# Executive summary


---
<!-- trackio-cell
{"type": "markdown", "id": "cell_180b988a36f6", "created_at": "2026-07-30T21:15:00+00:00", "title": "Executive summary", "pinned": true, "pinned_at": "2026-07-30T21:15:00+00:00"}
-->
Five live claims receive direct native evidence: the shared-prototype mechanism and Val5 best-case gain reproduce; the 0.7472 macro and S=2 ablation peak fail to reproduce under the printed algorithm; and the exact prototype-sharing work is 6.08% of per-worker confusion-matrix state. Ten public datasets match all registered scale fields exactly. Paired warning-strict runs and a packaged replay are byte-identical; no peer artifact, source-only abstention, or substitute benchmark is counted.

Primary records: [OpenReview](https://openreview.net/forum?id=KJq0iScNM6) and [arXiv](https://arxiv.org/abs/2508.02123).


---
<!-- trackio-cell
{"type": "figure", "id": "cell_293b9207228b", "created_at": "2026-07-30T21:15:00+00:00", "title": "Reproduction poster", "pinned": true, "pinned_at": "2026-07-30T21:15:00+00:00", "poster": true}
-->
````html
<iframe src="../../poster_embed.html" style="width:100%;height:430px;border:0" title="PTBCC reproduction poster"></iframe>
````