B5c-2a: correlated_nd_pilot complete (judged under @1, @2 frozen); campaign next -> B5c-2b

campaigns.yaml

@@ -93,10 +93,11 @@ campaigns:
   title: PyAutoFit search benchmark on gaussian_x3 (autofit_inference)
   status: running
   updated: '2026-10-16'
-  next: 'B5c-2: RAL 410866 (the correlated_nd pilot, 930 runs, from the private copy inference/autofit_inference_b5c)
-    finished 2026-10-16 with 926/930 completed and 4 OUT_OF_MEMORY at 8 G; pull results/ only, settle the 4 OOM
-    cells (more memory or excluded), judge under correlated_nd@1, freeze correlated_nd@2 from the pilot and submit its scored wave; the family is
-    catalogued apart from gaussian_x3 and ranks nothing across families.'
+  next: 'B5c-2b (draft/research/autofit_inference/search_ext_b5c2b_scored_wave_submit.md): realisations 2-3 and
+    their exact references, the correlated_nd@2 scored-wave manifest (83 cells x 50 seeds x 3 realisations,
+    12 450 runs) and its probe for 8 probe-first cells, then the submit on RAL --partition=ral from a private
+    pinned copy with the A2 memory requests; correlated_nd@2 is frozen (autofit_inference 44c5e77f1fb0); the
+    family is catalogued apart from gaussian_x3 and ranks nothing across families.'
   recent_progress: Wave 2 closed (B5b-2, 2026-10-15, autofit_inference#12) — RAL 409930 pulled, 12,750 rows
     admitted at the pin df6d218f10cd with 0 missing; NSS 50-step leads both evidence rankings; the catalogue
     ranks only legs with success rate >= 50 % over >= 20 attempts (post-hoc presentation convention); fit
@@ -180,14 +181,14 @@ tasks:
 - id: correlated_nd_pilot
   campaign: gaussian-x3-search-benchmark
   title: correlated_nd search benchmark — the pilot (wave 1, second model family)
-  status: running
+  status: complete
   priority: normal
   path: tasks/correlated_nd_pilot.md
   updated: '2026-10-16'
-  next: RAL 410866, the 930-run correlated_nd@1 pilot (protocol first committed 9ec37795f404, A1 before any
-    row), finished 2026-10-16 (926/930 completed, 4 OUT_OF_MEMORY at 8 G, results unpulled); B5c-2 pulls it,
-    settles the 4 OOM cells, judges it and freezes correlated_nd@2.
-  evidence: https://github.com/PyAutoLabs/autofit_inference/issues/14
+  next: Done (B5c-2a, autofit_inference#17) — pilot judged under correlated_nd@1 (1040 expected = 749 rows +
+    177 failed + 4 oom + 0 missing + 110 deferred; 307 accepted); correlated_nd@2 frozen in 44c5e77f1fb0 from
+    results/calibration/correlated_nd_wave1.json; the scored wave is B5c-2b.
+  evidence: https://github.com/PyAutoLabs/autofit_inference/issues/17
 - id: gaussian_x3_search_wave2
   campaign: gaussian-x3-search-benchmark
   title: gaussian_x3 search benchmark — wave 2 (scored)

dashboard.md

@@ -1,6 +1,6 @@
 # PyAutoInsight — inference control room
 
-<!-- insight-inputs:004fbffeb895e547f2c938b514aa10c7f79e8b20dc7b32f18ab17eb3e64d8c88 -->
+<!-- insight-inputs:25cabeb3e20fa27f0eceeaf73870e49f1bc78c35b6ed5f15573959f0075a6bec -->
 
 | Where | Count |
 |---|---:|
@@ -10,7 +10,7 @@
 | [Cached](#evidence) | 0 |
 | [Failed](#evidence) | 0 |
 
-<!-- insight-campaigns:c09fff24924c3c8bc5e2bfb0e9e37109d0202153cc34c91f3b9ee6281893322a -->
+<!-- insight-campaigns:be44ab685722080abcb342d8094de6ec3457b9c959757f7ba2962ef1304dc2ee -->
 ## Check in on all inference work
 
