diff --git a/.custodian-brief.md b/.custodian-brief.md
index 216babd..2784301 100644
--- a/.custodian-brief.md
+++ b/.custodian-brief.md
@@ -2,16 +2,15 @@
 # Custodian Brief — assembly-economics
 
 **Domain:** communication  
-**Last synced:** 2026-10-12 04:39 UTC  
+**Last synced:** 2026-10-12 05:33 UTC  
 **State Hub:** http://127.0.0.1:8000 *(adjust if running on a remote machine)*
 
 ## Active Workstreams
 
 ### GADM-0.3: global sensitivity, power channels, cohorts
-Progress: 3/6 done  |  workplan_id: `23e33ee7-cb27-52bc-819c-704f44f91663`
+Progress: 4/6 done  |  workplan_id: `23e33ee7-cb27-52bc-819c-704f44f91663`
 
 **Open tasks:**
-- · Separate wealth from power  `99e702d7`
 - · Strengthen attention dynamics and the full organism grid  `f56e20b4`
 - · Life-cycle cohorts  `2b749127`
 
diff --git a/AGENTS.md b/AGENTS.md
index 797f695..04fa022 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -22,6 +22,7 @@ cd simulations/gadm02 && python3 run_scenarios.py && python3 sensitivity.py
 cd simulations/gadm02 && python3 gsa.py   # global sensitivity, ~5 min
 cd simulations/gadm02 && python3 -B power_channels.py   # GADM-0.3 power channels (T03 stage)
 cd simulations/gadm02 && python3 -B wealth.py   # GADM-0.3 wealth vs. power
+cd simulations/gadm02 && python3 -B organism_grid.py   # GADM-0.3 organism grid
 ```
 
 Use `python3 -B` after quick edits; a stale bytecode cache once masked a change.
diff --git a/WORK-RECORDS.md b/WORK-RECORDS.md
index 70ddb25..dbfc919 100644
--- a/WORK-RECORDS.md
+++ b/WORK-RECORDS.md
@@ -43,6 +43,6 @@
 | task | ASSEMBLY-WP-0005-T01 | done | — | workplans/ASSEMBLY-WP-0005-gadm-0.3.md |
 | task | ASSEMBLY-WP-0005-T02 | done | — | workplans/ASSEMBLY-WP-0005-gadm-0.3.md |
 | task | ASSEMBLY-WP-0005-T03 | done | — | workplans/ASSEMBLY-WP-0005-gadm-0.3.md |
-| task | ASSEMBLY-WP-0005-T04 | todo | — | workplans/ASSEMBLY-WP-0005-gadm-0.3.md |
+| task | ASSEMBLY-WP-0005-T04 | done | — | workplans/ASSEMBLY-WP-0005-gadm-0.3.md |
 | task | ASSEMBLY-WP-0005-T05 | todo | — | workplans/ASSEMBLY-WP-0005-gadm-0.3.md |
 | task | ASSEMBLY-WP-0005-T06 | todo | — | workplans/ASSEMBLY-WP-0005-gadm-0.3.md |
diff --git a/models/GADM-0.2.md b/models/GADM-0.2.md
index 95b6a69..3b34054 100644
--- a/models/GADM-0.2.md
+++ b/models/GADM-0.2.md
@@ -292,7 +292,8 @@ Readings:
   which is WS-14 work.
 - A single population with no cohorts, sectors or regions.
 - Attention dynamics are weak: in the attention oligopoly, A falls only to
-  0.55. `aext` may be underestimated.
+  0.55. `aext` may be underestimated. *Resolved in GADM-0.3* (`GADM-0.3.md`
+  § 4.1: `aext` recalibrated to 0.275 against time-use evidence).
 - Euler integration, dt = 0.1. No stiffness issues were observed at these
   rates.
 
diff --git a/models/GADM-0.3.md b/models/GADM-0.3.md
index cda29db..484bf26 100644
--- a/models/GADM-0.3.md
+++ b/models/GADM-0.3.md
@@ -7,8 +7,9 @@ the code is the reference if the two ever disagree.
 # Generative Assembly Dynamics Model — GADM-0.3
 
 **Status:** in progress, exploratory. Implemented so far: power channels
-(§ 2, ASSEMBLY-WP-0005-T03) and wealth separated from power (§ 3, T04).
-Planned: attention dynamics and the organism grid (T05), cohorts (T06).
