diff --git a/CHANGELOG.md b/CHANGELOG.md
index 69984936..4644bab5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+- **`generate_synthetic_control_data()` data generator + a capstone `SyntheticControl` tutorial.** New public generator (`diff_diff/prep_dgp.py`, exported from `diff_diff`) builds a **single-treated-unit** factor-model panel for synthetic-control demos and tests: one treated unit whose latent factor loadings and baseline are an exact convex combination of a few donors (so the noiseless trajectory lies in the donor convex hull and a synthetic control reproduces it closely — the observed fit is approximate under added noise), persistent AR(1) factors, predictor covariates that each proxy a distinct factor, a common calendar time effect, and a known `"ramp"` or `"constant"` treatment effect emitted as `true_effect`. Tutorial **`docs/tutorials/25_synthetic_control_policy.ipynb`** walks the whole `SyntheticControl` surface end-to-end on a policy-evaluation story (one state adopts a clean-energy standard), structured around **two inference philosophies**: cross-unit permutation (`in_space_placebo` + Firpo–Possebom `confidence_set`, with `leave_one_out` / `in_time_placebo` robustness) versus over-time conformal (CWZ `conformal_test` / `conformal_confidence_intervals` / `conformal_average_effect`), with the per-period conformal band as the climax. A `tests/test_t25_synthetic_control_policy_drift.py` drift guard re-derives every quoted number from the generator.
+
 ### Fixed
 - **`LinearRegression.get_se()` / `get_inference()` no longer return a `NaN` standard error from a tiny-negative variance artifact.** A high-leverage / degenerate coefficient (e.g. an absorbed-FE dummy near-collinear with the treatment, whose Bell-McCaffrey Satterthwaite DOF already hits the noise-floor guard) can have a CR2/HC variance of ~0 (≈1e-32) whose vcov diagonal lands just-below-zero under BLAS-dependent float rounding; `np.sqrt` of the negative then produced a `NaN` SE **nondeterministically** — passing single-threaded but failing under the parallel pure-Python full-suite run (`tests/test_methodology_wls_cr2.py::TestLinearRegressionFENanGuardEndToEnd::test_did_absorbed_fe_lr_inference_nan_for_guarded_coefs`). Both SE sites now clamp the vcov diagonal at 0, so the SE is finite (0 for a genuinely-zero variance), deterministic, and BLAS-independent. **No change for any positive variance** (the clamp is a no-op there); only the previously-`NaN` degenerate case is affected.
 
diff --git a/diff_diff/__init__.py b/diff_diff/__init__.py
index 8a35fe7c..75a52a07 100644
--- a/diff_diff/__init__.py
+++ b/diff_diff/__init__.py
@@ -133,6 +133,7 @@
     generate_staggered_data,
     generate_staggered_ddd_data,
     generate_survey_did_data,
+    generate_synthetic_control_data,
     make_post_indicator,
     make_treatment_indicator,
     rank_control_units,
@@ -426,6 +427,7 @@
     "generate_survey_did_data",
     "generate_continuous_did_data",
     "generate_reversible_did_data",
+    "generate_synthetic_control_data",
     "create_event_time",
     "aggregate_survey",
     "aggregate_to_cohorts",
diff --git a/diff_diff/guides/llms-full.txt b/diff_diff/guides/llms-full.txt
index d6b1c7e8..6d6dccca 100644
--- a/diff_diff/guides/llms-full.txt
+++ b/diff_diff/guides/llms-full.txt
@@ -1956,6 +1956,7 @@ from diff_diff import (
     generate_factor_data,
     generate_ddd_data,
     generate_continuous_did_data,
+    generate_synthetic_control_data,
 )
 
 # Basic 2x2 DiD data
@@ -1985,6 +1986,11 @@ data = generate_ddd_data(n_per_cell=100, treatment_effect=2.0, seed=42)
 # Continuous dose data
 data = generate_continuous_did_data(n_units=500, n_periods=4,
                                     att_function="linear", att_slope=2.0, seed=42)
+
+# Single-treated-unit panel for synthetic control (noiseless treated path in the
+# donor convex hull; ramping or constant effect). Use with SyntheticControl.
+data = generate_synthetic_control_data(n_donors=20, n_pre=60, n_post=5,
+                                       effect_type="ramp", seed=0)
 ```
 
 ## Real-World Datasets
diff --git a/diff_diff/prep.py b/diff_diff/prep.py
index 1f1048a6..933996f7 100644
--- a/diff_diff/prep.py
+++ b/diff_diff/prep.py
@@ -28,6 +28,7 @@
     generate_staggered_data,
     generate_staggered_ddd_data,
     generate_survey_did_data,
+    generate_synthetic_control_data,
 )
 from diff_diff.survey import (
     ResolvedSurveyDesign,
diff --git a/diff_diff/prep_dgp.py b/diff_diff/prep_dgp.py
index 36f2656d..95658b68 100644
--- a/diff_diff/prep_dgp.py
+++ b/diff_diff/prep_dgp.py
@@ -466,6 +466,223 @@ def generate_factor_data(
     return pd.DataFrame(records)
 
 
+def generate_synthetic_control_data(
+    n_donors: int = 20,
+    n_pre: int = 24,
+    n_post: int = 6,
+    n_factors: int = 3,
+    n_predictors: int = 3,
+    treatment_effect: float = 5.0,
+    effect_type: str = "ramp",
+    effect_growth: float = 1.0,
+    factor_strength: float = 1.0,
+    factor_persistence: float = 0.9,
+    n_convex_donors: int = 4,
+    baseline: float = 50.0,
+    unit_baseline_sd: float = 5.0,
+    time_trend: float = 0.5,
+    predictor_noise_sd: float = 0.5,
+    noise_sd: float = 1.0,
+    seed: Optional[int] = None,
+) -> pd.DataFrame:
+    """
+    Generate a single-treated-unit panel for synthetic control (ADH) demos.
+
+    Creates a factor-model panel with ONE treated unit (``unit == 0``) and
+    ``n_donors`` never-treated donors, designed so the treated unit's underlying
+    (noiseless) trajectory lies in the span of the donor trajectories — so a synthetic
+    control can reproduce it closely. The DGP:
+
+        Y_it = b_i + beta_t + factor_strength * (Lambda_i . F_t) + tau_it + eps_it
+
+    where ``F_t`` is a persistent (AR(1)) latent factor path, ``Lambda_i`` are
+    nonnegative factor loadings, ``b_i`` is a unit baseline, ``beta_t`` is a common
+    calendar time effect, ``tau_it`` is the treatment effect (treated unit, post
+    periods only), and ``eps_it ~ N(0, noise_sd)``.
+
+    The treated unit's loadings and baseline are an exact convex combination of
+    ``n_convex_donors`` donors (Dirichlet weights), so in the **noiseless** limit the
+    treated unit's outcome path is itself that convex combination of donor paths — it
+    lies in the donor convex hull and a synthetic control reproduces it exactly. With
+    nonzero ``noise_sd`` / ``predictor_noise_sd`` the observed data is only
+    *approximately* in-hull, so a fitted synthetic control achieves a small (not
+    exactly zero) pre-period RMSPE. Note that the generating weights are NOT identified
+    by the estimator: many donor combinations reproduce the treated pre-period path
+    equally well, so a fitted synthetic control recovers the counterfactual outcome path
+    (and ATT), not this specific weight vector.
+
+    Unlike :func:`generate_factor_data` (which *shifts* treated loadings to create
+    confounding for TROP), this generator keeps the treated unit reproducible from
+    donors, which is what classic synthetic control requires.
+
+    Parameters
+    ----------
+    n_donors : int, default=20
+        Number of never-treated donor units. The in-space placebo p-value floor is
+        ``1 / (n_donors + 1)``; larger pools give finer permutation p-values.
+    n_pre : int, default=24
+        Number of pre-treatment periods.
+    n_post : int, default=6
+        Number of post-treatment periods.
+    n_factors : int, default=3
+        Number of latent factors driving the common time structure.
+    n_predictors : int, default=3
+        Number of time-invariant predictor covariates (each a noisy linear map of
+        the unit's loading vector). Pass these as ``predictors=`` to
+        :class:`~diff_diff.SyntheticControl` to exercise the V-search; otherwise
+        the fit defaults to pre-period outcomes and these columns are unused.
+    treatment_effect : float, default=5.0
+        Base treatment effect on the treated unit in post periods. Under
+        ``effect_type="ramp"`` this is the first post-period effect.
+    effect_type : str, default="ramp"
+        ``"ramp"`` (effect grows by ``effect_growth`` each post period) or
+        ``"constant"`` (effect fixed at ``treatment_effect``).
+    effect_growth : float, default=1.0
+        Per-post-period increment under ``effect_type="ramp"`` (ignored otherwise).
+    factor_strength : float, default=1.0
+        Scaling on the interactive (loading . factor) component.
+    factor_persistence : float, default=0.9
+        AR(1) coefficient on the latent factors in ``[0, 1]``: ``0`` gives i.i.d.
