Add verified Raspberry Pi 5 edge performance measurements

Record actual 16 GB Pi 5 latency, RAM and correctness with frozen evaluation inputs, raw per-call measurements, runtime hashes and reproducible settings. Preserve weights and existing training data.

README.md

@@ -90,7 +90,7 @@ web UI and Docker image.
 <!-- rpi5-measurements -->
 ## Raspberry Pi 5 edge-device performance
 
-Measured **2026-09-26** on a **Raspberry Pi 5 Model B, 16 GB RAM**, Debian 13.2/aarch64, Python 3.13.5. Measurement update: `edge-rpi5-20260926`; weights and training data are unchanged.
+Measured **2026-09-26** on a **Raspberry Pi 5 Model B, 16 GB RAM**, Debian 13.2/aarch64, Python 3.13.5. Measurement update: `edge-rpi5-20260926.1`; weights and training data are unchanged.
 
 | Threads | Median ms | p95 ms | p99 ms | Serial requests/s | Process RSS MiB | CPU °C min–mean–max | Timed correct |
 | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
@@ -101,7 +101,7 @@ Batch 1; 20 warmups and 500 timed calls per row, cycling over 10 frozen model-sp
 
 On-device quality check: **192/200** on training-set diagnostic, NOT held-out accuracy. For v3 this is explicitly a training-set diagnostic, not held-out accuracy; the earlier 96.73% result was not rerun.
 
-[Full Pi methodology, temperature plot and reproduction](edge_benchmarks/rpi5-2026-09-26/REPORT.md) · [Every latency/temperature reading](edge_benchmarks/rpi5-2026-09-26/readings.csv) · [Raw measurements](edge_benchmarks/rpi5-2026-09-26/results) · [Versioned evaluation data](https://huggingface.co/datasets/sraivante/home-commands-json-v3/tree/edge-rpi5-20260926/edge_benchmarks/rpi5-2026-09-26).
+[Full Pi methodology, temperature plot and reproduction](edge_benchmarks/rpi5-2026-09-26/REPORT.md) · [Every latency/temperature reading](edge_benchmarks/rpi5-2026-09-26/readings.csv) · [Raw measurements](edge_benchmarks/rpi5-2026-09-26/results) · [Versioned evaluation data](https://huggingface.co/datasets/sraivante/home-commands-json-v3/tree/edge-rpi5-20260926.1/edge_benchmarks/rpi5-2026-09-26).
 <!-- /rpi5-measurements -->
 
 ## Why a tiny model and not an LLM

edge_benchmarks/rpi5-2026-09-26/REPORT.md

@@ -1,6 +1,6 @@
 # Raspberry Pi 5 measurements — Tiny Home Robotics JSON 1M v3
 
-Measured on 2026-09-26; measurement revision `edge-rpi5-20260926`. The model weights and training data were not changed.
+Measured on 2026-09-26; measurement revision `edge-rpi5-20260926.1`. The model weights and training data were not changed.
 
 Hardware: **Raspberry Pi 5 Model B Rev 1.1**, 15.84 GiB OS-visible RAM (16 GB model), four CPU cores, aarch64, Debian 13.2, kernel `6.12.47+rpt-rpi-2712`. Python 3.13.5. The device's governor and library versions are recorded in each JSON result. Cooling and power-supply model were not inspected.
 
@@ -39,12 +39,12 @@ Timed-correct counts above describe the repeated ten-input latency set, not an i
 - Published model tested: [`sraivante/superfast-tiny-home-robotics-json-1m-v3@2b2e71d37ea9fa0fe6ab247b6a74e8db774fb6f2`](https://huggingface.co/sraivante/superfast-tiny-home-robotics-json-1m-v3/tree/2b2e71d37ea9fa0fe6ab247b6a74e8db774fb6f2). All tested runtime assets were checked against this revision.
 - Learned weight SHA-256: `fc749ecd89c1ae30a159d6d701036298b5583645b7fbf114311e006929c8778b` (2,146,783 bytes).
 - Associated preserved training dataset: [`sraivante/home-commands-json-v3@da10aca352a34cb2834a049867f6f2e9fcc30e3e`](https://huggingface.co/datasets/sraivante/home-commands-json-v3/tree/da10aca352a34cb2834a049867f6f2e9fcc30e3e). Existing source/split hashes and historical provenance remain in that snapshot. No fine-tuning was performed for this measurement update.
-- The [versioned evaluation inputs and Pi predictions](https://huggingface.co/datasets/sraivante/home-commands-json-v3/tree/edge-rpi5-20260926/edge_benchmarks/rpi5-2026-09-26) record the new diagnostic snapshot. `provenance.json` records its hashes, counts, source revisions, and historical identity limitations.
+- The [versioned evaluation inputs and Pi predictions](https://huggingface.co/datasets/sraivante/home-commands-json-v3/tree/edge-rpi5-20260926.1/edge_benchmarks/rpi5-2026-09-26) record the new diagnostic snapshot. `provenance.json` records its hashes, counts, source revisions, and historical identity limitations.
 - [Runtime identity check](runtime_identity.json); [raw per-call records](results); [exact environment](environment.lock.txt).
 
 ## Reproduce
 
-Use a 64-bit Raspberry Pi in an isolated environment. Download this model repository at `edge-rpi5-20260926`, then run:
+Use a 64-bit Raspberry Pi in an isolated environment. Download this model repository at `edge-rpi5-20260926.1`, then run:
 
 ```bash
 python3 -m venv .venv

edge_benchmarks/rpi5-2026-09-26/provenance.json

@@ -1,5 +1,5 @@
 {
-  "measurement_revision": "edge-rpi5-20260926",
+  "measurement_revision": "edge-rpi5-20260926.1",
   "model": {
     "repo_id": "sraivante/superfast-tiny-home-robotics-json-1m-v3",
     "revision": "2b2e71d37ea9fa0fe6ab247b6a74e8db774fb6f2",