MaxGhenis · Oct 27, 2026 · Oct 25, 2026 · Oct 25, 2026 · Oct 25, 2026 · Oct 25, 2026
diff --git a/.github/workflows/python.yml b/.github/workflows/python.yml
@@ -25,7 +25,8 @@ jobs:
           python-version: "3.13"
           activate-environment: true
       - name: Install
-        # #715 candidate UK 2.147.2/core 3.33.3; released certification pending. Retained
+        # d2011's UK 2.151.0/core 3.33.3 and the carrier the lock pins (policyengine.py 6.11.1,
+        # the pair's release; tests require provenance to certify the filled pair). Retained
         # historical pilot receipts keep their original model/data labels;
         # no test needs the private Enhanced FRS file.
         run: |

diff --git a/README.md b/README.md
@@ -12,7 +12,7 @@ This is a **provisional, model-conditional** release ahead of the 28 October 202
 
 Headline, 2039-40 (Enhanced FRS, cash terms, UK): a **provisional, model-conditional expected saving of £11.1bn gross and £7.9bn net of tax and benefits**, the probability-weighted average over 50,000 simulated paths of prices and earnings centred on the OBR's forecast, estimated from 160 full runs (Monte Carlo error about ±£0.1bn).
 
-**Data.** The published figures use the certified bundle, **policyengine.py 6.2.6** (policyengine-uk 2.125.1, policyengine-core 3.33.0) with **Enhanced FRS 1.58.0**. The same 40 paths are also run on **Microcosm's UK release** (`microcosm_uk_2024_25`, tag `microcosm-uk-2024-25-national-20261002T230158Z-5c6b3f68`, uncertified under this bundle) as a paired cross-check: Microcosm minus Enhanced FRS is +£1.12bn gross and +£0.49bn net in 2039-40. The cross-check is in `data/results.json` but not on the dashboard. This is the historical pre-Budget bundle. The binding rebuild will use the **pending d1727 release**, certifying policyengine-uk main around 26 October and **Enhanced FRS 1.58.2**, with separate model and data bridge steps before coverage and the fiscal run; see [REBUILD.md](docs/REBUILD.md).
+**Data.** The published figures use the certified bundle, **policyengine.py 6.2.6** (policyengine-uk 2.125.1, policyengine-core 3.33.0) with **Enhanced FRS 1.58.0**. The same 40 paths are also run on **Microcosm's UK release** (`microcosm_uk_2024_25`, tag `microcosm-uk-2024-25-national-20261002T230158Z-5c6b3f68`, uncertified under this bundle) as a paired cross-check: Microcosm minus Enhanced FRS is +£1.12bn gross and +£0.49bn net in 2039-40. The cross-check is in `data/results.json` but not on the dashboard. This is the historical pre-Budget bundle. The binding rebuild will use d2011's pair, released in **policyengine.py 6.11.1** (policyengine-uk 2.151.0, policyengine-core 3.33.3): Microcosm's national cut `microcosm-uk-2024-25-national-20261025T091414Z-a6299504` as primary, with its local-area cut for constituency and local-authority runs, and **Enhanced FRS 1.58.2** as the paired sensitivity. Separate model and data bridge steps run before coverage and the fiscal run; see [REBUILD.md](docs/REBUILD.md).
 
