diff --git a/complete/2026/08/jax-likelihood-smoke-pins-stale.md b/complete/2026/08/jax-likelihood-smoke-pins-stale.md
new file mode 100644
index 00000000..2cefbe47
--- /dev/null
+++ b/complete/2026/08/jax-likelihood-smoke-pins-stale.md
@@ -0,0 +1,130 @@
+# The jax_likelihood smoke-pin bug was already fixed when it was filed
+
+Retired unstarted on 2026-08-26 by a `/start_dev` research pass. Never issued
+as a GitHub issue and never developed: the four failures the prompt describes
+had all been resolved on `autolens_workspace_test` main by 2026-08-22, most of
+them within hours of the prompt being written. Recorded rather than deleted
+because the *reason* it went stale is the reusable finding.
+
+## Verified state at retirement
+
+`autolens_workspace_test` main `8be3d59`, Smoke Tests run
+[32922456742](https://github.com/PyAutoLabs/autolens_workspace_test/actions/runs/32922456742)
+(2026-08-26 02:24 UTC), green on both Python 3.12 and 3.13:
+
+```
+Running 22 listed scripts
+  scripts/imaging/jax_likelihood/lp.py ...              PASS (9.8s)
+  scripts/interferometer/jax_likelihood/rectangular.py  PASS (21.1s)
+  scripts/interferometer/jax_likelihood/mge.py ...      PASS (12.6s)
+  ... 22/22 PASS
+```
+
+The prompt's headline — "every workspace_test smoke sweep reads 20/24 until
+this lands" — is now 22/22. The denominator moved too: two further entries
+left `smoke_tests.txt` for reasons unrelated to pins.
+
+## Disposition of each claim
+
+- **`imaging/jax_likelihood/lp.py`, pin `-1.34797827e09` is double.** Fixed.
+  Repinned to `-6.74165366e08` in `197ce6e` (autolens_workspace_test#257) on
+  2026-08-19 — the same day the prompt was filed.
+- **"The unmerged fix `fb1aefe0b` sits in the orphan worktree
+  `~/Code/PyAutoLabs-wt/positions-lh-penalty-accumulation`; landing it and
+  re-pinning must happen together."** Both had already happened. `fb1aefe0b`
+  is the head SHA of [PyAutoLens#700](https://github.com/PyAutoLabs/PyAutoLens/pull/700)
+  ("sum PositionsLH penalties instead of doubling the last entry", fixes
+  PyAutoLens#699), merged 2026-08-17 — two days *before* the prompt called it
+  unmerged. `197ce6e` is precisely the paired re-pin the prompt asked for, and
+  it repinned five scripts, not four (it also caught
+  `interferometer/jax_likelihood/lp.py` and both `imaging/substructure/subhalo.py`
+  pairs).
+- **`interferometer/jax_likelihood/rectangular.py` misses pin `-3164.286252` by
+  0.0124% vs rtol 1e-4.** Passing. The pin literal is *unchanged* to this day,
+  and `99d63b3` (2026-08-21) re-verified the script green including its
+  TransformerNUFFT cross-check. So the 08-19 miss was environment drift in the
+  control run, not a stale pin — nothing to recalibrate and no tolerance to
+  widen.
+- **`interferometer/jax_likelihood/mge.py`, "same stale-pin family".** Fixed by
+  the same `197ce6e`: `-7.94439429e08` -> `-3.97221282e08`, i.e. it was a
+  PositionsLH-doubling casualty, not an independent drift.
+- **`multi_dataset/jax_likelihood/mge.py`, "same stale-pin family".** Never a
+  pin problem. Commented out of `smoke_tests.txt` on 2026-08-22 (#262) for
+  hanging to the 300s cap — the family-wide XLA compile stall tracked in
+  autolens_workspace_test#245. Its pin (`EXPECTED_VMAP_LOG_LIKELIHOOD =
+  -2173221.43685875`) is untouched since the `multi` -> `multi_dataset` rename
+  (`d7cc60c`) and has never been shown wrong.
