Views
No views yet
| Evaluation | Result |
|---|---|
| Three held-out dev sets, top-1 agreement with high-win-rate players | 54.3% |
| Same, as a fraction of a model trained directly on each set (pre-registered normalized score) | 78.6% |
| MSH frozen evaluation (licensed-IP set, untouched by training or tuning; single pre-registered pass over its first public snapshot) | 57.0% top-1, 87.7% top-3, log-loss 1.132, ECE 0.005 |
| Path | Contents |
|---|---|
runs/<run_id>/best.pt | The 14 pinned PyTorch checkpoints evaluated in the paper: F-dev, F-full, scaling rungs s1–s16, and ablations (no-text, no-context, proportional, top-filter, no-UB) |
onnx/ | ONNX exports of the deployed model (fdev-20260704, f-full-20260705) |
run_manifest.json | Role → run_id → checkpoint sha256. The authoritative pins: make_paper_tables.py refuses mismatched or missing runs |
frozen_battery.json | The pre-registered evaluation battery (protocol v1.1), frozen before the MSH snapshot download |
ledger.jsonl | Append-only experiment ledger |
paper-data/runs/ | Run-level JSONs (configs, per-epoch metrics, eval summaries) consumed by scripts/make_paper_tables.py |
run_manifest.json; verify after
download. The frozen protocol, including the pre-registration chronology and
the post-day-one MSH ceiling, is documented in
docs/eval_protocol.md.1git clone https://github.com/brianward92/mtga
2cd mtga
3python -m venv .venv && .venv/bin/pip install -r requirements-foundation.txt
4# place this repo's paper-data/runs/ at paper/data/runs/
5.venv/bin/python scripts/make_paper_tables.pyMTGA_DATA_ROOT to a directory
with this repository's runs/ under foundation/ and see
scripts/run_frozen_eval.py.