+(§ 2, ASSEMBLY-WP-0005-T03), wealth separated from power (§ 3, T04),
+attention recalibration and the organism grid (§ 4, T05). Planned: cohorts
+(T06).
 
 GADM-0.3 builds on GADM-0.2 (`GADM-0.2.md`). Everything not described here is
 unchanged; the implementation reuses `gadm02.py`. Time unit: one year.
@@ -257,10 +258,96 @@ value):
   although it plausibly could (through acquisitions). This is a deliberate
   simplification to make P3 testable, and it biases the result toward P3.
 
+---
+
+## 4. Attention recalibration and the organism grid (T05)
+
+### 4.1 Attention extraction against time-use evidence
+
+GADM-0.2 flagged attention dynamics as too weak: under its `aext` = 0.12,
+baseline attention headroom A *rose* from 0.50 to 0.65.
+
+Evidence used as the calibration anchor:
+
+- **American Time Use Survey 2023:** about 5.2 hours of leisure per day, of
+  which TV takes about 2.7 hours, over half (BLS).
+- **Social media:** roughly 2 h 20 min to 2 h 25 min per day for the average
+  internet user worldwide (DataReportal/GWI, Statista).
+
+Together these suggest that engagement-funded media already claim around half
+of discretionary time. Target: baseline A ≈ 0.45–0.5 (current state),
+falling to about 0.3 under an extraction regime.
+
+Solving the A equilibrium for these targets gives **`aext` = 0.275**:
+
+| Scenario | A (GADM-0.2 aext) | A (recalibrated) |
+|---|---|---|
+| Baseline | 0.69 | 0.49 |
+| Attention oligopoly | 0.57 | 0.37 |
+| Generative regime | 0.77 | 0.60 |
+| Generative, attention extraction | 0.44 | 0.26 |
+
+VFAC falls by 0.015–0.04 across scenarios. P and the scenario ordering are
+unchanged. This is an order-of-magnitude anchor, not an estimate: the
+mapping from hours of engagement media to "unclaimed attention" is itself an
+assumption (see the Goodhart note in `metrics/MetricsCatalog.md`, A).
+
+The T03 and T04 stages remain reproducible (`t03_params()`,
+`t04_params()`), verified by identical output.
+
+### 4.2 The 2 × 2 × 2 organism grid
+
+Axes (from `InformationOrganismsInGADM.md` § 5): **lineage ownership**
+(concentrated: L = lin_open = 0.1 / diffuse: 0.8), **membrane control**
+(operator: m = 0.2 / user-community: 0.8), **attention regime** (extraction:
+x_att = 0.9 / protected: 0.2). Each grid is run on the baseline and the
+generative background. Full tables:
+`simulations/gadm02/results/organism_grid.md`.
+
+Factorial effects (average change from the first to the second level):
+
+| Effect | VFAC, baseline bg. | VFAC, generative bg. | P, baseline bg. | P, generative bg. |
+|---|---|---|---|---|
+| lineage diffuse | **+0.130** | **+0.127** | −0.242 | −0.340 |
+| membrane user-controlled | +0.090 | +0.089 | −0.175 | −0.216 |
+| attention protected | +0.046 | +0.060 | −0.009 | +0.002 |
+| lineage × membrane | +0.040 | −0.005 | −0.093 | −0.032 |
+| other interactions | ≤ 0.011 | ≤ 0.006 | ≤ 0.006 | ≤ 0.005 |
+
+Consistency check: the (diffuse, user, protected) corner on the generative
+background reproduces the generative regime exactly (VFAC 0.672).
+
+### 4.3 Readings
+
+1. **Lineage ownership is the strongest organism lever,** ahead of membrane
+   control, on both backgrounds. This agrees with the GADM-0.2 Sobol
+   results only partly: there, `m` ranked above `L`. In the channel model,
+   lineage concentration feeds a self-reinforcing channel with learning with
+   use (P2), which strengthens its effect.
+2. **Lineage and membrane governance are complements where governance is
+   otherwise weak.** On the baseline background, doing both is worth +0.04
+   VFAC beyond the sum of the parts. On the generative background, the
+   interaction vanishes.
+3. **Attention protection improves VFAC but not power.** It acts through
+   attention headroom A, not through domination. In this model the attention
+   regime and discovery concentration are separate levers. The
+   attention-oligopoly scenario sets both.