+
+## Key traps / findings
+
+- **A control-test finding has a shelf life measured in hours.** This prompt
+  was written from a control run taken during `lazy-heavy-imports` (#1505) and
+  was obsolete before the day was out — `197ce6e` landed 2026-08-19 10:25 EDT.
+  Filing a finding is not the same as checking whether someone is already on
+  it; a pass over recent commits touching the named files would have caught it.
+- **"Orphan worktree" is a claim about a laptop, not about a repository.** A
+  local worktree whose branch has been merged and deleted upstream looks
+  identical to one holding genuinely unlanded work. The check that settles it
+  is the branch's head SHA against the remote's merged PRs — here `fb1aefe0b`
+  resolved straight to a PR merged two days earlier. Adjudicate an orphan from
+  the remote, never from the worktree's own state.
+- **One root cause can wear several symptom labels.** Three of the four listed
+  scripts were the *same* bug (the 2x-last PositionsLH penalty), not a
+  "stale-pin family". Grouping symptoms by folder invented a class of drift
+  that did not exist and would have sent the fix in the wrong direction —
+  widening tolerances on correct pins.
+- **A script leaving the smoke gate changes the denominator.** A pass/total
+  target like "20/24" is not a stable goal: `multi_dataset/jax_likelihood/mge.py`
+  and `multi_dataset/jax_likelihood/shared_preloads.py` both left the list for
+  timing reasons, so the sweep now reads 22/22 without any pin having been
+  touched for that.
+
+## Follow-ups
+
+- **Local debris only.** `~/Code/PyAutoLabs-wt/positions-lh-penalty-accumulation`
+  is a stale worktree over a merged-and-deleted branch on the laptop; it is a
+  `/repo_cleanup` item, not code work, and no cloud session can see or clear
+  it.
+- **Latent, owned elsewhere.** `multi_dataset/jax_likelihood/mge.py`'s pin has
+  never been verified against a post-PyAutoLens#700 library. If
+  autolens_workspace_test#245's XLA stall is fixed and the script returns to
+  the gate, re-derive its pin as part of that re-enable rather than trusting
+  the pre-rename literal. Deliberately not filed as its own prompt — it has no
+  standalone trigger.
+
+## Original prompt
+
+# autolens_workspace_test jax_likelihood pins: 4 scripts fail smoke on main
+
+Type: bug
+Target: autolens
+Repos:
+- @PyAutoLens
+Difficulty: low
+Autonomy: supervised
+Priority: normal
+Status: draft
+Filed: 2026-08-19 (backfilled from git)
+
+## Finding (2026-08-19, control-tested during lazy-heavy-imports #1505)
+
+`pyauto-heart smoke autolens_test` fails 4/24 on canonical main (verified twice,
+worktree and canonical identical):
+
+- `imaging/jax_likelihood/lp.py` — vmap result is ~half the hardcoded pin
+  `-1.34797827e09`. This is the positions-LH penalty-doubling: the unmerged fix
+  `fb1aefe0b` ("sum PositionsLH penalties instead of doubling the last entry")
+  sits in the orphan worktree `~/Code/PyAutoLabs-wt/positions-lh-penalty-accumulation`
+  (PyAutoLens). The pin was calibrated against the doubling behaviour — landing
+  that fix and re-pinning must happen together.
+- `interferometer/jax_likelihood/rectangular.py` — misses pin `-3164.286252` by
+  0.0124% vs rtol 1e-4 (stale-pin drift).
+- `interferometer/jax_likelihood/mge.py`, `multi_dataset/jax_likelihood/mge.py` —
+  same stale-pin family.
+
+## Task
+
+Adjudicate the orphan positions-LH worktree (land or discard `fb1aefe0b`), then
+recalibrate the four scripts' hardcoded pins against current main and widen
+tolerances where the value is legitimately environment-sensitive. Every
+workspace_test smoke sweep reads 20/24 until this lands.
diff --git a/complete/index.md b/complete/index.md
index 84c66e86..f8ea91dd 100644
--- a/complete/index.md
+++ b/complete/index.md
@@ -6,7 +6,7 @@ Token-light navigation over the finished-work records (schema:
 only then grep a dated bucket. Curators: edit the band between the CURATED
 markers; everything below GENERATED is rebuilt.
