PolicyEngine · MaxGhenis · Sep 4, 2026 · Sep 4, 2026
diff --git a/docs/progress.md b/docs/progress.md
@@ -2,7 +2,7 @@
 
 # Development progress
 
-*Snapshot as of 2026-09-04T12:20:00Z (UTC); updated at least daily while the evidence campaign is active. The data behind this page is committed at [`docs/progress/progress.json`](progress/progress.json).*
+*Snapshot as of 2026-09-04T18:30:00Z (UTC); updated at least daily while the evidence campaign is active. The data behind this page is committed at [`docs/progress/progress.json`](progress/progress.json).*
 
 Dynamics builds Social Security earnings histories from the PSID, and the corrected covered-earnings series is only as credible as the reading of the source documentation beneath it. Before that series ships, every piece of documentation the construction relies on is independently verified by the three arms below; the design is pre-registered and ratifies only when they complete. (Internally: the evidence campaign behind Amendment 20 (two-arm evidence charter for the covered-earnings correction design), under review in PR #405, open; draft ratified through round 6.2; next step, the A4 evidence freeze, then the C20 ratification chain toward revision 22.)
 
@@ -27,14 +27,14 @@ The foundations below are complete and in the repository today; the campaign tra
               align-items: baseline;">
     <strong>Prompt-purpose census</strong>
     <span style="font-variant-numeric: tabular-nums;">
-      17,888 / 20,815 &middot; 85.9%</span>
+      18,838 / 20,815 &middot; 90.5%</span>
   </div>
   <div style="background: #e9ecef; border-radius: 6px; height: 14px;
               margin: 0.35em 0;">
     <div style="background: #2c6496; border-radius: 6px; height: 14px;
-                width: 85.9%;"></div>
+                width: 90.5%;"></div>
   </div>
-  <div style="font-size: 0.9em; color: #555;">prompts adopted (contiguous R1–R17888).
+  <div style="font-size: 0.9em; color: #555;">prompts adopted (contiguous R1–R18838).
   Establishing what each of the ~21,000 remaining items in the PSID's 1968–2023 questionnaires and codebooks is actually asking, so the model only uses variables whose meaning has been adjudicated rather than assumed. Each block runs a full pass, an independent dense audit, and a correction sweep before its entries are adopted into the governing ledger.</div>
 </div>
 