+        factors, ``1`` a random walk. Serial dependence is what makes the
+        moving-block conformal scheme meaningful.
+    n_convex_donors : int, default=4
+        Number of donors whose convex combination defines the treated unit (must be
+        in ``[1, n_donors]``).
+    baseline : float, default=50.0
+        Mean unit baseline (e.g. a per-capita outcome level).
+    unit_baseline_sd : float, default=5.0
+        Standard deviation of donor baselines.
+    time_trend : float, default=0.5
+        Slope of the common calendar time effect ``beta_t = time_trend * t`` (a
+        common trend is matched by any convex combination, so it preserves in-hull
+        existence). Set to ``0.0`` for no trend.
+    predictor_noise_sd : float, default=0.5
+        Noise added to each predictor covariate.
+    noise_sd : float, default=1.0
+        Standard deviation of idiosyncratic outcome noise.
+    seed : int, optional
+        Random seed for reproducibility.
+
+    Returns
+    -------
+    pd.DataFrame
+        Long-format balanced panel with columns:
+
+        - ``unit``: unit identifier (``0`` is the treated unit; ``1..n_donors`` donors)
+        - ``period``: time period (``0..n_pre-1`` pre, ``n_pre..`` post)
+        - ``outcome``: outcome variable
+        - ``treatment``: absorbing 0/1 indicator (1 only for the treated unit in
+          post periods) — :meth:`SyntheticControl.fit` infers the treated unit and
+          post periods from this column
+        - ``treat``: unit-level ever-treated flag
+        - ``true_effect``: the true treatment effect for this observation
+        - ``x1 .. x{n_predictors}``: predictor covariates
+
+    Examples
+    --------
+    Generate a ramped-effect panel and fit a synthetic control:
+
+    >>> from diff_diff import generate_synthetic_control_data, SyntheticControl
+    >>> data = generate_synthetic_control_data(seed=42)
+    >>> res = SyntheticControl(seed=42).fit(
+    ...     data, outcome="outcome", treatment="treatment",
+    ...     unit="unit", time="period", predictors=["x1", "x2", "x3"])
+    >>> round(res.att, 1) > 0  # post-period gap recovers the injected effect
+    True
+    """
+    if n_donors < 2:
+        raise ValueError(f"n_donors ({n_donors}) must be at least 2")
+    if n_pre < 1:
+        raise ValueError(f"n_pre ({n_pre}) must be at least 1")
+    if n_post < 1:
+        raise ValueError(f"n_post ({n_post}) must be at least 1")
+    if n_factors < 1:
+        raise ValueError(f"n_factors ({n_factors}) must be at least 1")
+    if n_predictors < 0:
+        raise ValueError(f"n_predictors ({n_predictors}) must be non-negative")
+    if n_convex_donors < 1 or n_convex_donors > n_donors:
+        raise ValueError(f"n_convex_donors ({n_convex_donors}) must be in [1, n_donors={n_donors}]")
+    if effect_type not in ("ramp", "constant"):
+        raise ValueError(f"effect_type ({effect_type!r}) must be 'ramp' or 'constant'")
+    if not (0.0 <= factor_persistence <= 1.0):
+        raise ValueError(f"factor_persistence ({factor_persistence}) must be in [0, 1]")
+
+    rng = np.random.default_rng(seed)
+
+    n_periods = n_pre + n_post
+    n_units = n_donors + 1  # unit 0 is treated, 1..n_donors are donors
+
+    # Persistent latent factors F: (n_periods, n_factors). AR(1): rho=1 -> random
+    # walk, rho=0 -> i.i.d. The synthetic control removes this common structure, so
+    # the post-fit residuals stay stationary regardless of persistence.
+    F = np.empty((n_periods, n_factors))
+    F[0] = rng.normal(0, 1, n_factors)
+    for t in range(1, n_periods):
+        F[t] = factor_persistence * F[t - 1] + rng.normal(0, 1, n_factors)
+
+    # Donor loadings (nonnegative so a convex combination is well-defined) and
+    # baselines.
+    lambda_donor = np.abs(rng.normal(0, 1, (n_factors, n_donors)))
+    b_donor = rng.normal(baseline, unit_baseline_sd, n_donors)
+
+    # Treated unit = exact convex combination of n_convex_donors donors (in-hull).
+    convex_idx = rng.choice(n_donors, size=n_convex_donors, replace=False)
+    w_star = np.zeros(n_donors)
+    w_star[convex_idx] = rng.dirichlet(np.ones(n_convex_donors))
+    lambda_treated = lambda_donor @ w_star
+    b_treated = float(b_donor @ w_star)
+
+    # Stack: column 0 = treated, columns 1.. = donors.
+    loadings = np.column_stack([lambda_treated, lambda_donor])  # (n_factors, n_units)
+    baselines = np.concatenate([[b_treated], b_donor])  # (n_units,)
+
+    # Time-invariant predictors: each PRIMARILY proxies one distinct latent factor
+    # (diagonal-dominant map) plus a small cross-factor mix and noise. Distinct
+    # proxies give each predictor complementary signal, so the V-search spreads
+    # weight across them instead of leaning on a single redundant column.
+    pred_map = 0.25 * rng.normal(0, 1, (n_predictors, n_factors))
+    for h in range(n_predictors):
+        pred_map[h, h % n_factors] += 1.0
+    predictors = pred_map @ loadings + rng.normal(
+        0, predictor_noise_sd, (n_predictors, n_units)
+    )  # (n_predictors, n_units)
+
+    # Common calendar time effect (matched by any convex combination since sum w=1).
+    beta = time_trend * np.arange(n_periods)
+
+    records = []
+    for i in range(n_units):
+        is_treated_unit = i == 0
+        for t in range(n_periods):
+            post = t >= n_pre
+            y = baselines[i] + beta[t] + factor_strength * (loadings[:, i] @ F[t])
+
+            effect = 0.0
+            if is_treated_unit and post:
+                k = t - n_pre  # post-period index, 0-based
+                if effect_type == "ramp":
+                    effect = treatment_effect + effect_growth * k
+                else:
+                    effect = treatment_effect
+                y += effect
+
+            y += rng.normal(0, noise_sd)
+
+            row = {
+                "unit": i,
+                "period": t,
+                "outcome": y,
+                "treatment": int(is_treated_unit and post),
+                "treat": int(is_treated_unit),
+                "true_effect": effect,
+            }
+            for h in range(n_predictors):
+                row[f"x{h + 1}"] = predictors[h, i]
+            records.append(row)
+
+    return pd.DataFrame(records)
+
+
 def generate_ddd_data(
     n_per_cell: int = 100,
     treatment_effect: float = 2.0,
diff --git a/docs/api/prep.rst b/docs/api/prep.rst
index e01c80b4..f6012e87 100644
--- a/docs/api/prep.rst
+++ b/docs/api/prep.rst
@@ -128,6 +128,38 @@ Example
        time="period", treatment="treatment",
    )
 
+generate_synthetic_control_data
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Generate a **single-treated-unit** panel for synthetic control demos. A factor model
+places the treated unit's *noiseless* trajectory in the span of the donor trajectories
+(so a synthetic control reproduces it closely — the observed fit is approximate under
+the added transitory/predictor noise) and injects a known ramping or constant treatment
+effect. Use this with :class:`~diff_diff.SyntheticControl`.