 
-1142 records across 7 buckets.
+1143 records across 7 buckets.
 
 <!-- CURATED:START -->
 ## Highlights
@@ -122,6 +122,7 @@ _(curate hard-won records here — survives regeneration.)_
 - [jax-grad-local-vs-ci-assertions](2026/08/jax-grad-local-vs-ci-assertions.md)
 - [jax-grad-smoke-timeout-budget](2026/08/jax-grad-smoke-timeout-budget.md)
 - [jax-likelihood-mass-sensitivity](2026/08/jax-likelihood-mass-sensitivity.md) — Audit + fix for median-literal mass blindness across all jax_likelihood/datacube scripts (phase 2 of the findi…
+- [jax-likelihood-smoke-pins-stale](2026/08/jax-likelihood-smoke-pins-stale.md)
 - [jax-stall-shared-preloads-retime-refutation](2026/08/jax-stall-shared-preloads-retime-refutation.md)
 - [knowledge-board](2026/08/knowledge-board.md) — auto-closed on merge
 - [lacosmic-cr-option-and-star-pass-decoupling](2026/08/lacosmic-cr-option-and-star-pass-decoupling.md) — both deliberately OPEN — closure is the default-flip decision, not this ship
diff --git a/dashboard.html b/dashboard.html
index f1fa40b3..718265b2 100644
--- a/dashboard.html
+++ b/dashboard.html
@@ -185,7 +185,7 @@
 </head>
 <body>
 <header class="hero"><span class="orb"><svg class="mark" viewBox="0 0 48 48" fill="none" stroke="currentColor" stroke-width="1.3" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><circle cx="24" cy="24" r="20.4"/><path d="M20.2,37.6 L20.2,33.6 C20.2,32.4 19.4,31.6 18.4,30.8 C16.8,29.6 15.8,28.2 15.6,26.6 C15.5,25.6 14.9,25.2 13.9,24.9 C12.6,24.5 12.3,23.7 13.0,22.7 C13.8,21.6 14.5,20.6 14.6,19.4 C15.0,15.4 18.2,12.2 22.4,11.8 C27.2,11.3 31.6,14.6 32.3,19.2 C32.8,22.4 31.6,25.0 30.6,27.0 C29.9,28.4 29.6,29.6 29.6,31.2 L29.6,37.6"/><circle cx="24.6" cy="19.6" r="4.4"/><path d="M22.5,19.7 L24.0,21.3 L26.8,18.1"/><path d="M34.2,16.5 L38.8,16.5 M35.2,21.0 L39.4,21.0 M33.6,25.5 L37.2,25.5"/><g fill="currentColor" stroke="none"><circle cx="40.1" cy="16.5" r="1.4"/><circle cx="40.7" cy="21.0" r="1.4"/><circle cx="38.5" cy="25.5" r="1.4"/></g></svg></span><h1>PyAuto<b>Mind</b><span class="kind">Dashboard</span></h1><div class="rule"></div><p class="tag">Intent. Priority. Flow.</p></header><p class="lede">Every task the Mind is holding. Tap a task's 📋 and its <code>/start_dev</code> command is on your clipboard — paste it into a Claude Code chat to route Claude straight to that task. <a href="#recent">Recent</a> is the same work by date — what has been happening rather than what to do next.</p>
-<ul class="stats"><li><b>1</b><span>In flight</span></li><li><b>3</b><span>Parked</span></li><li><b>5</b><span>Planned</span></li><li><b>135</b><span>Backlog</span></li></ul>
+<ul class="stats"><li><b>1</b><span>In flight</span></li><li><b>3</b><span>Parked</span></li><li><b>5</b><span>Planned</span></li><li><b>134</b><span>Backlog</span></li></ul>
 <div class="fresh"><p><b>Last updated 2026-08-26.</b> This page is generated from <code>active/</code>, <code>draft/</code> and the registry files, so it is only as current as they are. <code>dashboard_refresh.yml</code> re-renders it on every push to <code>main</code> — that heals a stale page, but not a stale prompt: a task that shipped without its prompt advancing to <code>complete/</code> keeps rendering here as pickable backlog. Reconciling those is the refresh below.</p>
 <div class="task"><button class="copy" data-cmd="Bring the PyAutoMind dashboard up to date. Work in the PyAutoMind checkout:
 
@@ -250,7 +250,7 @@ <h2>Planned <a class="mdsrc" href="https://github.com/PyAutoLabs/PyAutoMind/blob
 <div class="task"><button class="copy" data-cmd="/route start the planned PyAutoMind task latent-nan-guard-honest-run — its record is in planned.md" aria-label="Copy the Claude command">📋</button><p><b>latent-nan-guard-honest-run</b><span class="facets"> — planned 2026-07-22</span></p></div>
 </details>
 <h2>Backlog <a class="mdsrc" href="https://github.com/PyAutoLabs/PyAutoMind/tree/main/draft">markdown version</a></h2>
-<p class="muted">135 filed prompts, not started — sorted most-pickable first (priority, then size). 25 of them belong to an epic and are listed only under Epics below.</p>
