Evidence
One page per claim, with its method and limits. The repeatable hardware measurements use one Comet and one mini PC, taken on 2026-09-29 and 2026-09-30. The NAS recovery is a separate operator account and post-mortem, without an independent action log. Raw test records are described on each page. A short video from the later Comet boot capture is published on the home page; the full raw frame set is not published.
Read in this order for the strongest proof first:
- Real recovery: nas-recovery.
- Platforms: platforms.
- OCR: ocr-role, then bios-ocr and vlm-vs-ocr.
| Page | Claim in one line |
|---|---|
| nas-recovery.md | A Comet with local OCR was used to diagnose and fix a real boot loop on a headless NAS |
| platforms.md | Linux tests recorded; Windows appears in an operator account without a repeatable suite |
| ocr-role.md | Why local OCR mattered in the recovery, using numbers from the pages below |
| mouse-accuracy.md | The target's kernel sees the mouse within 1/32767; X within 1 px |
| typing.md | 25/25 exact strings, fast and slow |
| bios-ocr.md | On a real BIOS, RapidOCR 0.98, Tesseract 0.94 |
| vlm-vs-ocr.md | Strict phrases of 32: local VLM 31, Tesseract 22, RapidOCR 16 |
| boot-menu-catch.md | Setup reached on a real AMI BIOS by tapping a key through POST |
| comet-quirks.md | What the Comet does differently from upstream PiKVM |
Common limits: one measured Comet setup, one test target, one operator. Nothing here is a vendor-wide success rate.