@@ -61,12 +61,12 @@ The foundations below are complete and in the repository today; the campaign tra
               align-items: baseline;">
     <strong>Q5 semantic annotation</strong>
     <span style="font-variant-numeric: tabular-nums;">
-      48 / 257 &middot; 18.7%</span>
+      54 / 257 &middot; 21.0%</span>
   </div>
   <div style="background: #e9ecef; border-radius: 6px; height: 14px;
               margin: 0.35em 0;">
     <div style="background: #2c6496; border-radius: 6px; height: 14px;
-                width: 18.7%;"></div>
+                width: 21.0%;"></div>
   </div>
   <div style="font-size: 0.9em; color: #555;">documents sealed.
   Verifying which survey questions connect to which data fields, document by document across the PSID questionnaire corpus: two independent annotators per document, then a reconciliation that seals its table of record.</div>
@@ -126,9 +126,9 @@ The three drill-down tables below decompose each arm's progress bar row by row.
 | q2009 G/R/P/KL (E5 block 6) | R17,023–R17,308 | 286 | adopted | 233 D / 53 SU | 97.32% sample / 98.60% full NOT CALIBRATED on family concentration; 4-row manifest adopted; folded v1.81 | 2026-09-02 |
 | fam2011 + q2011 BC/DE (E5 block 7) | R17,309–R17,585 | 277 | adopted | 230 D / 47 SU (corrected) | 77.97% strict sample NOT CALIBRATED (q2011 whole-roster EHC routing family) -> regeneration sweep-r2, 277/277; folded v1.83 | 2026-09-03 |
 | q2011 F/G/R/P/KL (E5 block 8; the tranche's last block) | R17,586–R17,888 | 303 | adopted | APPLY 226 / UNCOVERED 77 (corrected census) | 92.04% sample NOT CALIBRATED; closed 16-row manifest across six families adopted per the closed-manifest precedent; folded v1.84 — E5 tranche complete, contiguous R1–R17888 | 2026-09-03 |
-| fam2013 complete + q2013 BCDE/G (final-tranche block 1) | R17,889–R18,236 | 348 | in_cycle | — | pass 348/348 (225,291 B) -> dense audit NOT CALIBRATED on both limbs; closed 59-row manifest, seals must regenerate; folded v1.86; regeneration sweep in flight | — |
-| q2013 R/P/KL + fam2015 complete (final-tranche block 2) | R18,237–R18,526 | 290 | pending | — | — | — |
-| q2015 BCDE/G/R/P (final-tranche block 3) | R18,527–R18,838 | 312 | pending | — | — | — |
+| fam2013 complete + q2013 BCDE/G (final-tranche block 1) | R17,889–R18,236 | 348 | adopted | 348/348 regenerated (sweep) | pass 348/348 -> dense audit NOT CALIBRATED both limbs (59-row manifest, seals regenerate) -> regeneration sweep 348/348 byte-exact envelope; folded v1.87 | 2026-09-04 |
+| q2013 R/P/KL + fam2015 complete (final-tranche block 2) | R18,237–R18,526 | 290 | adopted | APPLY 217 / UNCOVERED 73 | pass recovered byte-exact from durable scratch -> dense audit CALIBRATED 99.37% sample / 99.66% full (one-row manifest R18462); folded v1.88 | 2026-09-04 |
+| q2015 BCDE/G/R/P (final-tranche block 3) | R18,527–R18,838 | 312 | adopted | — | pass 312/312 -> dense audit CALIBRATED 100% sample and full vector (empty contradiction set; 24/24 receipts byte-exact); folded v1.89 | 2026-09-04 |
 | q2015 KL + q2017 complete (final-tranche block 4) | R18,839–R19,111 | 273 | pending | — | — | — |
 | q2019 complete + q2021 A (final-tranche block 5) | R19,112–R19,384 | 273 | pending | — | — | — |
 | q2021 BC (final-tranche block 6) | R19,385–R19,749 | 365 | pending | — | — | — |
@@ -249,6 +249,12 @@ The three drill-down tables below decompose each arm's progress bar row by row.
 | 2001 family questionnaire QxQ companion (fam2001_QxQs.pdf) | 674 | RECALIBRATE (clean streak 0/2) | 2026-09-03 |
 | 2001 family questionnaire (q2001.pdf) | 2,825 | RECALIBRATE (neither lane canonical; resolved under the 1992q standard) | 2026-09-03 |
 | 2003 family questionnaire QxQ companion (fam2003_QxQs.pdf) | 370 | RECALIBRATE (230/370 occurrences diverged; all source-resolved) | 2026-09-03 |
+| 2003 family questionnaire (q2003.pdf) | 1,225 | RECALIBRATE (agreement 480/1,225; all divergences source-resolved) | 2026-09-04 |
+| 2005 family questionnaire QxQ companion (fam2005_QxQs.pdf) | 269 | lane A prevailing (174 of 194 divergences to A; common-mode 1/269) — first Opus/Opus pair | 2026-09-04 |
+| 2005 family questionnaire (q2005.pdf) | 1,212 | RECALIBRATE (neither lane canonical; common-mode 0/516) | 2026-09-04 |
+| 2007 family questionnaire QxQ companion (fam2007_QxQs.pdf) | 952 | RECONCILED — lane B prevails (917/952 as submitted; common-mode 7/389) | 2026-09-04 |
+| 2007 family questionnaire (q2007.pdf) | 1,605 | lane B adopted unmodified as the table of record (1,605/1,605) | 2026-09-04 |
+| 2009 family questionnaire QxQ companion (fam2009_QxQs.pdf) | 171 | both lanes rejected; the reconciled table stands (common-mode 5/171 = 2.9%, the highest yet) | 2026-09-04 |
 
 ## Development scorecard
 
@@ -305,7 +311,7 @@ From the pre-registered timeline ledger, entry 22 (registered 2026-09-03). Dates
 