+<p class="muted">134 filed prompts, not started — sorted most-pickable first (priority, then size). 25 of them belong to an epic and are listed only under Epics below.</p>
 <details>
 <summary>feature — 27</summary>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/feature/autoarray/numba_cpu_likelihood_mge_convolution_and_caching.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/feature/autoarray/numba_cpu_likelihood_mge_convolution_and_caching.md">Numba CPU likelihood phase 1: batched MGE convolution + operated-matrix caching</a><span class="tags"><span class="pill w">✨ feature</span><span class="pill">autoarray</span><span class="pill n">medium</span><span class="pill n">supervised</span><span class="pill r">high</span></span></p></div>
@@ -325,7 +325,7 @@ <h2>Backlog <a class="mdsrc" href="https://github.com/PyAutoLabs/PyAutoMind/tree
 <div class="task"><button class="copy" data-cmd="/start_dev draft/research/autolens_profiling/cluster_gradient_search_benchmark.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/research/autolens_profiling/cluster_gradient_search_benchmark.md">Cluster-scale gradient-search benchmark (Prodigy vs Nautilus, point-source)</a><span class="tags"><span class="pill w">🔬 research</span><span class="pill">autolens_profiling</span></span></p></div>
 </details>
 <details>
-<summary>bug — 18</summary>
+<summary>bug — 17</summary>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/health_fixes/jax_runtime_and_parity.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/health_fixes/jax_runtime_and_parity.md">Fix release JAX runtime compatibility and likelihood parity</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">health_fixes</span><span class="pill r">too-large</span><span class="pill n">supervised</span><span class="pill r">high</span></span></p></div>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/health_fixes/jit_visualization_outputs.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/health_fixes/jit_visualization_outputs.md">Fix JIT quick-update visualization output regressions</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">health_fixes</span><span class="pill r">too-large</span><span class="pill n">supervised</span><span class="pill r">high</span></span></p></div>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/health_fixes/samples_parameter_paths.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/health_fixes/samples_parameter_paths.md">Fix release result/sample parameter-path regressions</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">health_fixes</span><span class="pill r">too-large</span><span class="pill n">supervised</span><span class="pill r">high</span></span></p></div>
@@ -340,7 +340,6 @@ <h2>Backlog <a class="mdsrc" href="https://github.com/PyAutoLabs/PyAutoMind/tree
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/health_fixes/release_timeout_policy.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/health_fixes/release_timeout_policy.md">Resolve release-profile timeout scripts deliberately</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">health_fixes</span><span class="pill r">too-large</span><span class="pill n">supervised</span><span class="pill n">normal</span></span></p></div>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/priors/14_replace_transform_stack_with_bijectors.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/priors/14_replace_transform_stack_with_bijectors.md"><code>@PyAutoFit</code> Refactor: replace hand-rolled <code>AbstractDensityTransform</code> with <code>tfp.bijectors</code> / <code>numpyro.distributions.transforms</code></a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">priors</span><span class="pill r">too-large</span><span class="pill n">supervised</span><span class="pill n">normal</span></span></p></div>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/priors/z_features.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/priors/z_features.md">Priors &amp; Messages cleanup — tracker</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">priors</span><span class="pill r">too-large</span><span class="pill n">supervised</span><span class="pill n">normal</span></span></p></div>