 ## What the dashboard shows
 

diff --git a/data/binding-bridge.json b/data/binding-bridge.json
@@ -0,0 +1,67 @@
+{
+  "schema_version": 1,
+  "status": "ready",
+  "decision": "d2011 = A, Max 2026-10-25: the certified 2.151.0 Microcosm UK Budget pair (microcosm#1396) replaces #715's a133f37a pair; d1983 = B, Max 2026-10-24, put the binding primary on Microcosm",
+  "baseline_receipt": {
+    "path": "data/pilot/J-bridge-certified.json",
+    "sha256": "f5f42f5a6e20eb251dd26a283b840fdb825843e8edc9078c02fea78f14b6ac2f"
+  },
+  "steps": {
+    "model": {
+      "from": {
+        "packages": {
+          "policyengine": "6.2.6",
+          "policyengine-uk": "2.125.1",
+          "policyengine-core": "3.33.0"
+        },
+        "dataset": {
+          "name": "enhanced_frs_2024_25@1.58.0",
+          "sha256": "5ba399ea5ab9a6c7d4e9aaf6c623080beb34d9ad5f330f6244dbad72b8d960b6"
+        }
+      },
+      "to": {
+        "packages": {
+          "policyengine": "6.11.1",
+          "policyengine-uk": "2.151.0",
+          "policyengine-core": "3.33.3"
+        },
+        "dataset": {
+          "name": "enhanced_frs_2024_25@1.58.0",
+          "sha256": "5ba399ea5ab9a6c7d4e9aaf6c623080beb34d9ad5f330f6244dbad72b8d960b6"
+        }
+      }
+    },
+    "data": {
+      "from": {
+        "packages": {
+          "policyengine": "6.11.1",
+          "policyengine-uk": "2.151.0",
+          "policyengine-core": "3.33.3"
+        },
+        "dataset": {
+          "name": "enhanced_frs_2024_25@1.58.0",
+          "sha256": "5ba399ea5ab9a6c7d4e9aaf6c623080beb34d9ad5f330f6244dbad72b8d960b6"
+        }
+      },
+      "to": {
+        "packages": {
+          "policyengine": "6.11.1",
+          "policyengine-uk": "2.151.0",
+          "policyengine-core": "3.33.3"
+        },
+        "dataset": {
+          "name": "microcosm_uk_2024_25@a6299504",
+          "sha256": "b96a8cd625b645a409c063b1de5158532708a2f0d3c3897a794a8fb0bbd5064e"
+        }
+      }
+    }
+  },
+  "pending_release": {
+    "pull_request": "https://github.com/PolicyEngine/policyengine.py/pull/720",
+    "reviewed_head": "99a3e48b405e513a98850c64ee3564f0ca8e7553",
+    "bundle_manifest_path": "src/policyengine/data/bundle/manifest.json",
+    "policyengine_version": "6.11.1",
+    "bundle_manifest_sha256": "ab60903b390e7a765ea6558ec5e2d8fa5aede06b6f735fbf4e4c96109ffd1617",
+    "gate": "d2011 = A: the 2.151.0 national (microcosm#1396, a6299504) and its local-area cut certified together; fallback to #715's a133f37a pair with policyengine.py #699's area routing if not certified by 2026-10-27T18:00Z"
+  }
+}
diff --git a/data/binding-bridge.pending.json b/data/binding-bridge.pending.json
@@ -1,7 +1,7 @@
 {
   "schema_version": 1,
   "status": "pending",
-  "decision": "d1983 = B, Max 2026-10-24; certified policyengine.py #715 Microcosm UK Budget pair supersedes d1727 qualification-ledger primary",
+  "decision": "d2011 = A, Max 2026-10-25: the certified 2.151.0 Microcosm UK Budget pair (microcosm#1396) replaces #715's a133f37a pair; d1983 = B, Max 2026-10-24, put the binding primary on Microcosm",
   "baseline_receipt": {
     "path": "data/pilot/J-bridge-certified.json",
     "sha256": "f5f42f5a6e20eb251dd26a283b840fdb825843e8edc9078c02fea78f14b6ac2f"
@@ -22,7 +22,7 @@
       "to": {
         "packages": {
           "policyengine": null,
-          "policyengine-uk": "2.147.2",
+          "policyengine-uk": "2.151.0",
           "policyengine-core": "3.33.3"
         },
         "dataset": {
@@ -35,7 +35,7 @@
       "from": {
         "packages": {
           "policyengine": null,
-          "policyengine-uk": "2.147.2",
+          "policyengine-uk": "2.151.0",
           "policyengine-core": "3.33.3"
         },
         "dataset": {
@@ -46,22 +46,22 @@
       "to": {
         "packages": {
           "policyengine": null,
-          "policyengine-uk": "2.147.2",
+          "policyengine-uk": "2.151.0",
           "policyengine-core": "3.33.3"
         },
         "dataset": {
-          "name": "microcosm_uk_2024_25@a133f37a",
-          "sha256": "64f83900ca3a1242fb017585234844ce89f743d32e41cd2b6558057777f914aa"
+          "name": "microcosm_uk_2024_25@a6299504",
+          "sha256": "b96a8cd625b645a409c063b1de5158532708a2f0d3c3897a794a8fb0bbd5064e"
         }
       }
     }
   },
   "pending_release": {
-    "pull_request": "https://github.com/PolicyEngine/policyengine.py/pull/715",
-    "reviewed_head": "e02d41bceab57756373b2dc3bcf78635b856ec81",
+    "pull_request": null,
+    "reviewed_head": null,
     "bundle_manifest_path": "src/policyengine/data/bundle/manifest.json",
     "policyengine_version": null,
     "bundle_manifest_sha256": null,
-    "gate": "draft stacked on #704; attribution 2026-10-24T22:00Z to 2026-10-25T10:00Z, then review and release"
+    "gate": "d2011 = A: the 2.151.0 national (microcosm#1396, a6299504) and its local-area cut certified together; fallback to #715's a133f37a pair with policyengine.py #699's area routing if not certified by 2026-10-27T18:00Z"
   }
 }
diff --git a/docs/CALIBRATION_ANCHOR.md b/docs/CALIBRATION_ANCHOR.md
@@ -1,6 +1,6 @@
 # Calibration anchor and certified-input bridge
 