 Copy this into one chat. Add a campaign focus or idea before or after it, or leave it unchanged.
@@ -46,7 +46,7 @@ After taking action, report what changed, what the evidence supports and what re
 | [N=50 NUTS versus three EP repeats](https://github.com/PyAutoLabs/PyAutoCortex/blob/d45f198804615c090e6b6694cf725ddb0be2354e/projects/ep_toy_gaussian.md) | Cortex records failed wave 1 (EMFILE/OOM), wave-2 preparation and no submission. | Present the existing wave-2 proposal with current dependency evidence for decision. |
 | [Hierarchical slope recovery at scale](https://github.com/PyAutoLabs/PyAutoCortex/blob/d45f198804615c090e6b6694cf725ddb0be2354e/projects/slope_hierarchy_scale.md) | Cortex retains graphical baseline, post-processing OOM and stale EP hierarchical factor; Mind records later moments fix. | Verify the moments fix release and project mirror; recover missing summaries from existing samples before a proposed rerun. |
 | [IC50 EP and graphical scale ladder](https://github.com/PyAutoLabs/PyAutoCortex/blob/d45f198804615c090e6b6694cf725ddb0be2354e/projects/ic50_workspace.md) | Cortex records N=5/10/25 results, failed N=50 EP rung and width-interpretation caveat. | Check implementation close-outs, then propose a seeded ladder with appropriate output and mean-field diagnostics. |
-| [PyAutoFit search benchmark on gaussian_x3 (autofit_inference)](https://github.com/PyAutoLabs/autofit_inference/issues/12) | Wave 2 closed (B5b-2, 2026-10-15, autofit_inference#12) — RAL 409930 pulled, 12,750 rows admitted at the pin df6d218f10cd with 0 missing; NSS 50-step leads both evidence rankings; the catalogue ranks only legs with success rate &gt;= 50 % over &gt;= 20 attempts (post-hoc presentation convention); fit records published as inference-summary@3 (101 record shards). | B5c-2: RAL 410866 (the correlated_nd pilot, 930 runs, from the private copy inference/autofit_inference_b5c) finished 2026-10-16 with 926/930 completed and 4 OUT_OF_MEMORY at 8 G; pull results/ only, settle the 4 OOM cells (more memory or excluded), judge under correlated_nd@1, freeze correlated_nd@2 from the pilot and submit its scored wave; the family is catalogued apart from gaussian_x3 and ranks nothing across families. |
+| [PyAutoFit search benchmark on gaussian_x3 (autofit_inference)](https://github.com/PyAutoLabs/autofit_inference/issues/12) | Wave 2 closed (B5b-2, 2026-10-15, autofit_inference#12) — RAL 409930 pulled, 12,750 rows admitted at the pin df6d218f10cd with 0 missing; NSS 50-step leads both evidence rankings; the catalogue ranks only legs with success rate &gt;= 50 % over &gt;= 20 attempts (post-hoc presentation convention); fit records published as inference-summary@3 (101 record shards). | B5c-2b (draft/research/autofit_inference/search_ext_b5c2b_scored_wave_submit.md): realisations 2-3 and their exact references, the correlated_nd@2 scored-wave manifest (83 cells x 50 seeds x 3 realisations, 12 450 runs) and its probe for 8 probe-first cells, then the submit on RAL --partition=ral from a private pinned copy with the A2 memory requests; correlated_nd@2 is frozen (autofit_inference 44c5e77f1fb0); the family is catalogued apart from gaussian_x3 and ranks nothing across families. |
 
 ## Active tasks
 
@@ -58,7 +58,6 @@ After taking action, report what changed, what the evidence supports and what re
 | [Graphical Model Scale-Up — Scoping](https://github.com/PyAutoLabs/PyAutoInsight/blob/main/tasks/graphical_scoping.md) | graphical-ep | needs-slicing | high | Reconcile current Cortex scale results and library dependencies; select one bounded inference phase with a witness. |
 | [NUTS/HMC trial on validated likelihoods](https://github.com/PyAutoLabs/PyAutoInsight/blob/main/tasks/gradient_sampler_validated_likelihoods.md) | point-source-admission | needs-decision | normal | An unscoped idea, not permission to submit: reconcile point-source admission with imaging and weak-lensing candidate targets. |
 | [gaussian_x3 search benchmark — wave 1 (the pilot)](https://github.com/PyAutoLabs/PyAutoInsight/blob/main/tasks/gaussian_x3_search_wave1.md) | gaussian-x3-search-benchmark | blocked | normal | Pilot stopped at 223 of 520 runs and is not restarted; freeze gaussian_x3@2 from its 17-row calibration before any scored run; the deferred cells move to scored wave 2 (after A2 and A4). |
-| [correlated_nd search benchmark — the pilot (wave 1, second model family)](https://github.com/PyAutoLabs/PyAutoInsight/blob/main/tasks/correlated_nd_pilot.md) | gaussian-x3-search-benchmark | running | normal | RAL 410866, the 930-run correlated_nd@1 pilot (protocol first committed 9ec37795f404, A1 before any row), finished 2026-10-16 (926/930 completed, 4 OUT_OF_MEMORY at 8 G, results unpulled); B5c-2 pulls it, settles the 4 OOM cells, judges it and freezes correlated_nd@2. |
 | [gaussian_x3 search benchmark — wave 2 (scored)](https://github.com/PyAutoLabs/PyAutoInsight/blob/main/tasks/gaussian_x3_search_wave2.md) | gaussian-x3-search-benchmark | running | high | Wave 2 is closed and judged (B5b-2); the fit snapshot is captured from main under inference-summary@3 after the B5b-2 PRs merge. |
 
