ember

14Reproducibility

Run these from a clone of the repository on Apple Silicon. Identical requests to the same server return identical answers, so a re-run on the pins below should reproduce these numbers.

make bootstrap               # dependencies, pinned weights, readiness check
ember start                  # warm model server on 127.0.0.1:8765
ember eval run               # every item; or --split test, --category <recipe>
ember eval export            # this report: Markdown, HTML, figures, raw data
ember eval report --compare results/<a>_results.json results/<b>_results.json
PinValue
Commitcadc1ec
Dataset SHA-2566a457f6badb7dd53b50a9ce04857d4d01e885d4718f3eb6db9db58658d9f923c
Model revision17f0b0ad64efb65d273590632833508766b2aae6
Results fileclef-flash_20261003T203810Z_results.json
Trace fileclef-flash_20261003T203810Z_trace.jsonl
Bootstrap1,000 resamples, seed 0, percentile interval
Package gut0.1.0
Package torch2.14.1
Package transformers5.18.0
Package mcp2.3.0