+
+.. autofunction:: diff_diff.generate_synthetic_control_data
+
+Example
+^^^^^^^
+
+.. code-block:: python
+
+   from diff_diff import generate_synthetic_control_data, SyntheticControl
+
+   data = generate_synthetic_control_data(
+       n_donors=10,
+       n_pre=20,
+       n_post=4,
+       effect_type="ramp",
+       seed=0,
+   )
+
+   res = SyntheticControl(n_starts=1, seed=0).fit(
+       data, outcome="outcome", treatment="treatment",
+       unit="unit", time="period", predictors=["x1", "x2", "x3"],
+   )
+   print(round(res.att, 2), round(res.pre_rmspe, 2))
+
 Indicator Creation
 ------------------
 
diff --git a/docs/doc-deps.yaml b/docs/doc-deps.yaml
index 46ee8ecf..b21c3259 100644
--- a/docs/doc-deps.yaml
+++ b/docs/doc-deps.yaml
@@ -643,6 +643,8 @@ sources:
       - path: diff_diff/guides/llms.txt
         section: "Estimators"
         type: user_guide
+      - path: docs/tutorials/25_synthetic_control_policy.ipynb
+        type: tutorial
 
   diff_diff/synthetic_control_results.py:
     drift_risk: low
@@ -659,6 +661,8 @@ sources:
       - path: diff_diff/guides/llms-full.txt
         section: "SyntheticControlResults"
         type: user_guide
+      - path: docs/tutorials/25_synthetic_control_policy.ipynb
+        type: tutorial
 
   diff_diff/conformal.py:
     drift_risk: medium
@@ -670,6 +674,8 @@ sources:
         type: methodology
       - path: docs/api/synthetic_control.rst
         type: api_reference
+      - path: docs/tutorials/25_synthetic_control_policy.ipynb
+        type: tutorial
 
   # ── HonestDiD ───────��──────────────────────────────────────────────
 
@@ -917,6 +923,8 @@ sources:
         type: user_guide
       - path: docs/practitioner_decision_tree.rst
         type: user_guide
+      - path: docs/tutorials/25_synthetic_control_policy.ipynb
+        type: tutorial
 
   diff_diff/datasets.py:
     drift_risk: low
diff --git a/docs/index.rst b/docs/index.rst
index a638b0fd..38ce2725 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -109,6 +109,7 @@ Quick Links
    tutorials/15_efficient_did
    tutorials/16_survey_did
    tutorials/16_wooldridge_etwfe
+   tutorials/25_synthetic_control_policy
 
 .. toctree::
    :maxdepth: 1
diff --git a/docs/tutorials/25_synthetic_control_policy.ipynb b/docs/tutorials/25_synthetic_control_policy.ipynb
new file mode 100644
index 00000000..6c66a3dc
--- /dev/null
+++ b/docs/tutorials/25_synthetic_control_policy.ipynb
@@ -0,0 +1,1052 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1a69c65f",
+   "metadata": {},
+   "source": [
+    "# Synthetic control for a policy evaluation: two routes to inference\n",
+    "\n",
+    "One state adopts a **clean-energy standard** in a single quarter, and you want its\n",
+    "effect on **per-capita renewable electricity generation**. There is no clean control\n",
+    "group — no other state is a perfect twin of the one that acted. The *synthetic control\n",
+    "method* (Abadie, Diamond & Hainmueller 2010) solves this by **building** a counterfactual:\n",
+    "a weighted blend of untreated \"donor\" states chosen to track the treated state's\n",
+    "pre-policy trajectory. The post-policy gap between the real state and its synthetic twin\n",
+    "is the estimated effect.\n",
+    "\n",
+    "The catch: with a single treated unit there is **no analytical standard error** — in\n",
+    "`diff-diff`, `SyntheticControl`'s `se`, `t_stat`, `p_value`, and `conf_int` are `NaN` by\n",
+    "design. Inference instead comes from one of two genuinely different places, and this\n",
+    "tutorial walks **both**:\n",
+    "\n",
+    "- **Philosophy A — compare across regions** (permutation): is the treated state's gap\n",
+    "  unusual relative to pretending *each donor* had adopted the policy? This is the\n",
+    "  in-space placebo (ADH 2010) and the Firpo–Possebom (2018) confidence set.\n",
+    "- **Philosophy B — compare across time** (conformal): Chernozhukov, Wüthrich & Zhu (2021)\n",
+    "  invert a permutation-over-time test to produce a valid p-value for a hypothesized effect\n",
+    "  *path* and a **confidence interval for each post-period** — something cross-region\n",
+    "  permutation cannot give.\n",
+    "\n",
+    "We generate a synthetic panel where the truth is known, so every diagnostic can be checked\n",
+    "against the right answer."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6fcc14b4",
+   "metadata": {},
+   "source": [
+    "## 1. The setup\n",
+    "\n",
+    "We use `generate_synthetic_control_data`, which builds a factor-model panel with **one\n",
+    "treated unit (id `0`)** and a donor pool. The treated unit's latent factor loadings and\n",
+    "baseline are an exact convex combination of a few donors, so its **noiseless** trajectory\n",
+    "lies in the donor convex hull and a synthetic control can reproduce it closely — the\n",
+    "*observed* fit is approximate because we add transitory and predictor noise (so the\n",
+    "pre-period RMSPE is small but not exactly zero). A known **ramping** treatment effect\n",
+    "(`5, 6, 7, 8, 9`) is injected into the post period, mimicking a program that scales up as\n",
+    "it rolls out.\n",
+    "\n",
+    "We use a long pre-period (60 quarters) and a short post-period (5 quarters): synthetic\n",
+    "control wants a long, well-matched pre-window, and — as we'll see in §5 — the conformal\n",
+    "average-effect interval needs enough pre-period \"blocks\" to resolve."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9894e9a3",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:25.682914Z",
+     "iopub.status.busy": "2026-06-23T12:21:25.682658Z",
+     "iopub.status.idle": "2026-06-23T12:21:27.674959Z",
+     "shell.execute_reply": "2026-06-23T12:21:27.674696Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "panel: 1365 rows | 21 units (1 treated + 20 donors) | 65 quarters\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>unit</th>\n",
+       "      <th>period</th>\n",
+       "      <th>outcome</th>\n",
+       "      <th>treatment</th>\n",
+       "      <th>treat</th>\n",
+       "      <th>true_effect</th>\n",
+       "      <th>x1</th>\n",
+       "      <th>x2</th>\n",
+       "      <th>x3</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>49.004867</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.505192</td>\n",
+       "      <td>-0.399552</td>\n",
+       "      <td>0.971594</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>49.380750</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.505192</td>\n",
+       "      <td>-0.399552</td>\n",
+       "      <td>0.971594</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>51.031864</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.505192</td>\n",
+       "      <td>-0.399552</td>\n",
+       "      <td>0.971594</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>50.231137</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.505192</td>\n",
+       "      <td>-0.399552</td>\n",
+       "      <td>0.971594</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
+       "      <td>46.994405</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.505192</td>\n",
+       "      <td>-0.399552</td>\n",
+       "      <td>0.971594</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   unit  period    outcome  treatment  treat  true_effect        x1        x2  \\\n",
+       "0     0       0  49.004867          0      1          0.0  0.505192 -0.399552   \n",
+       "1     0       1  49.380750          0      1          0.0  0.505192 -0.399552   \n",
+       "2     0       2  51.031864          0      1          0.0  0.505192 -0.399552   \n",
+       "3     0       3  50.231137          0      1          0.0  0.505192 -0.399552   \n",
+       "4     0       4  46.994405          0      1          0.0  0.505192 -0.399552   \n",
+       "\n",
+       "         x3  \n",
+       "0  0.971594  \n",
+       "1  0.971594  \n",
+       "2  0.971594  \n",
+       "3  0.971594  \n",
+       "4  0.971594  "
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%matplotlib inline\n",
+    "import warnings\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "from diff_diff import SyntheticControl, generate_synthetic_control_data\n",
+    "\n",
+    "# On Apple-Silicon BLAS, harmless \"invalid value encountered in matmul\" RuntimeWarnings\n",
+    "# can surface from the optimizer; filter only that one (never UserWarnings, which carry\n",
+    "# methodology guidance). See numpy#28687.\n",
+    "warnings.filterwarnings(\"ignore\", category=RuntimeWarning, message=\".*encountered in matmul\")\n",
+    "\n",
+    "panel = generate_synthetic_control_data(\n",
+    "    n_donors=20,\n",
+    "    n_pre=60,\n",
+    "    n_post=5,\n",
+    "    n_factors=3,\n",
+    "    n_predictors=3,\n",
+    "    treatment_effect=5.0,   # first post-period effect\n",
+    "    effect_type=\"ramp\",     # effect grows by effect_growth each post period\n",
+    "    effect_growth=1.0,\n",
+    "    noise_sd=0.6,\n",
+    "    seed=0,\n",
+    ")\n",
+    "print(f\"panel: {len(panel)} rows | {panel['unit'].nunique()} units \"\n",
+    "      f\"(1 treated + 20 donors) | {panel['period'].nunique()} quarters\")\n",
+    "panel.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cada5276",
+   "metadata": {},
