with one click
cayley-puzzles
cayley-puzzles contains 10 collected skills from Erlemar, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Use this skill for any task in the cayley IHES Picture Cube project — training, solving, evaluation, ensembling, submission. Covers the full ML+search pipeline.
Strat-5 acceptance gate for a megaminx V model. Runs 51-pid stratified eval at beam 65k, compares to m05 baseline (50/51 / mean 89.4), reports pass/fail.
Run the top-N long-pid sym-ensemble rescue + merge cycle on the current best megaminx submission.
One-shot status across GCP solves, Kaggle kernels, and local runs for the megaminx competition.
Verify a megaminx submission CSV, submit to Kaggle, and update HANDOFF / SUBMISSION_JOURNEY / to_do_shortlist with the new score.
Pull the latest cayleypy-tpu-beam-smoke kernel output, aggregate per-rank JSONs, merge with current best, verify, and prep for submission.
Combine candidate submissions, post-process, verify, and submit to Kaggle.
Verify an already-built submission CSV then submit to Kaggle.
Provision a GCP TPU-Builders v6e flex-start VM, set it up (mount/create data disk, install jax[tpu]+torch, pull megaminx beam artifacts from GCS, verify device count), and run the SPMD beam. Use when resuming the megaminx v6e beam work (e.g. after the 8-chip backend bug is fixed) or spinning up any ct6e flex-start VM. Encodes the flex-start status/fault/stockout handling, the Windows plink-noise filter, and the diagnostics-first discipline learned 2026-06.
Use this skill for any task in the cayley IHES Picture Cube project — training, solving, evaluation, ensembling, submission. Covers the full ML+search pipeline.