docs: deploy from e588597

model-bakeoff/index.html

@@ -1039,7 +1039,7 @@ caveat needed to trust the numbers.</p>
 <p>Read <a href="../methodology/">How we score against X-Ray</a> first for what F1,
 precision, recall, and misID mean in this report. All numbers below use the
 per-second metric
-(<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/0bd27470698c45cab21935d636a04512360e1008/scripts/optimizer/second_score.py"><code>scripts/optimizer/second_score.py</code></a>).</p>
+(<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/e5885977dfd04741a0d1bb7aaf0270d9c40a2fa8/scripts/optimizer/second_score.py"><code>scripts/optimizer/second_score.py</code></a>).</p>
 <p>r50 (ArcFace w600k-R50) is excluded from the detailed comparison below. Its
 gallery was built with roughly 30% fewer reference images per actor than the
 other three models on the identical source photos (10808 vs 15055 total
@@ -1057,8 +1057,8 @@ output, and the cheap stage can be re-run against that cache as many times
 as needed with different Config values.</p>
 <p><code>scene_analyze --dump-embeddings out.h5</code> runs the expensive half once per
 film and writes per-frame face detections and embeddings to HDF5
-(<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/0bd27470698c45cab21935d636a04512360e1008/scripts/optimizer/SCHEMA.md"><code>scripts/optimizer/SCHEMA.md</code></a>).
-<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/0bd27470698c45cab21935d636a04512360e1008/scripts/optimizer/replay.py"><code>scripts/optimizer/replay.py</code></a>
+(<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/e5885977dfd04741a0d1bb7aaf0270d9c40a2fa8/scripts/optimizer/SCHEMA.md"><code>scripts/optimizer/SCHEMA.md</code></a>).
+<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/e5885977dfd04741a0d1bb7aaf0270d9c40a2fa8/scripts/optimizer/replay.py"><code>scripts/optimizer/replay.py</code></a>
 then re-assembles the real C++ <code>face_tracker</code>, <code>identity_matcher</code>, and
 <code>scene_tracker</code> nodes into a Python-driven KPN network and replays a
 film's cached embeddings through them, varying <code>prob_threshold</code>,
@@ -1507,7 +1507,7 @@ runtime feature of the application; see
 into the application would require.</p>
 <p><strong>Pose expansion</strong> (promoting a confidently identified track's novel-pose
 views into a per-film gallery annex,
-<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/0bd27470698c45cab21935d636a04512360e1008/src/gallery/track_gallery.hpp"><code>src/gallery/track_gallery.hpp</code></a>):</p>
+<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/e5885977dfd04741a0d1bb7aaf0270d9c40a2fa8/src/gallery/track_gallery.hpp"><code>src/gallery/track_gallery.hpp</code></a>):</p>
 <table>
 <thead>
 <tr>
@@ -1563,7 +1563,7 @@ and the two methodology bugs caught while checking it.</p>
 <h2 id="calibration-curves">Calibration curves<a class="headerlink" href="#calibration-curves" title="Permanent link">&para;</a></h2>
 <p>Each gallery carries a fitted Platt sigmoid <code>P(match | sim) = σ(a·sim + b)</code>,
 stored directly in the gallery HDF5
-(<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/0bd27470698c45cab21935d636a04512360e1008/src/gallery/gallery_calibration.hpp"><code>src/gallery/gallery_calibration.hpp</code></a>).
+(<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/e5885977dfd04741a0d1bb7aaf0270d9c40a2fa8/src/gallery/gallery_calibration.hpp"><code>src/gallery/gallery_calibration.hpp</code></a>).
 This measures discriminative power independent of whatever
 <code>prob_threshold</code> a given run used:</p>
 <p><img alt="Calibrated P(match|similarity) for all four models" src="../assets/images/calibration_curves.png" /></p>
@@ -1572,7 +1572,7 @@ variants) and the lowest P=0.5 decision boundary (similarity 0.23 vs
 0.27-0.31), separating same-actor from different-actor pairs more
 confidently at a lower similarity than any ArcFace variant tested,
 including r50. Generated by
-<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/0bd27470698c45cab21935d636a04512360e1008/scripts/docs/calibration_chart.py"><code>scripts/docs/calibration_chart.py</code></a>.</p>
+<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/e5885977dfd04741a0d1bb7aaf0270d9c40a2fa8/scripts/docs/calibration_chart.py"><code>scripts/docs/calibration_chart.py</code></a>.</p>
 <h2 id="extinction-and-anneal-window-search">Extinction and anneal window search<a class="headerlink" href="#extinction-and-anneal-window-search" title="Permanent link">&para;</a></h2>
 <p>Every one of the 512 DE evaluations for the winning LVFace <code>full_exp</code>
 combo, plotted over the <code>prob_threshold</code> × <code>extinction_sec</code> plane:</p>
@@ -1632,7 +1632,7 @@ past 60s, or does it plateau there. Not chased further this pass.</p>
 </span><span id="__span-0-24"><a id="__codelineno-0-24" name="__codelineno-0-24" href="#__codelineno-0-24"></a>python3<span class="w"> </span>scripts/docs/first_fpi_frames.py
 </span></code></pre></div>
 <p>See also the session log
-<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/0bd27470698c45cab21935d636a04512360e1008/experiments/SESSION_STATE.md"><code>experiments/SESSION_STATE.md</code></a>.</p>
+<a href="https://gitea.tourolle.paris/dtourolle/scene-actor-extraction/raw/commit/e5885977dfd04741a0d1bb7aaf0270d9c40a2fa8/experiments/SESSION_STATE.md"><code>experiments/SESSION_STATE.md</code></a>.</p>