-> **Integration (part D).** The anchor is now part of each dataset's registry entry (`datasets.ageing_anchor`: 2025 for Enhanced FRS 1.56.16 and 1.57.4, read from `frs_release.py` at each tag; Microcosm has no published calibration year, so its anchor is 2024, the first year the ONS projection covers). *Superseded for Microcosm: every registered cut's targets are dated 2025, so each anchors at 2025 (5c6b3f68 since 95732e2). Builds from microcosm#1095 on, such as a133f37a, also write the solved weights at the data year divided by the model's own projection, so their 2025 weights are exactly the solved ones; 5c6b3f68's are the solved ones times 1.0072 ([METHOD.md](METHOD.md)).* The rake keeps the dataset's own weights in the anchor year and every year before it (`demography.annual_weights`). The level difference described below, runtime 2025 weights = calibrated weights × 1.0072 × 1.027 / 1.039 = 0.9956, is reported upstream as policyengine-uk-data#538. Re-checked on policyengine-uk 2.120.0: every 2025 weight is its 2024 weight × 1.0072.
+> **Integration (part D).** The anchor is now part of each dataset's registry entry (`datasets.ageing_anchor`: 2025 for Enhanced FRS 1.56.16 and 1.57.4, read from `frs_release.py` at each tag; Microcosm has no published calibration year, so its anchor is 2024, the first year the ONS projection covers). *Superseded for Microcosm: every registered cut's targets are dated 2025, so each anchors at 2025 (5c6b3f68 since 95732e2). Builds from microcosm#1095 on (a133f37a, and d2011's a6299504 at microcosm#1396) also write the solved weights at the data year divided by the model's own projection, so their 2025 weights are exactly the solved ones; 5c6b3f68's are the solved ones times 1.0072 ([METHOD.md](METHOD.md)).* The rake keeps the dataset's own weights in the anchor year and every year before it (`demography.annual_weights`). The level difference described below, runtime 2025 weights = calibrated weights × 1.0072 × 1.027 / 1.039 = 0.9956, is reported upstream as policyengine-uk-data#538. Re-checked on policyengine-uk 2.120.0: every 2025 weight is its 2024 weight × 1.0072.
 
 The pilot uses **2025**, the calibration year configured in the exact source release for its certified Enhanced FRS. It anchors to the runtime's native 2025 weights. Those weights do not restore the builder's original calibrated weights, so preserved Housing Benefit and Pension Credit calibration remains an acceptance gate.