+4. **Better organism governance increases attention pressure unless attention
+   is protected.** Under extraction, A is lowest in the best-governed corner
+   (0.29 versus 0.36 at baseline), because better-governed organisms grow
+   larger, and extraction scales with K_Ω. Organism governance and attention
+   protection have to go together.
+5. **Organism governance alone does not reach the generative regime.** On the
+   baseline background, the best organism corner (VFAC 0.560) closes about 70 %
+   of the gap to the full generative regime (0.672). The discovery channel
+   stays at about 0.6, because it depends on discovery concentration, which
+   is not an organism lever.
+
 ## Reproduce
 
 ```bash
 python3 -B -m unittest discover -s simulations/gadm02
 cd simulations/gadm02 && python3 -B power_channels.py   # T03 stage (wealth off)
 cd simulations/gadm02 && python3 -B wealth.py           # T04: P3 and scenarios
+cd simulations/gadm02 && python3 -B organism_grid.py    # T05: 2 × 2 × 2 organism grid
 ```
diff --git a/models/README.md b/models/README.md
index 0aaf570..0e7657d 100644
--- a/models/README.md
+++ b/models/README.md
@@ -11,7 +11,7 @@ exploratory: they generate hypotheses and are not established results.
 | [InformationOrganismsInGADM.md](InformationOrganismsInGADM.md) | mapping note v0.1 | ASSEMBLY-WP-0003-T03; input for GADM-0.2 (ASSEMBLY-WP-0004) |
 | [GADM-CLD.md](GADM-CLD.md) | v0.1 | causal-loop diagram, loops, signed link table (ASSEMBLY-WP-0004-T01/T02) |
 | [GADM-0.2.md](GADM-0.2.md) | GADM-0.2 | extensions decision, equations, scenario and sensitivity findings (ASSEMBLY-WP-0004) |
-| [GADM-0.3.md](GADM-0.3.md) | in progress | power channels (P1/P2) and wealth separated from power (P3) (ASSEMBLY-WP-0005-T03/T04) |
+| [GADM-0.3.md](GADM-0.3.md) | in progress | power channels (P1/P2) wealth separated from power (P3), attention recalibration and organism grid (ASSEMBLY-WP-0005-T03–T05) |
 | [GADM-0.3-Candidates.md](GADM-0.3-Candidates.md) | outline | life-cycle and power extensions, deferred items (ASSEMBLY-WP-0004-T08) |
 
 ## Conventions
diff --git a/simulations/README.md b/simulations/README.md
index 3a9115a..82cdde1 100644
--- a/simulations/README.md
+++ b/simulations/README.md
@@ -6,7 +6,7 @@ model version it implements.
 | Directory | Model | Entry points |
 |-----------|-------|--------------|
 | `gadm02/` | GADM-0.2 (`models/GADM-0.2.md`) | `run_scenarios.py`, `sensitivity.py`, `gsa.py`, `test_gadm02.py` |
-| `gadm02/gadm03.py` | GADM-0.3: power channels, wealth (`models/GADM-0.3.md`) | `power_channels.py`, `wealth.py`, `test_gadm03.py` |
+| `gadm02/gadm03.py` | GADM-0.3: power channels, wealth (`models/GADM-0.3.md`) | `power_channels.py`, `wealth.py`, `organism_grid.py`, `test_gadm03.py` |
 
 Python 3.10+, standard library only. Use `python3 -B` after quick edits: a stale
 bytecode cache can mask same-size changes made within the same second.
diff --git a/simulations/gadm02/gadm03.py b/simulations/gadm02/gadm03.py
index 89bd91c..34945c8 100644
--- a/simulations/gadm02/gadm03.py
+++ b/simulations/gadm02/gadm03.py
@@ -59,6 +59,10 @@ PARAMS.update({
     "t_w": 0.10,     # wealth-tax effectiveness
     "wtax": 0.20,    # wealth-tax lever (0..1)
     "k_w": 0.04,     # wealth → market/political control conversion
+    # attention extraction recalibrated against time-use evidence (T05):
+    # GADM-0.2's 0.12 let baseline attention headroom rise to 0.65; 0.275 keeps
+    # it near 0.45 (engagement media already take ~half of leisure time).
+    "aext": 0.275,
     # counter coefficients: calibrated, see calibrate()
     "c_m": 0.0794, "c_i": 0.3117, "c_d": 0.2815, "c_mem": 0.1354, "c_lin": 0.1372, "c_pol": 0.4011,
 })
@@ -134,7 +138,12 @@ def calibrate(params: dict | None = None, init: dict | None = None) -> dict:
 
 def t03_params() -> dict:
     """Parameter overrides that reproduce the T03 power-channel model (no wealth)."""