 [Ledger](https://github.com/PyAutoLabs/PyAutoInsight/blob/main/campaigns.yaml)

tasks/correlated_nd_pilot.md

@@ -66,13 +66,42 @@ Every dataset × backend has an exact reference, complete in `results/reference/
 - The first submission, 409957, failed at import in every task: the shared RAL clone had
   been switched by another session. It was cancelled and wrote no row.
 
-This task authorises nothing further. Pulling, judging and the `correlated_nd@2` freeze
-are B5c-2.
-
-## Next (B5c-2)
-
-1. Pull the pilot's rows (`results/` only) and judge them under `correlated_nd@1`; settle
-   the 4 OOM cells (more memory or excluded).
-2. Calibrate the PLACEHOLDERs and timeouts, then freeze `correlated_nd@2` before any
-   scored row.
-3. Submit the scored wave: 50 seeds × realisations 1–3 × every non-deferred cell.
+## Judged and closed (2026-10-16, B5c-2a, autofit_inference#17)
+
+**Status: complete.** `results/` of 410866 was pulled from the private copy (930 rows; the
+8 exact references there are byte-identical to the committed ones) and judged under
+`correlated_nd@1` (`results/accounting/correlated_nd_pilot.json`, reconciled with the
+committed `sacct` extract):
+
+- **1040 expected = 749 completed rows + 177 failed + 4 `oom` + 0 missing + 110 deferred**;
+  930 admitted, 0 refused.
+- Under `@1`: **307 accepted, 623 rejected**. The pilot ranks nothing.
+- `oom` is a new attempt class. The submit had written cap stubs for the 4 OUT_OF_MEMORY
+  tasks, because SLURM's OOM SIGKILL exits 137 under `timeout`. They were rewritten from
+  sacct, with MaxRSS 7.6 / 7.7 / 3.1 / 8.4 G at the 8 G request.
+- The failures:
+  - 80 Emcee/Zeus rows (d20, banana) crashed in the harness's chain diagnostics after the
+    search. That bug is fixed.
+  - 60 d100 Nautilus rows, which fail at the pin.
+  - 10 d100 warm NUTS rows.
+  - 27 rows stopped at the 4 h cap (d50 Nautilus `n_live_100`, d50 warm NUTS).
+
+**Calibration and freeze.** The calibration is
+[`results/calibration/correlated_nd_wave1.json`](https://github.com/PyAutoLabs/autofit_inference/blob/main/results/calibration/correlated_nd_wave1.json).
+`correlated_nd@2` (protocol §11 A2) was frozen in autofit_inference `44c5e77f1fb0` before any
+scored row:
+- σ-ratio bands are per task. The evidence band is [0.85, 1.1] (79 rows). The posterior
+  band is kept at [0.5, 2.0] (1 row, < 20).
+- The ESS and R-hat bars are kept.
+- 75 timed cells and 8 probe-first cells.
+- 21 cells are deferred, each with its reason. They include the OOM cells d50 Nautilus
+  `n_live_100` and d50 warm NUTS (by the cap rule) and every d100 Nautilus cell.
+- Memory is `max(8 G, ceil(2 × the pilot peak))`: 16 G for d50 Nautilus `n_live_400`,
+  17 G for d100 cold NUTS.
+
+## Next
+
+B5c-2b (`draft/research/autofit_inference/search_ext_b5c2b_scored_wave_submit.md`):
+realisations 2–3 and their exact references, then the scored-wave manifest (83 cells × 50
+seeds × 3 realisations = 12 450 runs) and its probe, then the submit. Nothing is submitted
+by this task.