+   "source": [
+    "Columns: `unit` (0 = the treated state), `period` (0–59 pre, 60–64 post),\n",
+    "`outcome` (per-capita renewable generation), `treatment` (absorbing 0/1 — `1` only for the\n",
+    "treated state in post quarters), `true_effect` (the injected effect, for grading), and\n",
+    "three pre-treatment covariates `x1, x2, x3` — think *industrial electricity demand*,\n",
+    "*renewable-resource quality*, and *installed capacity*. `SyntheticControl.fit` infers the\n",
+    "treated unit and the post window directly from `treatment`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eec7c3db",
+   "metadata": {},
+   "source": [
+    "## 2. Fit the synthetic control\n",
+    "\n",
+    "`SyntheticControl` chooses **donor weights** (nonnegative, summing to one) so the synthetic\n",
+    "state matches the treated state on the predictors, and **predictor weights** `V` (via a\n",
+    "nested pre-period search) that decide how much each predictor matters. We pass the three\n",
+    "covariates as `predictors=` and use light solver settings to keep the notebook fast."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "243d4304",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:27.676080Z",
+     "iopub.status.busy": "2026-06-23T12:21:27.675946Z",
+     "iopub.status.idle": "2026-06-23T12:21:31.046072Z",
+     "shell.execute_reply": "2026-06-23T12:21:31.045783Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ATT (avg post-period gap): 6.790\n",
+      "pre-period RMSPE:          0.987\n",
+      "\n",
+      "top donor weights:\n",
+      " unit   weight\n",
+      "    2 0.509414\n",
+      "    3 0.256761\n",
+      "   13 0.081908\n",
+      "   18 0.071077\n",
+      "   16 0.016055\n",
+      "\n",
+      "predictor weights (V): {'x1': 0.461, 'x2': 0.081, 'x3': 0.458}\n"
+     ]
+    }
+   ],
+   "source": [
+    "sc = SyntheticControl(\n",
+    "    v_method=\"nested\",\n",
+    "    n_starts=1,\n",
+    "    inner_min_decrease=1e-3,\n",
+    "    optimizer_options={\"maxiter\": 50},\n",
+    "    seed=0,\n",
+    ")\n",
+    "res = sc.fit(\n",
+    "    panel,\n",
+    "    outcome=\"outcome\",\n",
+    "    treatment=\"treatment\",\n",
+    "    unit=\"unit\",\n",
+    "    time=\"period\",\n",
+    "    predictors=[\"x1\", \"x2\", \"x3\"],\n",
+    ")\n",
+    "print(f\"ATT (avg post-period gap): {res.att:.3f}\")\n",
+    "print(f\"pre-period RMSPE:          {res.pre_rmspe:.3f}\")\n",
+    "print(\"\\ntop donor weights:\")\n",
+    "print(res.get_weights_df().head(5).to_string(index=False))\n",
+    "print(\"\\npredictor weights (V):\", {k: round(v, 3) for k, v in res.v_weights.items()})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "16da9a9e",
+   "metadata": {},
+   "source": [
+    "**Reading the fit.** The synthetic state is a *sparse* blend — a couple of donors\n",
+    "carry most of the weight (here roughly `0.51·unit 2 + 0.26·unit 3 + …`). The pre-period\n",
+    "RMSPE of about **0.99** is small relative to the `5`–`9` effect, so the synthetic tracks the\n",
+    "treated state closely *before* the policy. The average post-period gap is **≈ 6.8**, against a\n",
+    "true average of `7.0`.\n",
+    "\n",
+    "**An honest caveat on the weights.** Do not read the weights as \"the true recipe.\" With\n",
+    "many donors and few factors, *many* weightings reproduce the pre-period path equally well —\n",
+    "the weight vector is **not identified**. What synthetic control identifies is the\n",
+    "**counterfactual outcome path** (and hence the gap/ATT), not a unique set of weights."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8e37cda3",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:31.047129Z",
+     "iopub.status.busy": "2026-06-23T12:21:31.047059Z",
+     "iopub.status.idle": "2026-06-23T12:21:31.050217Z",
+     "shell.execute_reply": "2026-06-23T12:21:31.049973Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>predictor</th>\n",
+       "      <th>treated</th>\n",
+       "      <th>synthetic</th>\n",
+       "      <th>donor_mean</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>x1</td>\n",
+       "      <td>0.505</td>\n",
+       "      <td>0.506</td>\n",
+       "      <td>0.028</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>x2</td>\n",
+       "      <td>-0.400</td>\n",
+       "      <td>-0.363</td>\n",
+       "      <td>0.298</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>x3</td>\n",
+       "      <td>0.972</td>\n",
+       "      <td>0.975</td>\n",
+       "      <td>0.545</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  predictor  treated  synthetic  donor_mean\n",
+       "0        x1    0.505      0.506       0.028\n",
+       "1        x2   -0.400     -0.363       0.298\n",
+       "2        x3    0.972      0.975       0.545"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Predictor balance: does the synthetic state look like the treated state on the\n",
+    "# covariates? Compare to the raw donor-pool average.\n",
+    "res.predictor_balance.round(3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a14ecfe5",
+   "metadata": {},
+   "source": [
+    "**Balance check.** The synthetic state matches the treated state almost exactly on\n",
+    "all three covariates (the `treated` and `synthetic` columns nearly coincide), while the raw\n",
+    "`donor_mean` is noticeably off. That is the whole point of weighting: a *plain* average of\n",
+    "donors is a poor comparison, but the *weighted* synthetic is a close one."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "5af70671",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:31.051203Z",
+     "iopub.status.busy": "2026-06-23T12:21:31.051129Z",
+     "iopub.status.idle": "2026-06-23T12:21:31.133201Z",
+     "shell.execute_reply": "2026-06-23T12:21:31.132941Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot 1: the treated state vs its synthetic counterfactual.\n",
+    "gd = res.get_gap_df().sort_values(\"period\")\n",
+    "periods = gd[\"period\"].to_numpy()\n",
+    "treated_y = panel[panel[\"unit\"] == 0].sort_values(\"period\")[\"outcome\"].to_numpy()\n",
+    "synth_y = treated_y - gd[\"gap\"].to_numpy()\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(9, 5))\n",
+    "ax.plot(periods, treated_y, color=\"#1f77b4\", lw=1.8, label=\"Treated state (actual)\")\n",
+    "ax.plot(periods, synth_y, color=\"#d62728\", lw=1.8, ls=\"--\", label=\"Synthetic control\")\n",
+    "ax.axvline(59.5, color=\"gray\", ls=\":\", lw=1, label=\"Policy onset\")\n",
+    "ax.set_xlabel(\"Quarter\")\n",
+    "ax.set_ylabel(\"Per-capita renewable generation\")\n",
+    "ax.set_title(\"Treated state vs synthetic control\")\n",
+    "ax.legend(loc=\"upper left\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "50e1271f",
+   "metadata": {},
+   "source": [
+    "## 3. The effect path\n",
+    "\n",
+    "The **gap** (treated − synthetic) is flat and near zero before the policy and opens up\n",
+    "after it. Overlaying the known `true_effect` shows the estimate recovers the ramp."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "b6efc707",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:31.134200Z",
+     "iopub.status.busy": "2026-06-23T12:21:31.134104Z",
+     "iopub.status.idle": "2026-06-23T12:21:31.174271Z",
+     "shell.execute_reply": "2026-06-23T12:21:31.174032Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot 2: estimated gap vs the true effect.\n",
+    "true_eff = panel[panel[\"unit\"] == 0].sort_values(\"period\")[\"true_effect\"].to_numpy()\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(9, 5))\n",
+    "ax.plot(periods, gd[\"gap\"].to_numpy(), color=\"#1f77b4\", lw=1.8, label=\"Estimated gap\")\n",
+    "ax.plot(periods, true_eff, color=\"green\", lw=1.6, ls=\":\", label=\"True effect\")\n",
+    "ax.axhline(0, color=\"black\", lw=0.7)\n",
+    "ax.axvline(59.5, color=\"gray\", ls=\":\", lw=1, label=\"Policy onset\")\n",
+    "ax.set_xlabel(\"Quarter\")\n",
+    "ax.set_ylabel(\"Gap (treated − synthetic)\")\n",
+    "ax.set_title(\"Estimated effect path\")\n",
+    "ax.legend(loc=\"upper left\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "42fe2f49",
+   "metadata": {},
+   "source": [
+    "The pre-period gap hugs zero (good fit), and the post-period gap climbs roughly\n",
+    "`5 → 9`, tracking the truth. But a single treated unit gives us one realization — **is this\n",
+    "gap distinguishable from noise?** That is the inference question, and the rest of the\n",
+    "tutorial answers it two ways."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c8019a7",
+   "metadata": {},
+   "source": [
+    "## 4. Philosophy A — compare across regions\n",
+    "\n",
+    "If the policy did nothing, the treated state's post/pre RMSPE ratio should look like what we\n",
+    "get by pretending *each donor* was treated. The **in-space placebo** (ADH 2010 §2.4) refits\n",
+    "the synthetic control with each donor cast as the \"treated\" unit and ranks the real treated\n",
+    "state's ratio against that placebo distribution."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a11a84fb",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:31.175249Z",
+     "iopub.status.busy": "2026-06-23T12:21:31.175179Z",
+     "iopub.status.idle": "2026-06-23T12:21:56.304732Z",