-    return {"wealth_on": 0.0, **calibrate({"wealth_on": 0.0})}
+    return {"wealth_on": 0.0, "aext": g2.PARAMS["aext"], **calibrate({"wealth_on": 0.0})}
+
+
+def t04_params() -> dict:
+    """Parameter overrides that reproduce the T04 stage (wealth, old attention)."""
+    return {"aext": g2.PARAMS["aext"]}
 
 
 def simulate(params: dict | None = None, init: dict | None = None,
diff --git a/simulations/gadm02/organism_grid.py b/simulations/gadm02/organism_grid.py
new file mode 100644
index 0000000..59b8dcb
--- /dev/null
+++ b/simulations/gadm02/organism_grid.py
@@ -0,0 +1,81 @@
+"""Full 2 x 2 x 2 organism scenario grid (InformationOrganismsInGADM.md § 5).
+
+Axes: lineage ownership (concentrated / diffuse), membrane control (operator /
+user-community), attention regime (extraction / protected). Each corner is run
+on two backgrounds (baseline and generative regime), and analysed as a 2^3
+factorial design: main effects and interactions on final VFAC and P.
+
+Usage: python3 -B simulations/gadm02/organism_grid.py
+"""
+
+from __future__ import annotations
+
+import itertools
+import sys
+from pathlib import Path
+
+sys.dont_write_bytecode = True
+
+import gadm03 as g  # noqa: E402
+from scenarios import load_all  # noqa: E402
+
+OUT = Path(__file__).resolve().parent / "results"
+AXES = {
+    "lineage": ({"L": 0.1, "lin_open": 0.1}, {"L": 0.8, "lin_open": 0.8}),   # concentrated / diffuse
+    "membrane": ({"m": 0.2}, {"m": 0.8}),                                   # operator / user
+    "attention": ({"x_att": 0.9}, {"x_att": 0.2}),                          # extraction / protected
+}
+LABELS = {"lineage": ("concentrated", "diffuse"), "membrane": ("operator", "user"),
+          "attention": ("extraction", "protected")}
+
+
+def effects(results: dict, key: str) -> list[tuple[str, float]]:
+    """2^3 factorial effects (high minus low level, averaged) for output `key`."""
+    names = list(AXES)
+    out = []
+    for r in range(1, 4):
+        for combo in itertools.combinations(range(3), r):
+            total = 0.0
+            for levels, res in results.items():
+                sign = 1
+                for i in combo:
+                    sign *= 1 if levels[i] == 1 else -1
+                total += sign * res[key]
+            out.append((" × ".join(names[i] for i in combo), total / 4))
+    return out
+
+
+def main() -> None:
+    OUT.mkdir(exist_ok=True)
+    scs = load_all()
+    lines = [f"# {g.MODEL_VERSION}: 2 × 2 × 2 organism grid", "",
+             "Generated by `simulations/gadm02/organism_grid.py`. Full GADM-0.3 (power",
+             "channels, wealth, recalibrated attention). Final values at t = 100 years.",
+             "Effects: average change from the first to the second level (diffuse,",
+             "user-controlled, protected); interactions in the standard 2^k sense.", ""]
+    for bg in ("baseline", "generative_regime"):
+        sc = scs[bg]
+        results = {}
+        lines += [f"## Background: {sc['title']}", "",
+                  "| Lineage | Membrane | Attention | VFAC | P | A | membrane ch. | lineage ch. | discovery ch. |",
+                  "|---|---|---|---|---|---|---|---|---|"]
+        for levels in itertools.product((0, 1), repeat=3):
+            params = dict(sc["params"])
+            for axis, lv in zip(AXES, levels):
+                params.update(AXES[axis][lv])
+            r = g.simulate(params, sc["init"])[-1]
+            results[levels] = r
+            lab = [LABELS[a][lv] for a, lv in zip(AXES, levels)]
+            lines.append(f"| {lab[0]} | {lab[1]} | {lab[2]} | {r['VFAC']:.3f} | {r['P']:.2f} | {r['A']:.2f} | "
+                         f"{r['Pmem']:.2f} | {r['Plin']:.2f} | {r['Pd']:.2f} |")
+        lines += ["", "| Effect | on VFAC | on P |", "|---|---|---|"]
+        ev, ep = effects(results, "VFAC"), dict(effects(results, "P"))
+        for name, v in sorted(ev, key=lambda t: -abs(t[1])):
+            lines.append(f"| {name} | {v:+.3f} | {ep[name]:+.3f} |")
+        lines.append("")
+    (OUT / "organism_grid.md").write_text("\n".join(lines) + "\n")
+    print("\n".join(lines))
+
+
+if __name__ == "__main__":
+    main()
diff --git a/simulations/gadm02/results/organism_grid.md b/simulations/gadm02/results/organism_grid.md
new file mode 100644
index 0000000..530cf7f
--- /dev/null
+++ b/simulations/gadm02/results/organism_grid.md
@@ -0,0 +1,53 @@
+# GADM-0.3-power: 2 × 2 × 2 organism grid
+
+Generated by `simulations/gadm02/organism_grid.py`. Full GADM-0.3 (power
+channels, wealth, recalibrated attention). Final values at t = 100 years.
