site: the instrument section; neural demo pins index-v5

P3: /ml gains the measurement-discipline section - the five rules that exist because the naive version produced a wrong number we nearly shipped (full-set-only with the five subset-inflation instances; decode protocol as part of the number, beam-4 4.2x over greedy; label-provenance hashing; paired bootstrap CIs; checksummed index and the margins flip gate). P4: the neural demo moves its asset index pin from v3 to v5 (23-model catalog; proxy verified serving) and links its model select to the leaderboard for tier numbers.

Author: ronaldtse

src/pages/ml.astro

@@ -352,6 +352,50 @@ const clientModels = [
     </div>
   </section>
 
+  <!-- ════════════════════════════════════════════════════════════════
+       THE INSTRUMENT — why the numbers can be trusted
+       ════════════════════════════════════════════════════════════════ -->
+  <section class="section" id="instrument">
+    <div class="container contract-grid">
+      <div>
+        <p class="eyebrow">The instrument</p>
+        <h2>Every trap we fell into, now a rule.</h2>
+        <p class="section-deck">
+          Measurement discipline isn't ceremony — each of these rules exists because the naive
+          version produced a wrong number we nearly shipped. They are why a number on this page
+          means the same thing next month, on another machine.
+        </p>
+      </div>
+      <ul class="contract-facts instrument-facts">
+        <li>
+          <strong>Full evaluation sets, only.</strong> Five measured instances where evaluating
+          on a domain-neighborhood subset overstated student quality — worst case 3.2× (a claimed
+          0.72pp gap that was 2.28pp on the full set).
+        </li>
+        <li>
+          <strong>The decode protocol is part of the number.</strong> Beam-4 with length
+          normalization inflated a student's PER 4.2× over greedy on the same artifact (12.06
+          vs 2.85) — every published row names its decode.
+        </li>
+        <li>
+          <strong>Identical numbers must mean identical data.</strong> Label provenance is
+          content-hashed into every run record; a reproduced figure is only evidence of
+          reproducibility when the input pipeline is versioned.
+        </li>
+        <li>
+          <strong>CIs, not point estimates.</strong> Paired sentence-level bootstrap on every
+          verdict, deterministic seed — deltas come with their intervals.
+        </li>
+        <li>
+          <strong>Checksummed end to end.</strong> The index ships with a sha256 sidecar, every
+          zip member is verified on load, and a margins gate watches what the CER gate cannot
+          see — silent quantization flips (keeping the output head in fp32 cut them 36× at
+          +0.4% size).
+        </li>
+      </ul>
+    </div>
+  </section>
+
   <!-- ════════════════════════════════════════════════════════════════
        THE CONTRACT — IMF v1
        ════════════════════════════════════════════════════════════════ -->

src/pages/neural.astro

@@ -22,6 +22,10 @@ import Base from "../layouts/Base.astro"
       <option value="ara-diac-small-1.0-int8">Arabic diacritization — 1.0 (int8, 264 MB)</option>
       <option value="tha-g2p-small-1.0">Thai G2P — small (int8, 202 MB)</option>
     </select>
+    <p class="tier-hint">
+      Full-set numbers for every tier — the leaderboard and the client ladder — on
+      <a href="/ml#leaderboard">the neural layer page</a>.
+    </p>
 
     <label for="input">Input</label>
     <textarea id="input" rows="4" dir="auto">السلام عليكم ورحمة الله</textarea>
@@ -41,6 +45,14 @@ import Base from "../layouts/Base.astro"
 </Base>
 
 <style>
+  .tier-hint {
+    font-size: 0.8125rem;
+    opacity: 0.72;
+    margin: 0.4rem 0 1.25rem;
+  }
+  .tier-hint a {
+    text-decoration: underline;
+  }
   .progress-track {
     height: 8px;
     background: rgba(128, 128, 128, 0.25);
@@ -91,7 +103,7 @@ import Base from "../layouts/Base.astro"
 <script>
   import { imf } from "interscript/ml"
 
-  const ASSET_INDEX = "https://api.interscript.org/v1/assets/index-v3/models-index.yaml"
+  const ASSET_INDEX = "https://api.interscript.org/v1/assets/index-v5/models-index.yaml"
 
   const $ = (id: string) => document.getElementById(id)!
   let current: { dispose?(): Promise<void> } | null = null