+     "shell.execute_reply": "2026-06-23T12:21:56.304454Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "placebo p-value: 0.0476\n",
+      "treated post/pre RMSPE ratio: 7.03 (rank 1 of 21)\n"
+     ]
+    }
+   ],
+   "source": [
+    "placebo = res.in_space_placebo(n_starts=1)\n",
+    "print(f\"placebo p-value: {res.placebo_p_value:.4f}\")\n",
+    "print(f\"treated post/pre RMSPE ratio: {res.rmspe_ratio:.2f} \"\n",
+    "      f\"(rank 1 of {res.n_placebos + 1})\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "78882a15",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:56.305796Z",
+     "iopub.status.busy": "2026-06-23T12:21:56.305723Z",
+     "iopub.status.idle": "2026-06-23T12:21:56.338721Z",
+     "shell.execute_reply": "2026-06-23T12:21:56.338449Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot 3: the placebo distribution of post/pre RMSPE ratios (Abadie's plot).\n",
+    "pl = res.get_placebo_df().sort_values(\"rmspe_ratio\")\n",
+    "colors = [\"#d62728\" if t else \"#bbbbbb\" for t in pl[\"is_treated\"]]\n",
+    "labels = [\"Treated state\" if t else \"\" for t in pl[\"is_treated\"]]\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(9, 5))\n",
+    "ax.barh(range(len(pl)), pl[\"rmspe_ratio\"], color=colors)\n",
+    "for y, (lab, t) in enumerate(zip(labels, pl[\"is_treated\"])):\n",
+    "    if t:\n",
+    "        ax.text(pl[\"rmspe_ratio\"].iloc[y], y, \"  treated\", va=\"center\", color=\"#d62728\")\n",
+    "ax.set_xlabel(\"Post/pre RMSPE ratio\")\n",
+    "ax.set_ylabel(\"Units (sorted)\")\n",
+    "ax.set_title(\"In-space placebo: the treated state is the most extreme\")\n",
+    "ax.set_yticks([])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5fd82f97",
+   "metadata": {},
+   "source": [
+    "**Reading the placebo.** The treated state has the **largest** post/pre RMSPE ratio\n",
+    "of all 21 units, giving a permutation p-value of **≈ 0.048** — significant at the 5% level.\n",
+    "(With 20 donors the smallest achievable p-value is `1/21`; a larger donor pool would give a\n",
+    "finer p-value.)\n",
+    "\n",
+    "The Firpo–Possebom (2018) **confidence set** inverts this placebo test over a family of\n",
+    "effect paths. The simplest family is a *constant* effect."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "94bda60c",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:56.339735Z",
+     "iopub.status.busy": "2026-06-23T12:21:56.339660Z",
+     "iopub.status.idle": "2026-06-23T12:21:56.342584Z",
+     "shell.execute_reply": "2026-06-23T12:21:56.342315Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "90% confidence set for a constant effect: [4.05, 24.33]\n"
+     ]
+    }
+   ],
+   "source": [
+    "cs = res.confidence_set(family=\"constant\", gamma=0.1)\n",
+    "in_set = cs[cs[\"in_set\"]]\n",
+    "print(f\"90% confidence set for a constant effect: \"\n",
+    "      f\"[{in_set['param'].min():.2f}, {in_set['param'].max():.2f}]\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89b85d55",
+   "metadata": {},
+   "source": [
+    "**A rigid family.** The constant-effect set is wide and lopsided — because our effect\n",
+    "*ramps* rather than staying constant, a single constant value is a poor description, and the\n",
+    "test only rejects clearly-wrong constants. This is exactly the gap Philosophy B fills: a\n",
+    "per-period interval that needs no parametric effect-path assumption.\n",
+    "\n",
+    "First, two standard robustness checks (ADH 2015)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "723eadfa",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:21:56.343511Z",
+     "iopub.status.busy": "2026-06-23T12:21:56.343444Z",
+     "iopub.status.idle": "2026-06-23T12:22:19.559001Z",
+     "shell.execute_reply": "2026-06-23T12:22:19.558740Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "max |change in ATT| when dropping any one donor: 0.761\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Leave-one-out: drop each weighted donor and refit; how much does the gap move?\n",
+    "loo = res.leave_one_out(n_starts=1)\n",
+    "moved = loo[loo[\"status\"] == \"loo\"]\n",
+    "print(f\"max |change in ATT| when dropping any one donor: {moved['delta_att'].abs().max():.3f}\")\n",
+    "\n",
+    "# Plot 4: leave-one-out gap paths (spaghetti) around the baseline.\n",
+    "log = res.get_leave_one_out_gaps()\n",
+    "fig, ax = plt.subplots(figsize=(9, 5))\n",
+    "for _, sub in log.groupby(\"dropped_unit\"):\n",
+    "    sub = sub.sort_values(\"period\")\n",
+    "    ax.plot(sub[\"period\"], sub[\"gap\"], color=\"#cccccc\", lw=0.8)\n",
+    "ax.plot(periods, gd[\"gap\"].to_numpy(), color=\"#1f77b4\", lw=2.0, label=\"Baseline (all donors)\")\n",
+    "ax.axhline(0, color=\"black\", lw=0.7)\n",
+    "ax.axvline(59.5, color=\"gray\", ls=\":\", lw=1)\n",
+    "ax.set_xlabel(\"Quarter\")\n",
+    "ax.set_ylabel(\"Gap (treated − synthetic)\")\n",
+    "ax.set_title(\"Leave-one-out: the effect path is robust to dropping any single donor\")\n",
+    "ax.legend(loc=\"upper left\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "49f1875e",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:22:19.560064Z",
+     "iopub.status.busy": "2026-06-23T12:22:19.559989Z",
+     "iopub.status.idle": "2026-06-23T12:22:22.894449Z",
+     "shell.execute_reply": "2026-06-23T12:22:22.894171Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " placebo_period  placebo_att status\n",
+      "             20        0.598    ran\n",
+      "             35        0.075    ran\n",
+      "             50       -0.367    ran\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# In-time (backdating) placebo: pretend the policy hit at an earlier quarter and\n",
+    "# check that no \"effect\" appears before the real onset.\n",
+    "itp = res.in_time_placebo(placebo_periods=[20, 35, 50], n_starts=1)\n",
+    "print(itp[[\"placebo_period\", \"placebo_att\", \"status\"]].round(3).to_string(index=False))\n",
+    "\n",
+    "# Plot 5: backdated gap paths stay near zero.\n",
+    "itg = res.get_in_time_placebo_gaps()\n",
+    "fig, ax = plt.subplots(figsize=(9, 5))\n",
+    "for pp, sub in itg.groupby(\"placebo_period\"):\n",
+    "    sub = sub.sort_values(\"period\")\n",
+    "    ax.plot(sub[\"period\"], sub[\"gap\"], lw=1.2, label=f\"fake onset @ {pp}\")\n",
+    "ax.plot(periods, gd[\"gap\"].to_numpy(), color=\"#1f77b4\", lw=2.0, label=\"real gap\")\n",
+    "ax.axhline(0, color=\"black\", lw=0.7)\n",
+    "ax.axvline(59.5, color=\"gray\", ls=\":\", lw=1, label=\"real onset\")\n",
+    "ax.set_xlabel(\"Quarter\")\n",
+    "ax.set_ylabel(\"Gap (treated − synthetic)\")\n",
+    "ax.set_title(\"In-time placebo: no effect appears before the real policy\")\n",
+    "ax.legend(loc=\"upper left\", fontsize=8)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "30eec1c4",
+   "metadata": {},
+   "source": [
+    "**Robustness.** Dropping any single donor moves the ATT by at most **≈ 0.76** — the\n",
+    "result does not hinge on one comparison state. And backdating the \"policy\" to earlier\n",
+    "quarters produces near-zero placebo effects (all `|·| < 1`), versus the real `5`–`9`: the\n",
+    "divergence is specific to the actual onset, not a pre-existing trend."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5cb79698",
+   "metadata": {},
+   "source": [
+    "## 5. Philosophy B — compare across time (conformal)\n",
+    "\n",
+    "Philosophy A asks whether the treated state is unusual *among units*. Conformal inference\n",
+    "(CWZ 2021) asks a different question: given **this** state's own time series, is the\n",
+    "post-period gap distinguishable from the pre-period fluctuations, **period by period**?\n",
+    "\n",
+    "Under a hypothesized effect path, CWZ subtracts it off, fits a *time-symmetric* proxy\n",
+    "synthetic control (constrained least squares on the raw outcomes over **all** periods — no\n",
+    "`V` matrix; this is what the exactness theory requires, and it differs slightly from the\n",
+    "headline ADH fit), and permutes the residuals over time. We start with the sharp null of\n",
+    "**no effect**."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "2a9ee973",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:22:22.895479Z",
+     "iopub.status.busy": "2026-06-23T12:22:22.895397Z",
+     "iopub.status.idle": "2026-06-23T12:22:22.901106Z",
+     "shell.execute_reply": "2026-06-23T12:22:22.900876Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "joint conformal test, H0: no effect  ->  p = 0.0154 (|Pi| = 65 permutations)\n",
+      "joint conformal test, H0: the TRUE ramp  ->  p = 0.831\n"
+     ]
+    }
+   ],
+   "source": [
+    "joint = res.conformal_test(0.0)\n",
+    "print(f\"joint conformal test, H0: no effect  ->  p = {joint['p_value']:.4f} \"\n",
+    "      f\"(|Pi| = {joint['n_perms']} permutations)\")\n",
+    "\n",
+    "# Sanity: the test should NOT reject the true ramp.\n",
+    "true_ramp = (\n",
+    "    panel[(panel[\"unit\"] == 0) & (panel[\"treatment\"] == 1)]\n",
+    "    .sort_values(\"period\")[\"true_effect\"].to_numpy()\n",
+    ")\n",
+    "print(f\"joint conformal test, H0: the TRUE ramp  ->  p = \"\n",
+    "      f\"{res.conformal_test(true_ramp)['p_value']:.3f}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5d723bb9",