 ## Recent milestones
 
-- **2026-09-04** — After an overnight capacity hold, final-tranche block 1 enters its regeneration sweep and the 2003q reconciliation resumes on the one available Codex lane; a fresh orchestrator session takes over the sequencing record.
+- **2026-09-04** — Final-tranche blocks 1–3 close (ledger v1.89; purpose reaches 90.50%): block 1 on its regeneration sweep, block 2 CALIBRATED at 99.66% on a one-row manifest, block 3 CALIBRATED at 100% with an empty contradiction set. Q5 seals 2003q, 2005f, 2005q, 2007f, 2007q and 2009f (54/257), the last five on Opus reconciliations; the first Opus/Opus pairs measure common-mode rates of 0.4%, 1.8%, 0.0% and 2.9%. The C20 ceremony-kit correction reaches its fifth round as a Sol-written change that an independent Opus review ACCEPTS, clearing the last precondition on the A4 evidence freeze other than the census itself. Six Claude accounts run Opus lanes in parallel after subfleet's false month-long parks are found and cleared.
 - **2026-09-03** — The E5 first tranche completes: block 8 closes on its audit's closed 16-row manifest (ledger v1.84; purpose reaches 85.94%). The final tranche R17889–R20815 is planned as the entire remainder — 2,927 ranks across eight documents from 2013 to 2023 in ten blocks (v1.85) — and its first block passes 348/348 and is audited (v1.86) with a 59-row regeneration manifest. Q5 seals 2001f, 2003f and 2001q (48/257), the latter two on Claude Opus reconciliations in 42–43 minutes against a one-to-three-hour Sol baseline.
 - **2026-09-03** — E5 blocks 6–7 close (ledger v1.83; purpose reaches 84.48%) and the tranche's last block, block 8 to R17888, is in flight. Q5 seals 1999f and 1999q — the latter the campaign's largest table of record at 8,498 rows — reaching 45/257. An output-order mandate (full serialization first, no placeholders) is adopted as standing process law for large deliverables after a truncated sweep had to be re-run.
 - **2026-09-02** — E5 blocks 3–5 close (block 3 CALIBRATED at 100% — the third perfect purpose block); purpose reaches 81.78%. Q5 seals 1997q after a dual-serialization cross-recovery repaired a damaged lane print without a re-run (43/257).

diff --git a/docs/progress/detail.json b/docs/progress/detail.json
@@ -516,35 +516,35 @@
         "rank_start": 17889,
         "rank_end": 18236,
         "ranks": 348,
-        "status": "in_cycle",
-        "dispositions": null,
-        "audit": "pass 348/348 (225,291 B) -> dense audit NOT CALIBRATED on both limbs; closed 59-row manifest, seals must regenerate; folded v1.86; regeneration sweep in flight",
-        "adopted_on": null,
-        "source": "sol-ce-purpose-audit-R17889-18236-report.md"
+        "status": "adopted",
+        "dispositions": "348/348 regenerated (sweep)",
+        "audit": "pass 348/348 -> dense audit NOT CALIBRATED both limbs (59-row manifest, seals regenerate) -> regeneration sweep 348/348 byte-exact envelope; folded v1.87",
+        "adopted_on": "2026-09-04",
+        "source": "sol-ce-purpose-correction-sweep-R17889-18236-report.md"
       },
       {
         "document": "q2013 R/P/KL + fam2015 complete (final-tranche block 2)",
         "era": "Final tranche (R17889–R20815: fam2013/q2013 through q2023; E5 through 2015, E6 from 2017)",
         "rank_start": 18237,
         "rank_end": 18526,
         "ranks": 290,
-        "status": "pending",
-        "dispositions": null,
-        "audit": null,
-        "adopted_on": null,
-        "source": "sol-ce-purpose-ledger-e5final-build-report.md"
+        "status": "adopted",
+        "dispositions": "APPLY 217 / UNCOVERED 73",
+        "audit": "pass recovered byte-exact from durable scratch -> dense audit CALIBRATED 99.37% sample / 99.66% full (one-row manifest R18462); folded v1.88",
+        "adopted_on": "2026-09-04",
+        "source": "sol-ce-purpose-audit-R18237-18526-report.md"
       },
       {
         "document": "q2015 BCDE/G/R/P (final-tranche block 3)",
         "era": "Final tranche (R17889–R20815: fam2013/q2013 through q2023; E5 through 2015, E6 from 2017)",
         "rank_start": 18527,
         "rank_end": 18838,
         "ranks": 312,
-        "status": "pending",
+        "status": "adopted",
         "dispositions": null,
-        "audit": null,
-        "adopted_on": null,
-        "source": "sol-ce-purpose-ledger-e5final-build-report.md"
+        "audit": "pass 312/312 -> dense audit CALIBRATED 100% sample and full vector (empty contradiction set; 24/24 receipts byte-exact); folded v1.89",
+        "adopted_on": "2026-09-04",
+        "source": "sol-ce-purpose-audit-R18527-18838-report.md"
       },
       {
         "document": "q2015 KL + q2017 complete (final-tranche block 4)",
@@ -1433,6 +1433,54 @@
         "verdict": "RECALIBRATE (230/370 occurrences diverged; all source-resolved)",
         "sealed_on": "2026-09-03",
         "source": "sol-ce-q5-doc-2003f-reconciled-report.md"
+      },
+      {
+        "doc": "document_065",
+        "label": "2003 family questionnaire (q2003.pdf)",
+        "rows_sealed": 1225,
+        "verdict": "RECALIBRATE (agreement 480/1,225; all divergences source-resolved)",
+        "sealed_on": "2026-09-04",
+        "source": "sol-ce-q5-doc-2003q-reconciled-report.md"
+      },
+      {
+        "doc": "document_066",
+        "label": "2005 family questionnaire QxQ companion (fam2005_QxQs.pdf)",
+        "rows_sealed": 269,
+        "verdict": "lane A prevailing (174 of 194 divergences to A; common-mode 1/269) — first Opus/Opus pair",
+        "sealed_on": "2026-09-04",
+        "source": "sol-ce-q5-doc-2005f-reconciled-report.md"
+      },
+      {
+        "doc": "document_067",
+        "label": "2005 family questionnaire (q2005.pdf)",
+        "rows_sealed": 1212,
+        "verdict": "RECALIBRATE (neither lane canonical; common-mode 0/516)",
+        "sealed_on": "2026-09-04",
+        "source": "sol-ce-q5-doc-2005q-reconciled-report.md"
+      },
+      {
+        "doc": "document_068",
+        "label": "2007 family questionnaire QxQ companion (fam2007_QxQs.pdf)",
+        "rows_sealed": 952,
+        "verdict": "RECONCILED — lane B prevails (917/952 as submitted; common-mode 7/389)",
+        "sealed_on": "2026-09-04",
+        "source": "sol-ce-q5-doc-2007f-reconciled-report.md"
+      },
+      {
+        "doc": "document_069",
+        "label": "2007 family questionnaire (q2007.pdf)",
+        "rows_sealed": 1605,
+        "verdict": "lane B adopted unmodified as the table of record (1,605/1,605)",
+        "sealed_on": "2026-09-04",
+        "source": "sol-ce-q5-doc-2007q-reconciled-report.md"
+      },
+      {
+        "doc": "document_070",
+        "label": "2009 family questionnaire QxQ companion (fam2009_QxQs.pdf)",
+        "rows_sealed": 171,
+        "verdict": "both lanes rejected; the reconciled table stands (common-mode 5/171 = 2.9%, the highest yet)",
+        "sealed_on": "2026-09-04",
+        "source": "sol-ce-q5-doc-2009f-reconciled-report.md"
       }
     ]
   }