-<div class="task"><button class="copy" data-cmd="/start_dev draft/bug/autolens/jax_likelihood_smoke_pins_stale.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/autolens/jax_likelihood_smoke_pins_stale.md">autolens_workspace_test jax_likelihood pins: 4 scripts fail smoke on main</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">autolens</span><span class="pill n">low</span><span class="pill n">supervised</span><span class="pill n">normal</span></span></p></div>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/autoarray/reconstruction_noise_map_solver_mismatch.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/autoarray/reconstruction_noise_map_solver_mismatch.md">The reconstruction noise map describes a different estimator than the default solver</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">autoarray</span><span class="pill n">medium</span><span class="pill r">human-required</span><span class="pill n">low</span></span></p></div>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/pyautolens/point_source_json_datasets_record_no_regime.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/pyautolens/point_source_json_datasets_record_no_regime.md">Point-source JSON datasets record no resolution regime</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">pyautolens</span><span class="pill n">medium</span><span class="pill n">supervised</span><span class="pill n">low</span></span></p></div>
 <div class="task"><button class="copy" data-cmd="/start_dev draft/bug/autolens/interferometer_release_leg_oom.md" aria-label="Copy the Claude command">📋</button><p><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/autolens/interferometer_release_leg_oom.md">interferometer/start_here.py OOM in nightly release-validation integrate leg</a><span class="tags"><span class="pill w">🐛 bug</span><span class="pill">autolens</span></span></p></div>
@@ -502,12 +501,6 @@ <h2>Backlog <a class="mdsrc" href="https://github.com/PyAutoLabs/PyAutoMind/tree
 <tr hidden>
 <td class="when">2026-08-19</td>
 <td class="what">filed</td>
-<td><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/autolens/jax_likelihood_smoke_pins_stale.md">autolens_workspace_test jax_likelihood pins: 4 scripts fail smoke on…</a></td>
-<td class="pick"><button class="copy" data-cmd="/start_dev draft/bug/autolens/jax_likelihood_smoke_pins_stale.md" aria-label="Copy the Claude command">📋</button></td>
-</tr>
-<tr hidden>
-<td class="when">2026-08-19</td>
-<td class="what">filed</td>
 <td><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/research/autofit/autofit_profiling_bootstrap.md">autofit_profiling: bootstrap the repo + general PyAutoFit profiling…</a></td>
 <td class="pick"><button class="copy" data-cmd="/start_dev draft/research/autofit/autofit_profiling_bootstrap.md" aria-label="Copy the Claude command">📋</button></td>
 </tr>
@@ -691,6 +684,12 @@ <h2>Backlog <a class="mdsrc" href="https://github.com/PyAutoLabs/PyAutoMind/tree
 <td><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/docs/workspaces/plot_coverage_followups.md">plot coverage — follow-ups deferred from plot-coverage-gaps</a></td>
 <td class="pick"><button class="copy" data-cmd="/start_dev draft/docs/workspaces/plot_coverage_followups.md" aria-label="Copy the Claude command">📋</button></td>
 </tr>
+<tr hidden>
+<td class="when">2026-07-30</td>
+<td class="what">filed</td>
+<td><a href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/draft/bug/pyautohands/generate_rejects_autocti_after_deleting_notebooks.md"><code>generate.py</code> deletes notebooks/ before rejecting an unknown project</a></td>
+<td class="pick"><button class="copy" data-cmd="/start_dev draft/bug/pyautohands/generate_rejects_autocti_after_deleting_notebooks.md" aria-label="Copy the Claude command">📋</button></td>
+</tr>
 </table>
 <button class="more" data-page="10">… 10 more (40 left)</button>
 <h2>Epics <a class="mdsrc" href="https://github.com/PyAutoLabs/PyAutoMind/blob/main/epics.md">markdown version</a></h2>
diff --git a/dashboard.md b/dashboard.md
index eb8cee04..a1a562d6 100644
--- a/dashboard.md
+++ b/dashboard.md
@@ -45,7 +45,7 @@ anything you could not verify.