+   "metadata": {},
+   "source": [
+    "The sharp null of no effect is rejected (**p ≈ 0.015**), while the true ramp is not\n",
+    "rejected (large p) — exactly as it should be. Now the payoff: **a confidence interval for\n",
+    "the effect in each post quarter**, by inverting that test over a grid of candidate values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "3625338c",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:22:22.902043Z",
+     "iopub.status.busy": "2026-06-23T12:22:22.901964Z",
+     "iopub.status.idle": "2026-06-23T12:22:22.954980Z",
+     "shell.execute_reply": "2026-06-23T12:22:22.954706Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " period  lower  upper  true_effect\n",
+      "     60   3.91   5.87          5.0\n",
+      "     61   4.50   6.46          6.0\n",
+      "     62   6.56   8.52          7.0\n",
+      "     63   7.45   9.52          8.0\n",
+      "     64   7.94  10.01          9.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "ci = res.conformal_confidence_intervals(alpha=0.1, scheme=\"moving_block\")\n",
+    "ci_show = ci[[\"period\", \"lower\", \"upper\"]].copy()\n",
+    "ci_show[\"true_effect\"] = true_eff[-5:]\n",
+    "print(ci_show.round(2).to_string(index=False))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "432d5ad4",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:22:22.955949Z",
+     "iopub.status.busy": "2026-06-23T12:22:22.955881Z",
+     "iopub.status.idle": "2026-06-23T12:22:23.002107Z",
+     "shell.execute_reply": "2026-06-23T12:22:23.001843Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 900x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Plot 6: the per-period conformal CI band (the payoff).\n",
+    "post_periods = ci[\"period\"].to_numpy()\n",
+    "sc_gap_post = gd[gd[\"phase\"] == \"post\"].sort_values(\"period\")[\"gap\"].to_numpy()\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(9, 5))\n",
+    "ax.fill_between(post_periods, ci[\"lower\"], ci[\"upper\"], alpha=0.25, color=\"#1f77b4\",\n",
+    "                label=\"90% conformal CI\")\n",
+    "ax.plot(post_periods, sc_gap_post, \"s--\", color=\"#1f77b4\", label=\"SC gap (point estimate)\")\n",
+    "ax.plot(post_periods, true_eff[-5:], \"o-\", color=\"green\", label=\"True effect\")\n",
+    "ax.set_xlabel(\"Quarter\")\n",
+    "ax.set_ylabel(\"Effect on per-capita generation\")\n",
+    "ax.set_title(\"CWZ pointwise conformal intervals track the ramping effect\")\n",
+    "ax.legend(loc=\"upper left\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6bee1aa6",
+   "metadata": {},
+   "source": [
+    "**Reading the band.** Each post quarter gets its own 90% interval, and the band\n",
+    "**rises with the ramp**, containing the true effect in every period — without ever assuming\n",
+    "the effect is constant or linear. This is what cross-region permutation could not deliver: a\n",
+    "calibrated, period-by-period uncertainty statement. (Each interval is a 90% interval, so an\n",
+    "occasional period legitimately missing the truth would be expected; here all five contain it.)\n",
+    "\n",
+    "For a single-number summary, CWZ also gives a confidence interval for the **average** effect\n",
+    "by collapsing the panel into non-overlapping blocks."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "4847e971",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2026-06-23T12:22:23.003092Z",
+     "iopub.status.busy": "2026-06-23T12:22:23.003008Z",
+     "iopub.status.idle": "2026-06-23T12:22:23.020638Z",
+     "shell.execute_reply": "2026-06-23T12:22:23.020351Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "90% CI for the average post-period effect: [6.50, 7.48]  (true average = 7.0)\n",
+      "(collapsed into 13 blocks)\n"
+     ]
+    }
+   ],
+   "source": [
+    "ae = res.conformal_average_effect(alpha=0.1, scheme=\"moving_block\")\n",
+    "print(f\"90% CI for the average post-period effect: \"\n",
+    "      f\"[{ae['lower']:.2f}, {ae['upper']:.2f}]  (true average = 7.0)\")\n",
+    "print(f\"(collapsed into {ae['n_blocks']} blocks)\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2a96951a",
+   "metadata": {},
+   "source": [
+    "The average-effect interval is **≈ [6.5, 7.5]** — tight, bounded, and bracketing the\n",
+    "true `7.0`. **Practitioner footnote:** this interval works by collapsing the panel into\n",
+    "`T/T* = 13` blocks and permuting them; its resolution is `1/13 ≈ 0.077`, comfortably below\n",
+    "`α = 0.1`. With a *short* pre-period the block count drops, the permutation grid coarsens,\n",
+    "and the interval can become uninformative (the method fails closed to `(-∞, ∞)` rather than\n",
+    "reporting a falsely-precise width). That is precisely why we used a long, 60-quarter\n",
+    "pre-window."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d7f4fd90",
+   "metadata": {},
+   "source": [
+    "## 6. The two philosophies, side by side\n",
+    "\n",
+    "| | Philosophy A (across regions) | Philosophy B (across time) |\n",
+    "|---|---|---|\n",
+    "| Question | Is the treated unit unusual vs *other units*? | Is the gap unusual vs *this unit's own history*? |\n",
+    "| Tools | in-space placebo, Firpo–Possebom set | CWZ test, pointwise CIs, average-effect CI |\n",
+    "| Resolution set by | number of donors (`1/(J+1)`) | number of periods / blocks |\n",
+    "| Output | one p-value; a set for a constant/linear family | per-period intervals; a free-form path p-value |\n",
+    "| Needs | a sizable donor pool | a long pre-period |\n",
+    "\n",
+    "Neither dominates. Cross-region permutation is the classic, intuitive check and is robust to\n",
+    "how the within-unit errors are correlated. Over-time conformal is the only one of the two\n",
+    "that gives you a **calibrated interval for each period's effect** without assuming a\n",
+    "parametric shape — invaluable when, as here, the effect evolves."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "32a59c77",
+   "metadata": {},
+   "source": [
+    "## 7. Practitioner takeaways\n",
+    "\n",
+    "- **Reach for synthetic control** when a single (or a few) units are treated and no untreated\n",
+    "  unit is a credible stand-alone control, but a *weighted blend* of donors can reproduce the\n",
+    "  treated unit's pre-period path. Check the pre-period RMSPE and the predictor-balance table\n",
+    "  before trusting any post-period gap.\n",
+    "- **Don't over-read the weights** — the counterfactual path is identified; the exact weights\n",
+    "  are not.\n",
+    "- **For inference, use both routes.** Report the in-space placebo p-value and a robustness\n",
+    "  pair (leave-one-out + in-time placebo); add CWZ pointwise intervals when stakeholders need\n",
+    "  period-by-period uncertainty, and the average-effect interval for a headline number.\n",
+    "- **Design for the method you'll use:** cross-region permutation wants a sizable donor pool\n",
+    "  (the p-value floor is `1/(J+1)`); conformal inference — especially the average-effect\n",
+    "  interval — wants a long pre-period.\n",
+    "\n",
+    "**Extensions not covered here:** folding covariates into the conformal proxy; the `q = 2`/\n",
+    "`q = ∞` conformal norms (we used `q = 1`); the `scheme=\"iid\"` permutation set; and the `cv`/\n",
+    "`inverse_variance` routes for selecting `V`.\n",
+    "\n",
+    "**Related tutorials:** [03 — Synthetic DiD](03_synthetic_did.ipynb) (a regression-weighted\n",
+    "cousin) and [10 — TROP](10_trop.ipynb) (a triply-robust panel estimator).\n",
+    "\n",
+    "**References:** Abadie, Diamond & Hainmueller (2010, 2015); Firpo & Possebom (2018);\n",
+    "Chernozhukov, Wüthrich & Zhu (2021). Full citations in the project\n",
+    "[references](../references.rst)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/tests/test_prep.py b/tests/test_prep.py
index 408adc36..68ef8a65 100644
--- a/tests/test_prep.py
+++ b/tests/test_prep.py
@@ -1040,6 +1040,182 @@ def test_invalid_n_treated(self):
             generate_factor_data(n_units=10, n_treated=0)
 
 
+class TestGenerateSyntheticControlData:
+    """Tests for generate_synthetic_control_data function."""
+
+    def test_basic_generation(self):
+        """Shape and exact column set (incl. predictor columns)."""
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data = generate_synthetic_control_data(
+            n_donors=10, n_pre=12, n_post=4, n_predictors=3, seed=42
+        )
+        assert len(data) == (10 + 1) * (12 + 4)  # (donors + treated) x periods
+        assert set(data.columns) == {
+            "unit",
+            "period",
+            "outcome",
+            "treatment",
+            "treat",
+            "true_effect",
+            "x1",
+            "x2",
+            "x3",
+        }
+
+    def test_single_treated_unit(self):
+        """Exactly one ever-treated unit (unit 0)."""
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data = generate_synthetic_control_data(n_donors=15, seed=42)
+        ever_treated = data.groupby("unit")["treat"].first()
+        assert ever_treated.sum() == 1
+        assert ever_treated.loc[0] == 1  # treated unit is id 0
+
+    def test_treatment_absorbing_treated_post_only(self):
+        """treatment==1 only for the treated unit in post periods."""
