then use attribution to see which inputs carried the signal, and hand that to a mathematician. In knot theory it led Marc Lackenby to define a new quantity, the natural slope of a knot, and to prove a theorem bounding the signature in terms of it. In representation theory it led Geordie Williamson to structure in Bruhat interval graphs bearing on the combinatorial invariance conjecture for Kazhdan–Lusztig polynomials. Published in Nature.

Novelty check

Both theorems are new and neither had a prior form in the literature; both were proved conventionally by the human mathematicians after the models indicated where to look. The general idea of using computation to generate conjectures is old — what was new was the attribution step turning a black-box predictor into a usable hint.

Caveats

The mathematics was done by humans; the models indicated which relationships were worth studying, which is why autonomy is ai-assisted. Ernest Davis's review argues the "guiding human intuition" framing overstates the contribution and that the knot-theory signal was within reach of simpler statistical methods. The theorems themselves are not disputed.

Independent checks

Ernest Davis (critical review of the framing): theorems accepted; disputes how much the deep learning contributed · link ↗

Sources

How this is graded

whataifound.org grades every entry on two axes: verification (how solid the result is, from a machine-checked proof down to refuted) and autonomy (how much the AI did versus its human collaborators). This finding is peer reviewed and ai-assisted. Full definitions are in the methodology.

Cite this entry

whataifound.org (2021). Two theorems found by machine pattern-spotting in knot theory and representation theory. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2021-12-01-knot-theory-intuition

← All mathematics findings in the registry