 | [In flight](#in-flight) (`active/`) | 1 |
 | [Parked](#parked) (`parked.md`) | 3 |
 | [Planned](#planned) (`planned.md`) | 5 |
-| [Backlog](#backlog) (`draft/`) | 135 |
+| [Backlog](#backlog) (`draft/`) | 134 |
 
 ## Start here
 
@@ -247,7 +247,7 @@ Scoped but not started; some are not yet prompt files. Full detail in [`planned.
 
 ## Backlog
 
-**135** filed prompts, not started. Each section is sorted most-pickable first (priority, then size). **25** of them belong to an epic and are listed only under [Epics](#epics) below.
+**134** filed prompts, not started. Each section is sorted most-pickable first (priority, then size). **25** of them belong to an epic and are listed only under [Epics](#epics) below.
 
 <details>
 <summary><b>feature</b> — 27</summary>
@@ -777,7 +777,7 @@ Scoped but not started; some are not yet prompt files. Full detail in [`planned.
 </details>
 
 <details>
-<summary><b>bug</b> — 18</summary>
+<summary><b>bug</b> — 17</summary>
 
 <details><summary>📋 <a href="draft/bug/health_fixes/jax_runtime_and_parity.md">Fix release JAX runtime compatibility and likelihood parity</a> — health_fixes · too-large · supervised · high</summary>
 
@@ -891,14 +891,6 @@ Scoped but not started; some are not yet prompt files. Full detail in [`planned.
 
 </details>
 
-<details><summary>📋 <a href="draft/bug/autolens/jax_likelihood_smoke_pins_stale.md">autolens_workspace_test jax_likelihood pins: 4 scripts fail smoke on main</a> — autolens · low · supervised · normal</summary>
-
-```
-/start_dev draft/bug/autolens/jax_likelihood_smoke_pins_stale.md
-```
-
-</details>
-
 <details><summary>📋 <a href="draft/bug/autoarray/reconstruction_noise_map_solver_mismatch.md">The reconstruction noise map describes a different estimator than the default solver</a> — autoarray · medium · human-required · low</summary>
 
 ```
@@ -1203,14 +1195,13 @@ The 50 newest things to happen to the work in hand, newest first — issued, par
 | 2026-08-21 | filed | <a href="draft/feature/autoarray/rectangular_bilinear_rtu_mesh_split.md">Rectangular mesh split: Bilinear (fast CPU default) vs RTU…</a> |
 | 2026-08-20 | filed | <a href="draft/feature/autoarray/numba_cpu_likelihood_kernel_cdf_fast_path.md">Numba CPU likelihood phase 2: kernel-CDF numba fast path (the 49-88%…</a> |
 | 2026-08-20 | filed | <a href="draft/feature/autoarray/numba_cpu_likelihood_mge_convolution_and_caching.md">Numba CPU likelihood phase 1: batched MGE convolution +…</a> |
-| 2026-08-19 | filed | <a href="draft/bug/autolens/jax_likelihood_smoke_pins_stale.md">autolens_workspace_test jax_likelihood pins: 4 scripts fail smoke on…</a> |
 | 2026-08-19 | filed | <a href="draft/research/autofit/autofit_profiling_bootstrap.md">autofit_profiling: bootstrap the repo + general PyAutoFit profiling…</a> |
+| 2026-08-19 | issued | <a href="active/16_transformed_message_factor_gradient_unpack.md"><code>@PyAutoFit</code> <code>TransformedMessage.factor_gradient</code> crashes on first…</a> |
 
 <details><summary>… 10 more (30 left)</summary>
 
 | Date | Event | Task |
 |------|-------|------|