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data = generate_synthetic_control_data(n_donors=8, n_pre=10, n_post=4, seed=1)
+        treated_rows = data[data["treatment"] == 1]
+        assert (treated_rows["unit"] == 0).all()
+        assert (treated_rows["period"] >= 10).all()
+        # Donors are never treated; treated unit's pre periods are untreated.
+        assert (data[data["unit"] != 0]["treatment"] == 0).all()
+        assert (data[(data["unit"] == 0) & (data["period"] < 10)]["treatment"] == 0).all()
+
+    def test_ramp_effect_increases(self):
+        """Ramp effect strictly increases across post periods; pre/donor are zero."""
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data = generate_synthetic_control_data(
+            n_donors=8,
+            n_pre=10,
+            n_post=5,
+            effect_type="ramp",
+            treatment_effect=5.0,
+            effect_growth=1.0,
+            seed=1,
+        )
+        post_eff = (
+            data[(data["unit"] == 0) & (data["period"] >= 10)]
+            .sort_values("period")["true_effect"]
+            .to_numpy()
+        )
+        assert np.allclose(post_eff, [5.0, 6.0, 7.0, 8.0, 9.0])
+        assert np.all(np.diff(post_eff) > 0)
+        # true_effect is zero everywhere else.
+        assert (data[data["treatment"] == 0]["true_effect"] == 0).all()
+
+    def test_constant_effect_flat(self):
+        """Constant effect is flat across post periods."""
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data = generate_synthetic_control_data(
+            n_donors=8,
+            n_pre=10,
+            n_post=5,
+            effect_type="constant",
+            treatment_effect=4.0,
+            seed=1,
+        )
+        post_eff = data[(data["unit"] == 0) & (data["period"] >= 10)]["true_effect"]
+        assert (post_eff == 4.0).all()
+
+    def test_reproducibility(self):
+        """Seed produces reproducible data."""
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data1 = generate_synthetic_control_data(seed=123)
+        data2 = generate_synthetic_control_data(seed=123)
+        pd.testing.assert_frame_equal(data1, data2)
+
+    def test_treated_in_hull_recovers_effect(self):
+        """The treated unit's latent trajectory is in the donor hull, so on noisy
+        observed data a synthetic control achieves a small (approximate) pre-period
+        RMSPE and recovers the average effect (loose tolerance). The exact-hull
+        property is pinned separately by ``test_noiseless_outcome_path_in_hull``."""
+        from diff_diff import SyntheticControl
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data = generate_synthetic_control_data(
+            n_donors=15,
+            n_pre=20,
+            n_post=4,
+            effect_type="constant",
+            treatment_effect=5.0,
+            noise_sd=0.4,
+            seed=0,
+        )
+        res = SyntheticControl(
+            n_starts=1,
+            inner_min_decrease=1e-3,
+            optimizer_options={"maxiter": 50},
+            seed=0,
+        ).fit(
+            data,
+            outcome="outcome",
+            treatment="treatment",
+            unit="unit",
+            time="period",
+            predictors=["x1", "x2", "x3"],
+        )
+        # Good pre-fit (treated reproducible from donors) and recovered effect.
+        assert res.pre_rmspe < 2.0
+        assert abs(res.att - 5.0) < 2.0
+
+    def test_noiseless_outcome_path_in_hull(self):
+        """At zero noise the treated unit's outcome path IS an exact convex combination
+        of the donor paths (it lies in the donor convex hull), so a synthetic control
+        matching the pre-period outcome path reproduces it to ~zero pre-RMSPE — orders
+        of magnitude below the noisy case. Pins the *noiseless* in-hull claim the
+        docstring/tutorial make (the observed fit on noisy data is only approximate)."""
+        from diff_diff import SyntheticControl
+        from diff_diff.prep import generate_synthetic_control_data
+
+        data = generate_synthetic_control_data(
+            n_donors=12,
+            n_pre=20,
+            n_post=4,
+            effect_type="constant",
+            treatment_effect=5.0,
+            noise_sd=0.0,
+            predictor_noise_sd=0.0,
+            seed=0,
+        )
+        # Match on the full pre-period outcome path (no predictors=): the path itself is
+        # the exact convex combination, so the simplex fit is (near-)exact.
+        res = SyntheticControl(
+            n_starts=1,
+            inner_min_decrease=1e-4,
+            optimizer_options={"maxiter": 50},
+            seed=0,
+        ).fit(data, outcome="outcome", treatment="treatment", unit="unit", time="period")
+        assert res.pre_rmspe < 0.05, f"noiseless pre_rmspe={res.pre_rmspe:.4f} not ~0"
+        assert abs(res.att - 5.0) < 0.5
+
+    def test_invalid_arguments(self):
+        """Each validation guard raises ValueError with an informative message."""
+        from diff_diff.prep import generate_synthetic_control_data
+
+        with pytest.raises(ValueError, match="n_donors"):
+            generate_synthetic_control_data(n_donors=1)
+        with pytest.raises(ValueError, match="n_pre"):
+            generate_synthetic_control_data(n_pre=0)
+        with pytest.raises(ValueError, match="n_post"):
+            generate_synthetic_control_data(n_post=0)
+        with pytest.raises(ValueError, match="n_factors"):
+            generate_synthetic_control_data(n_factors=0)
+        with pytest.raises(ValueError, match="n_predictors"):
+            generate_synthetic_control_data(n_predictors=-1)
+        with pytest.raises(ValueError, match="n_convex_donors"):
+            generate_synthetic_control_data(n_donors=5, n_convex_donors=6)
+        with pytest.raises(ValueError, match="effect_type"):
+            generate_synthetic_control_data(effect_type="quadratic")
+        with pytest.raises(ValueError, match="factor_persistence"):
+            generate_synthetic_control_data(factor_persistence=1.5)
+
+
 class TestGenerateDddData:
     """Tests for generate_ddd_data function."""
 
diff --git a/tests/test_t25_synthetic_control_policy_drift.py b/tests/test_t25_synthetic_control_policy_drift.py
new file mode 100644
index 00000000..5b07f568
--- /dev/null
+++ b/tests/test_t25_synthetic_control_policy_drift.py
@@ -0,0 +1,244 @@
+"""Drift detection for Tutorial 25 (``docs/tutorials/25_synthetic_control_policy.ipynb``).
+
+The tutorial narrative quotes seed-specific numbers (ATT, pre-RMSPE, donor weights,
+placebo p-value, leave-one-out sensitivity, conformal p-values, the pointwise CI band, and
+the average-effect interval). ``pytest --nbmake`` only checks the cells *execute*; it does
+not check the prose. These asserts re-derive the same numbers from the library generator
+``generate_synthetic_control_data`` with the locked kwargs and check them against the values
+quoted in the markdown. If library numerics drift, this test fails and a maintainer must
+update the prose or investigate.
+
+Unlike the inline-DGP tutorials (e.g. T23), T25 builds its panel from the public generator,
+so there is no DGP code to duplicate — the drift test calls the same generator. A
+``test_notebook_kwargs_match`` sync-guard pins the generator/fit kwargs so a notebook-only
+edit can't silently change the behavior the numbers describe.
+"""
+
+from __future__ import annotations
+
+import warnings
+
+import numpy as np
+import pytest
+
+from diff_diff import SyntheticControl, generate_synthetic_control_data
+
+# Locked config — must stay in sync with the notebook §1/§2 cells.
+SEED = 0
+N_DONORS = 20
+N_PRE = 60
+N_POST = 5
+TREATMENT_EFFECT = 5.0
+EFFECT_GROWTH = 1.0
+NOISE_SD = 0.6
+PREDICTORS = ["x1", "x2", "x3"]
+IN_TIME_BACKDATES = [20, 35, 50]
+TRUE_RAMP = np.array([5.0, 6.0, 7.0, 8.0, 9.0])
+
+
+def _silence_matmul_warnings() -> None:
+    """Mirror the notebook's narrow Apple-Silicon BLAS RuntimeWarning filter
+    (numpy#28687); a no-op on other platforms. Never silences UserWarnings."""
+    warnings.filterwarnings("ignore", category=RuntimeWarning, message=r".*encountered in matmul")
+
+
+@pytest.fixture(scope="module")
+def fit():
+    """Build the panel and run the full surface once (matches the notebook order)."""