+Effects: average change from the first to the second level (diffuse,
+user-controlled, protected); interactions in the standard 2^k sense.
+
+## Background: Baseline (current trends)
+
+| Lineage | Membrane | Attention | VFAC | P | A | membrane ch. | lineage ch. | discovery ch. |
+|---|---|---|---|---|---|---|---|---|
+| concentrated | operator | extraction | 0.291 | 0.82 | 0.36 | 0.85 | 0.93 | 0.70 |
+| concentrated | operator | protected | 0.322 | 0.82 | 0.71 | 0.85 | 0.93 | 0.70 |
+| concentrated | user | extraction | 0.338 | 0.74 | 0.35 | 0.04 | 0.93 | 0.69 |
+| concentrated | user | protected | 0.376 | 0.74 | 0.70 | 0.04 | 0.93 | 0.68 |
+| diffuse | operator | extraction | 0.372 | 0.68 | 0.34 | 0.85 | 0.04 | 0.66 |
+| diffuse | operator | protected | 0.422 | 0.67 | 0.68 | 0.86 | 0.05 | 0.66 |
+| diffuse | user | extraction | 0.495 | 0.41 | 0.29 | 0.06 | 0.06 | 0.60 |
+| diffuse | user | protected | 0.560 | 0.40 | 0.64 | 0.06 | 0.06 | 0.62 |
+
+| Effect | on VFAC | on P |
+|---|---|---|
+| lineage | +0.130 | -0.242 |
+| membrane | +0.090 | -0.175 |
+| attention | +0.046 | -0.009 |
+| lineage × membrane | +0.040 | -0.093 |
+| lineage × attention | +0.011 | -0.006 |
+| membrane × attention | +0.005 | -0.001 |
+| lineage × membrane × attention | +0.002 | -0.000 |
+
+## Background: Generative regime
+
+| Lineage | Membrane | Attention | VFAC | P | A | membrane ch. | lineage ch. | discovery ch. |
+|---|---|---|---|---|---|---|---|---|
+| concentrated | operator | extraction | 0.395 | 0.68 | 0.28 | 0.86 | 0.95 | 0.08 |
+| concentrated | operator | protected | 0.447 | 0.67 | 0.63 | 0.86 | 0.95 | 0.08 |
+| concentrated | user | extraction | 0.486 | 0.49 | 0.27 | 0.08 | 0.95 | 0.07 |
+| concentrated | user | protected | 0.544 | 0.50 | 0.62 | 0.08 | 0.95 | 0.08 |
+| diffuse | operator | extraction | 0.522 | 0.37 | 0.26 | 0.86 | 0.12 | 0.07 |
+| diffuse | operator | protected | 0.584 | 0.37 | 0.61 | 0.87 | 0.12 | 0.08 |
+| diffuse | user | extraction | 0.602 | 0.12 | 0.25 | 0.09 | 0.13 | 0.08 |
+| diffuse | user | protected | 0.672 | 0.13 | 0.60 | 0.09 | 0.14 | 0.08 |
+
+| Effect | on VFAC | on P |
+|---|---|---|
+| lineage | +0.127 | -0.340 |
+| membrane | +0.089 | -0.216 |
+| attention | +0.060 | +0.002 |
+| lineage × attention | +0.006 | +0.005 |
+| lineage × membrane | -0.005 | -0.032 |
+| membrane × attention | +0.004 | +0.004 |
+| lineage × membrane × attention | +0.001 | -0.002 |
+
diff --git a/simulations/gadm02/results/wealth.md b/simulations/gadm02/results/wealth.md
index a658826..4507090 100644
--- a/simulations/gadm02/results/wealth.md
+++ b/simulations/gadm02/results/wealth.md
@@ -1,6 +1,7 @@
 # GADM-0.3-power + wealth: hypothesis P3 and scenarios
 
-Generated by `simulations/gadm02/wealth.py`. Full GADM-0.3 (wealth_on = 1).