-| 2026-08-19 | issued | <a href="active/16_transformed_message_factor_gradient_unpack.md"><code>@PyAutoFit</code> <code>TransformedMessage.factor_gradient</code> crashes on first…</a> |
 | 2026-08-19 | filed | <a href="draft/feature/pyautohands/release_board_run_logs_enrichment.md">Release board: local run_logs enrichment</a> |
 | 2026-08-19 | filed | <a href="draft/docs/pyautobrain/rtd_organism_currency.md">RTD organism docs currency: Nerves page, organ-count drift, hands.md…</a> |
 | 2026-08-19 | filed | <a href="draft/refactor/pyautomind/repos_sync_check_dedup.md">Deduplicate repos_sync.py's check/write pairs</a> |
@@ -1220,12 +1211,12 @@ The 50 newest things to happen to the work in hand, newest first — issued, par
 | 2026-08-18 | filed | <a href="draft/bug/priors/15_transformed_message_logpdf_jacobian.md"><code>@PyAutoFit</code> <code>TransformedMessage.logpdf</code>/<code>pdf</code> omit the transform…</a> |
 | 2026-08-17 | filed | <a href="draft/feature/autofit/prior_exit_sampler_coverage.md">Which other searches need prior-support handling — coverage audit…</a> |
 | 2026-08-17 | filed | <a href="draft/feature/pyautomind/repos-sync-config-stamper.md">Teach repos_sync --write to stamp organ config surfaces</a> |
+| 2026-08-16 | filed | <a href="draft/bug/autofit/loggaussian_prior_declares_own_support.md"><code>LogGaussianPrior</code> misreports its own support as <code>(-inf, inf)</code></a> |
 
 <details><summary>… 10 more (20 left)</summary>
 
 | Date | Event | Task |
 |------|-------|------|
-| 2026-08-16 | filed | <a href="draft/bug/autofit/loggaussian_prior_declares_own_support.md"><code>LogGaussianPrior</code> misreports its own support as <code>(-inf, inf)</code></a> |
 | 2026-08-14 | filed | <a href="draft/bug/workspaces/jax_likelihood_pins_stale_by_1e4.md">Three <code>jax_likelihood</code> pins are stale by ~1.24e-4 and fail the smoke…</a> |
 | 2026-08-09 | found | <a href="planned.md#isothermal-ell-sph-oversampling-at-the-cusp">isothermal-ell-sph-oversampling-at-the-cusp</a> |
 | 2026-08-08 | parked | <a href="parked.md#pyautoreduce-slacs1430-acs-comparison">pyautoreduce-slacs1430-acs-comparison</a> |
@@ -1235,12 +1226,12 @@ The 50 newest things to happen to the work in hand, newest first — issued, par
 | 2026-08-06 | filed | <a href="draft/docs/autocti/api_rst_rewrite.md">Rewrite PyAutoCTI docs/api — 55 of 89 autosummary entries are dead</a> |
 | 2026-08-06 | filed | <a href="draft/maintenance/libraries/dep_cap_refresh_2026_08.md">Dependency-cap refresh 2026-08: safe bumps, astropy 8 decision, two…</a> |
 | 2026-08-05 | filed | <a href="draft/feature/autofit/search_seed_reproducibility.md">Give PyAutoFit searches a <code>seed</code> — today no search can be made…</a> |
+| 2026-08-04 | filed | <a href="draft/maintenance/autolens_profiling/jwst_lw_untracked_gitignore_gap.md">dataset/imaging/jwst_lw is untracked because the gitignore was never…</a> |
 
 <details><summary>… 10 more (10 left)</summary>
 
 | Date | Event | Task |
 |------|-------|------|
-| 2026-08-04 | filed | <a href="draft/maintenance/autolens_profiling/jwst_lw_untracked_gitignore_gap.md">dataset/imaging/jwst_lw is untracked because the gitignore was never…</a> |
