summaryrefslogtreecommitdiff
path: root/design/experiment-spec.md
diff options
context:
space:
mode:
authorVoid Agent <void@jayrup.hermes>2026-08-14 13:14:09 +0100
committerVoid Agent <void@jayrup.hermes>2026-08-14 13:14:09 +0100
commit9c50f31c66e788ff08eeac83f84e90e9bc1a921e (patch)
tree6e960573f436ee65f35ce9b77ad9064977339a8c /design/experiment-spec.md
parent898a0570dfe619ec2bcf330b07dce9b23cb63d54 (diff)
rnn: fully-tied cell (read-in+compute+decode), lambda ramp, ACT regression test; design: prior art + review
Diffstat (limited to 'design/experiment-spec.md')
-rw-r--r--design/experiment-spec.md17
1 files changed, 17 insertions, 0 deletions
diff --git a/design/experiment-spec.md b/design/experiment-spec.md
index c814057..77d1606 100644
--- a/design/experiment-spec.md
+++ b/design/experiment-spec.md
@@ -125,3 +125,20 @@ cross the gap from pattern matching to computation.
---
> Copied from the research repo `prime-grokking/main.md` @ 546dc2c (provenance: `~/Projects/research`, remote ssh://meru/~/projects/research.git).
+
+
+---
+
+## Prior art (appended 2026-08-14, Gemini 3.6 Flash design review)
+
+No prior grokking work on next-prime / primality found. Canonical refs:
+
+- Power et al. 2022 (arXiv:2201.02177) — grokking, modular arithmetic
+- Nanda et al. 2023 (arXiv:2301.05217) — grokking progress measures
+- Liu et al. 2022 (arXiv:2205.10343) — empirical grokking study
+- Varma et al. 2023 (arXiv:2309.02390) — grokking via circuit efficiency
+- Graves 2016 (arXiv:1603.08983) — ACT
+- Banino et al. 2021 (arXiv:2107.05407) — PonderNet
+- Giannou et al. 2023 (arXiv:2301.13196) — looped transformers
+- Xu et al. ICLR 2020 (arXiv:1905.13211) — algorithmic alignment
+- Xu et al. 2021 (arXiv:2009.11848) — extrapolation / GNNs