diff --git a/docs/progress/progress.json b/docs/progress/progress.json
@@ -1,7 +1,7 @@
 {
   "schema_version": 1,
   "description": "Data behind docs/progress.md (the development-progress dashboard). Update this file and run `python scripts/build_progress_page.py`; never edit docs/progress.md by hand.",
-  "as_of": "2026-09-04T12:20:00Z",
+  "as_of": "2026-09-04T18:30:00Z",
   "framework": {
     "amendment": "Amendment 20 (two-arm evidence charter for the covered-earnings correction design)",
     "pr": 405,
@@ -47,9 +47,9 @@
       "key": "purpose",
       "label": "Prompt-purpose census",
       "description": "Establishing what each of the ~21,000 remaining items in the PSID's 1968–2023 questionnaires and codebooks is actually asking, so the model only uses variables whose meaning has been adjudicated rather than assumed. Each block runs a full pass, an independent dense audit, and a correction sweep before its entries are adopted into the governing ledger.",
-      "done": 17888,
+      "done": 18838,
       "total": 20815,
-      "unit": "prompts adopted (contiguous R1–R17888)"
+      "unit": "prompts adopted (contiguous R1–R18838)"
     },
     {
       "key": "a3",
@@ -63,7 +63,7 @@
       "key": "q5",
       "label": "Q5 semantic annotation",
       "description": "Verifying which survey questions connect to which data fields, document by document across the PSID questionnaire corpus: two independent annotators per document, then a reconciliation that seals its table of record.",
-      "done": 48,
+      "done": 54,
       "total": 257,
       "unit": "documents sealed"
     }
@@ -89,7 +89,7 @@
   "milestones": [
     {
       "date": "2026-09-04",
-      "text": "After an overnight capacity hold, final-tranche block 1 enters its regeneration sweep and the 2003q reconciliation resumes on the one available Codex lane; a fresh orchestrator session takes over the sequencing record."
+      "text": "Final-tranche blocks 1–3 close (ledger v1.89; purpose reaches 90.50%): block 1 on its regeneration sweep, block 2 CALIBRATED at 99.66% on a one-row manifest, block 3 CALIBRATED at 100% with an empty contradiction set. Q5 seals 2003q, 2005f, 2005q, 2007f, 2007q and 2009f (54/257), the last five on Opus reconciliations; the first Opus/Opus pairs measure common-mode rates of 0.4%, 1.8%, 0.0% and 2.9%. The C20 ceremony-kit correction reaches its fifth round as a Sol-written change that an independent Opus review ACCEPTS, clearing the last precondition on the A4 evidence freeze other than the census itself. Six Claude accounts run Opus lanes in parallel after subfleet's false month-long parks are found and cleared."
     },
     {
       "date": "2026-09-03",