 | 2026-08-04 | filed | <a href="draft/maintenance/autolens_workspace/cosmos_web_ring_mask_dtype.md">cosmos_web_ring stores boolean masks as float64, wasting ~3.4 MB of…</a> |
 | 2026-08-04 | filed | <a href="draft/maintenance/autolens_workspace_developer/stale_api_rot_audit.md">autolens_workspace_developer: broad stale-API rot (56 symbols, no CI)</a> |
 | 2026-08-04 | filed | <a href="draft/triage/nightly_release_blocked_eight_nights.md">Nightly release has been blocked 8 nights running — triage the streak</a> |
@@ -1250,6 +1241,7 @@ The 50 newest things to happen to the work in hand, newest first — issued, par
 | 2026-07-31 | filed | <a href="draft/research/autolens/quick_update_plotting_cost.md">Quick-update plotting cost — minutes per update, and it is not JAX…</a> |
 | 2026-07-31 | filed | <a href="draft/research/autolens_profiling/cluster_gradient_search_benchmark.md">Cluster-scale gradient-search benchmark (Prodigy vs Nautilus…</a> |
 | 2026-07-30 | filed | <a href="draft/docs/workspaces/plot_coverage_followups.md">plot coverage — follow-ups deferred from plot-coverage-gaps</a> |
+| 2026-07-30 | filed | <a href="draft/bug/pyautohands/generate_rejects_autocti_after_deleting_notebooks.md"><code>generate.py</code> deletes notebooks/ before rejecting an unknown project</a> |
 
 </details>
 
diff --git a/draft/bug/autolens/jax_likelihood_smoke_pins_stale.md b/draft/bug/autolens/jax_likelihood_smoke_pins_stale.md
deleted file mode 100644
index a4b4cd83..00000000
--- a/draft/bug/autolens/jax_likelihood_smoke_pins_stale.md
+++ /dev/null
@@ -1,34 +0,0 @@
-# autolens_workspace_test jax_likelihood pins: 4 scripts fail smoke on main
-
-Type: bug
-Target: autolens
-Repos:
-- @PyAutoLens
-Difficulty: low
-Autonomy: supervised
-Priority: normal
-Status: draft
-Filed: 2026-08-19 (backfilled from git)
-
-## Finding (2026-08-19, control-tested during lazy-heavy-imports #1505)
-
-`pyauto-heart smoke autolens_test` fails 4/24 on canonical main (verified twice,
-worktree and canonical identical):
-
-- `imaging/jax_likelihood/lp.py` — vmap result is ~half the hardcoded pin
-  `-1.34797827e09`. This is the positions-LH penalty-doubling: the unmerged fix
-  `fb1aefe0b` ("sum PositionsLH penalties instead of doubling the last entry")
-  sits in the orphan worktree `~/Code/PyAutoLabs-wt/positions-lh-penalty-accumulation`
-  (PyAutoLens). The pin was calibrated against the doubling behaviour — landing
-  that fix and re-pinning must happen together.
-- `interferometer/jax_likelihood/rectangular.py` — misses pin `-3164.286252` by
-  0.0124% vs rtol 1e-4 (stale-pin drift).
-- `interferometer/jax_likelihood/mge.py`, `multi_dataset/jax_likelihood/mge.py` —
-  same stale-pin family.
-
-## Task
-
-Adjudicate the orphan positions-LH worktree (land or discard `fb1aefe0b`), then
-recalibrate the four scripts' hardcoded pins against current main and widen
-tolerances where the value is legitimately environment-sensitive. Every
-workspace_test smoke sweep reads 20/24 until this lands.