docs(notebooks): disclose 32B uncertain-adjudication pass in palliative PRISMA methods (refs #653, #655)

The 116 stage-2 uncertains (+2 no-tool-call stragglers) were re-screened
independently by qwen2.5:32b on the rig 4090 with first-pass rationales
withheld: 19 include / 6 exclude / 91 confirmed uncertain (stage-3
material). Final corpus: 4,997/4,999 screened — 2,264 inc / 2,642 exc /
91 unc. 14B rationale archive kept in session scratchpad.

notebooks/palliative_care_rfi.py

@@ -152,8 +152,11 @@ def _(mo):
     tags**, so it always reflects current screening progress.
 
     > **Methods disclosures:** single-reviewer LLM screening (no human
-    > dual-screening yet); stage-3 full-text eligibility and data
-    > extraction have not run; grey literature (standards documents,
+    > dual-screening yet); records the 14B screener marked `uncertain`
+    > were adjudicated in a second pass by a larger model
+    > (qwen2.5:32b) with the first-pass rationale withheld for
+    > independence; stage-3 full-text eligibility and data extraction
+    > have not run; grey literature (standards documents,
     > OIG/GAO/MedPAC/CMMI) bypasses clinical screening per the
     > project criteria.
     """)