jgalego
/

knot2vec

@@ -37,13 +37,24 @@ It prints the five nearest of the 12,965 prime knots up to 13 crossings, guesses
 A diagram becomes its Gauss sequence: walk the knot and, at each crossing, record whether the strand passes over or under and the crossing's sign. Crossings are named by first visit and the walk starts at a random edge. A transformer encodes the sequence, and a contrastive loss pulls two scrambles of the same knot together against the rest of the batch. Small heads predict signature, determinant and volume.
-Not trained yet.
 ## 📊 Results
-Each test diagram is a fresh scramble. The model names it by the nearest canonical KnotInfo diagram among all 12,965 knots. *Seen* knots were in training, as other diagrams; *unseen* knots never were.
-Not evaluated yet.
 ## ⚠️ Limitations

 A diagram becomes its Gauss sequence: walk the knot and, at each crossing, record whether the strand passes over or under and the crossing's sign. Crossings are named by first visit and the walk starts at a random edge. A transformer encodes the sequence, and a contrastive loss pulls two scrambles of the same knot together against the rest of the batch. Small heads predict signature, determinant and volume.
+| | |
+|---|---|
+| Parameters | 4,924,943 (6 layers, width 256) |
+| Steps | 20000, 512 knots (two diagrams each) per step |
+| Learning rate | 0.0003, cosine; temperature 0.05 |
+| Final loss | 0.2043 (contrastive 0.1145) |
+| Hardware | NVIDIA A10G, 102 min |
 ## 📊 Results
+Each test diagram is a fresh scramble. The model names it by the nearest canonical KnotInfo diagram among all 12965 knots. *Seen* knots were in training, as other diagrams; *unseen* knots never were.
+| Knots | n | Top-1 | Top-5 | Signature | Determinant ±10% | Volume MAE |
+|---|---|---|---|---|---|---|
+| seen | 46676 | 0.849 | 0.973 | 0.794 | 0.199 | 1.507 |
+| unseen | 5184 | 0.856 | 0.969 | 0.781 | 0.207 | 1.583 |
+Chance top-1 is 7.7e-05. For an exact answer, use SnapPy's `identify()`.
 ## ⚠️ Limitations