+Generated by `simulations/gadm02/wealth.py`. T04 stage of GADM-0.3 (wealth on,
+GADM-0.2 attention extraction).
 Final values at t = 100 years.
 
 ## P3: wealth tax sweep
diff --git a/simulations/gadm02/wealth.py b/simulations/gadm02/wealth.py
index b998196..0342f4a 100644
--- a/simulations/gadm02/wealth.py
+++ b/simulations/gadm02/wealth.py
@@ -4,6 +4,9 @@ P3: wealth taxation alone does not bound domination P when the membrane
 channel dominates. Test: sweep the wealth-tax lever wtax in [0, 1] in three
 settings and compare wealth W with the channels it can and cannot reach.
 
+Runs the T04 stage (gadm03.t04_params(): attention extraction as in GADM-0.2)
+so the results in models/GADM-0.3.md § 3 stay reproducible after T05.
+
 Usage: python3 -B simulations/gadm02/wealth.py
 """
 
@@ -30,7 +33,8 @@ def main() -> None:
     OUT.mkdir(exist_ok=True)
     scs = load_all()
     lines = [f"# {g.MODEL_VERSION} + wealth: hypothesis P3 and scenarios", "",
-             "Generated by `simulations/gadm02/wealth.py`. Full GADM-0.3 (wealth_on = 1).",
+             "Generated by `simulations/gadm02/wealth.py`. T04 stage of GADM-0.3 (wealth on,",
+             "GADM-0.2 attention extraction).",
              "Final values at t = 100 years.", "",
              "## P3: wealth tax sweep", ""]
     for name, title in CASES:
@@ -39,7 +43,7 @@ def main() -> None:
                   "| wtax | W | market | political | membrane | lineage | P | VFAC |",
                   "|---|---|---|---|---|---|---|---|"]
         for t in TAX:
-            r = g.simulate({**sc["params"], "wtax": t}, sc["init"])[-1]
+            r = g.simulate({**sc["params"], **g.t04_params(), "wtax": t}, sc["init"])[-1]
             lines.append(f"| {t:.2f} | {r['W']:.2f} | {r['Pm']:.2f} | {r['Ppol']:.2f} | "
                          f"{r['Pmem']:.2f} | {r['Plin']:.2f} | {r['P']:.2f} | {r['VFAC']:.3f} |")
         lines.append("")
@@ -48,7 +52,7 @@ def main() -> None:
               "|---|---|---|---|---|---|---|---|"]
     for name, sc in scs.items():
         a = g.simulate({**sc["params"], **g.t03_params()}, sc["init"])[-1]
-        b = g.simulate(sc["params"], sc["init"])[-1]
+        b = g.simulate({**sc["params"], **g.t04_params()}, sc["init"])[-1]
         lines.append(f"| {sc['title']} | {a['P']:.2f} | {b['P']:.2f} | {b['W']:.2f} | {b['Pm']:.2f} | "
                      f"{b['Ppol']:.2f} | {a['VFAC']:.3f} | {b['VFAC']:.3f} |")
     (OUT / "wealth.md").write_text("\n".join(lines) + "\n")
diff --git a/workplans/ASSEMBLY-WP-0005-gadm-0.3.md b/workplans/ASSEMBLY-WP-0005-gadm-0.3.md
index df54be5..fd9473e 100644
--- a/workplans/ASSEMBLY-WP-0005-gadm-0.3.md
+++ b/workplans/ASSEMBLY-WP-0005-gadm-0.3.md
@@ -77,7 +77,7 @@ with a check-dependent conversion into P. Test hypothesis P3.
 
 ```task
 id: ASSEMBLY-WP-0005-T05
-status: todo
+status: done
 priority: medium
 state_hub_task_id: "f56e20b4-33b5-5a6e-9e4c-fca63f99bbe1"
 ```