+    panel = generate_synthetic_control_data(
+        n_donors=N_DONORS,
+        n_pre=N_PRE,
+        n_post=N_POST,
+        n_factors=3,
+        n_predictors=3,
+        treatment_effect=TREATMENT_EFFECT,
+        effect_type="ramp",
+        effect_growth=EFFECT_GROWTH,
+        noise_sd=NOISE_SD,
+        seed=SEED,
+    )
+    with warnings.catch_warnings():
+        _silence_matmul_warnings()
+        res = SyntheticControl(
+            v_method="nested",
+            n_starts=1,
+            inner_min_decrease=1e-3,
+            optimizer_options={"maxiter": 50},
+            seed=SEED,
+        ).fit(
+            panel,
+            outcome="outcome",
+            treatment="treatment",
+            unit="unit",
+            time="period",
+            predictors=PREDICTORS,
+        )
+        res.in_space_placebo(n_starts=1)
+        cs = res.confidence_set(family="constant", gamma=0.1)
+        loo = res.leave_one_out(n_starts=1)
+        itp = res.in_time_placebo(placebo_periods=IN_TIME_BACKDATES, n_starts=1)
+        joint0 = res.conformal_test(0.0)
+        joint_true = res.conformal_test(TRUE_RAMP)
+        ci = res.conformal_confidence_intervals(alpha=0.1, scheme="moving_block")
+        ae = res.conformal_average_effect(alpha=0.1, scheme="moving_block")
+    return {
+        "panel": panel,
+        "res": res,
+        "cs": cs,
+        "loo": loo,
+        "itp": itp,
+        "joint0": joint0,
+        "joint_true": joint_true,
+        "ci": ci,
+        "ae": ae,
+    }
+
+
+def test_panel_composition(fit):
+    """§1 quoted: 1365 rows = 21 units (1 treated + 20 donors) × 65 quarters."""
+    panel = fit["panel"]
+    assert len(panel) == (N_DONORS + 1) * (N_PRE + N_POST) == 1365
+    assert panel["unit"].nunique() == N_DONORS + 1 == 21
+    assert panel["period"].nunique() == N_PRE + N_POST == 65
+    assert panel.groupby("unit")["treat"].first().sum() == 1  # single treated unit
+
+
+def test_true_effect_ramp(fit):
+    """§1 quoted: the injected post-period effect ramps 5 -> 9."""
+    te = (
+        fit["panel"]
+        .query("unit == 0 and treatment == 1")
+        .sort_values("period")["true_effect"]
+        .to_numpy()
+    )
+    np.testing.assert_array_equal(te, TRUE_RAMP)
+
+
+def test_att_and_pre_rmspe(fit):
+    """§2 quoted: ATT ≈ 6.8 (true mean 7.0), pre-period RMSPE ≈ 0.99.
+
+    Bands (not exact pins) absorb cross-platform BLAS variation in the nested V-search."""
+    res = fit["res"]
+    assert 6.5 <= res.att <= 7.1, f"att={res.att:.3f} outside [6.5, 7.1]"
+    assert 0.85 <= res.pre_rmspe <= 1.15, f"pre_rmspe={res.pre_rmspe:.3f} outside [0.85, 1.15]"
+
+
+def test_top_donor_weights(fit):
+    """§2 quoted: synthetic ≈ 0.51·unit 2 + 0.26·unit 3 + … (sparse; unit 2 dominant)."""
+    w = fit["res"].donor_weights
+    top_unit = max(w, key=w.get)
+    assert top_unit == 2, f"top-weighted donor is {top_unit}, expected 2"
+    assert 0.42 <= w[2] <= 0.58, f"weight[2]={w[2]:.3f} outside [0.42, 0.58]"
+    assert 0.20 <= w[3] <= 0.32, f"weight[3]={w[3]:.3f} outside [0.20, 0.32]"
+
+
+def test_predictor_balance(fit):
+    """§2 quoted: synthetic matches treated on all 3 covariates, far better than donor mean."""
+    pb = fit["res"].predictor_balance
+    synth_gap = (pb["treated"] - pb["synthetic"]).abs().max()
+    donor_gap = (pb["treated"] - pb["donor_mean"]).abs().max()
+    assert synth_gap < 0.1, f"max |treated-synthetic|={synth_gap:.3f} not < 0.1"
+    assert donor_gap > synth_gap, "synthetic should match treated better than the raw donor mean"
+
+
+def test_nan_analytical_inference(fit):
+    """Intro claim: classic SCM has no analytical SE — these stay NaN by design."""
+    res = fit["res"]
+    assert np.isnan(res.se)
+    assert np.isnan(res.t_stat)
+    assert np.isnan(res.p_value)
+    assert all(np.isnan(b) for b in res.conf_int)
+    assert res.is_significant is False
+
+
+def test_in_space_placebo(fit):
+    """§4 quoted: placebo p ≈ 0.048 (= 1/21, treated most extreme of 21)."""
+    res = fit["res"]
+    assert res.n_placebos == N_DONORS == 20
+    assert res.placebo_p_value == pytest.approx(1.0 / (N_DONORS + 1), abs=1e-6)
+    # Treated unit has the largest post/pre RMSPE ratio in the reference set.
+    pl = res.get_placebo_df()
+    assert bool(pl.loc[pl["is_treated"], "rmspe_ratio"].iloc[0] >= pl["rmspe_ratio"].max())
+
+
+def test_constant_confidence_set_wide_and_positive(fit):
+    """§4 quoted: the constant-effect set is wide and lopsided (rigid family vs a ramp)."""
+    in_set = fit["cs"][fit["cs"]["in_set"]]
+    lo, hi = in_set["param"].min(), in_set["param"].max()
+    assert lo < 6.0 and hi > 12.0, f"constant set [{lo:.2f}, {hi:.2f}] not wide/positive"
+
+
+def test_leave_one_out_robust(fit):
+    """§4 quoted: dropping any one donor moves the ATT by at most ≈ 0.76."""
+    moved = fit["loo"][fit["loo"]["status"] == "loo"]
+    max_delta = moved["delta_att"].abs().max()
+    assert max_delta < 1.2, f"max |delta_att|={max_delta:.3f} not < 1.2"
+
+
+def test_in_time_placebo_small(fit):
+    """§4 quoted: backdated 'effects' are all |·| < 1 vs the real 5–9."""
+    ran = fit["itp"][fit["itp"]["status"] == "ran"]
+    assert len(ran) == len(IN_TIME_BACKDATES)
+    assert (ran["placebo_att"].abs() < 1.0).all()
+
+
+def test_conformal_joint_test(fit):
+    """§5 quoted: joint p(no effect) ≈ 0.015 (= 1/65); the true ramp is NOT rejected."""
+    j0, jt = fit["joint0"], fit["joint_true"]
+    assert j0["n_perms"] == N_PRE + N_POST == 65
+    assert j0["p_value"] == pytest.approx(1.0 / 65, abs=1e-6)
+    assert jt["p_value"] > 0.5, f"true-ramp p={jt['p_value']:.3f} should be large"
+
+
+def test_pointwise_band_brackets_truth(fit):
+    """§5 quoted: the pointwise conformal band contains the true effect in all 5 periods."""
+    ci = fit["ci"].sort_values("period")
+    covered = ((ci["lower"].to_numpy() <= TRUE_RAMP) & (TRUE_RAMP <= ci["upper"].to_numpy())).sum()
+    assert covered == N_POST == 5, f"only {covered}/5 periods bracket the truth"
+
+
+def test_average_effect_ci(fit):
+    """§5 quoted: average-effect 90% CI ≈ [6.5, 7.5], bounded, bracketing 7.0; 13 blocks."""
+    ae = fit["ae"]
+    assert ae["status"] == "ran"
+    assert ae["n_blocks"] == (N_PRE + N_POST) // N_POST == 13
+    assert ae["lower"] <= 7.0 <= ae["upper"], "avg-effect CI must bracket the true mean 7.0"
+    assert 6.0 <= ae["lower"] <= 6.8, f"avg lower={ae['lower']:.2f} outside [6.0, 6.8]"
+    assert 7.2 <= ae["upper"] <= 7.9, f"avg upper={ae['upper']:.2f} outside [7.2, 7.9]"
+
+
+def test_notebook_kwargs_match():
+    """Sync guard: the notebook's generator/fit kwargs must match this module's locked
+    config, so a notebook-only edit can't silently invalidate the quoted numbers.
+
+    CI isolation note: the pure-Python / Rust CI jobs copy ``tests/`` without ``docs/``;
+    this guard skips gracefully there (nbmake separately verifies execution)."""
+    import json
+    from pathlib import Path
+
+    nb_path = (
+        Path(__file__).resolve().parents[1]
+        / "docs"
+        / "tutorials"
+        / "25_synthetic_control_policy.ipynb"
+    )
+    if not nb_path.exists():
+        pytest.skip(f"Notebook not found at {nb_path}; sync guard is local-dev only.")
+    with nb_path.open() as f:
+        nb = json.load(f)
+    src = "\n".join("".join(c["source"]) for c in nb["cells"] if c["cell_type"] == "code")
+    # Generator + fit kwargs the quoted numbers depend on.
+    for needle in (
+        "n_donors=20",
+        "n_pre=60",
+        "n_post=5",
+        "treatment_effect=5.0",
+        'effect_type="ramp"',
+        "effect_growth=1.0",
+        "noise_sd=0.6",
+        "seed=0",
+        'predictors=["x1", "x2", "x3"]',
+        "placebo_periods=[20, 35, 50]",
+        "inner_min_decrease=1e-3",
+    ):
+        assert needle in src, f"notebook §1/§2 missing locked kwarg: {needle!r}"