Low-overhead error detection with spacetime codes

# Standard library imports
import random
import time

# External libraries
import matplotlib.pyplot as plt
import numpy as np
from tqdm import tqdm

# Qiskit
from qiskit import QuantumCircuit
from qiskit.quantum_info import Clifford, Pauli, PauliLindbladMap, PauliList
from qiskit.result import sampled_expectation_value
from qiskit.transpiler import generate_preset_pass_manager
from qiskit.visualization import plot_coupling_map

# Qiskit Aer
from qiskit_aer import AerSimulator
from qiskit_aer.noise import NoiseModel as AerNoiseModel
from qiskit_aer.noise import ReadoutError, depolarizing_error

# Qiskit IBM Runtime
from qiskit_ibm_runtime import NoiseLearner, QiskitRuntimeService
from qiskit_ibm_runtime import SamplerV2 as Sampler

# Qiskit Paulice
from qiskit_paulice import add_pauli_checks
from qiskit_paulice.layout import get_check_qubits
from qiskit_paulice.noise_models import NoiseModel

def random_clifford_circuit(
    num_qubits: int, depth: int, rng: np.random.Generator
) -> QuantumCircuit:
    """Brickwork random Clifford on `num_qubits`, with `depth` CZ layers."""
    qc = QuantumCircuit(num_qubits)
    qc.h(range(num_qubits))
    for d in range(depth):
        for i in range(d % 2, num_qubits - 1, 2):
            qc.cz(i, i + 1)
        for q in range(num_qubits):
            if rng.integers(0, 2):
                qc.sx(q)
            if rng.integers(0, 2):
                qc.s(q)
            if rng.integers(0, 2):
                qc.sx(q)
    return qc


def find_check_layout(
    backend,
    num_qubits: int,
    rng: np.random.Generator,
    num_trials: int = 200,
    max_gate_error: float = 0.03,
    max_readout_error: float = 0.2,
) -> list[int]:
    """Find a low-error path of `num_qubits` qubits with many available ancillas.

    Builds random self-avoiding walks on the coupling map, excluding the qubits
    and two-qubit gates whose reported errors exceed the thresholds, and keeps
    the path that offers the most target and ancilla pairs. Ties are broken by
    the lower average two-qubit gate error along the path.
    """
    target = backend.target
    gate_2q = next(
        name for name in ("cz", "ecr", "cx") if name in target.operation_names
    )

    # Collect per-edge gate errors and per-qubit readout errors
    edge_error = {}
    for qubits, props in target[gate_2q].items():
        edge = tuple(sorted(qubits))
        if props is not None and props.error is not None:
            edge_error[edge] = min(edge_error.get(edge, 1.0), props.error)
    readout_error = {
        qubit: target["measure"][(qubit,)].error
        for (qubit,) in target["measure"]
    }

    # Keep only the edges whose gate and readout errors are acceptable
    adjacency = {}
    for (q1, q2), error in edge_error.items():
        if (
            error <= max_gate_error
            and readout_error.get(q1, 1.0) <= max_readout_error
            and readout_error.get(q2, 1.0) <= max_readout_error
        ):
            adjacency.setdefault(q1, set()).add(q2)
            adjacency.setdefault(q2, set()).add(q1)

    # Random self-avoiding walks; keep the path with the most check pairs
    starts = sorted(adjacency)
    best_path = None
    best_score = (-1, float("inf"))
    for _ in range(num_trials):
        path = [starts[rng.integers(len(starts))]]
        while len(path) < num_qubits:
            options = sorted(adjacency[path[-1]] - set(path))
            if not options:
                break
            path.append(options[rng.integers(len(options))])
        if len(path) < num_qubits:
            continue
        num_pairs = len(get_check_qubits(backend.coupling_map, path)[0])
        mean_error = float(
            np.mean(
                [edge_error[tuple(sorted(e))] for e in zip(path, path[1:])]
            )
        )
        if num_pairs > best_score[0] or (
            num_pairs == best_score[0] and mean_error < best_score[1]
        ):
            best_path, best_score = path, (num_pairs, mean_error)

    if best_path is None:
        raise RuntimeError(
            "No connected low-error path found. Relax the error thresholds."
        )
    return best_path


def learned_noise_model(layer_errors, layout: list[int]) -> NoiseModel:
    """Build a `NoiseModel` from `NoiseLearner` results.

    `NoiseLearner` reports one `PauliLindbladError` per entangling layer, whose
    generators are indexed against that layer's own physical qubits, while
    `NoiseModel.from_pauli_lindblad_maps` expects `PauliLindbladMap`s indexed the
    way `NoiseModel.from_backend` indexes them: by position in `layout`. This
    translates between the two and drops generators that fall outside `layout`.
    """
    phys_to_virt = {phys: virt for virt, phys in enumerate(layout)}
    maps = []
    for layer in layer_errors:
        if layer.error is None:
            continue
        terms = []
        for pauli, rate in zip(
            layer.error.generators, layer.error.rates, strict=True
        ):
            label, indices = [], []
            for local, phys in enumerate(layer.qubits):
                x, z = bool(pauli.x[local]), bool(pauli.z[local])
                if not (x or z):
                    continue
                if phys not in phys_to_virt:
                    break  # generator reaches outside the layout, so skip it
                label.append("Y" if x and z else "X" if x else "Z")
                indices.append(phys_to_virt[phys])
            else:
                if label:
                    terms.append(
                        ("".join(label), tuple(indices), float(rate))
                    )
        # Each map needs a 2-qubit generator to define an entangling layer
        if any(len(t[1]) == 2 for t in terms):
            maps.append(
                PauliLindbladMap.from_sparse_list(
                    terms, num_qubits=len(layout)
                )
            )
    if not maps:
        raise RuntimeError(
            "No usable layer errors. Check that the learner ran on this layout."
        )
    return NoiseModel.from_pauli_lindblad_maps(maps)


def append_basis_rotation(
    circuit: QuantumCircuit, pauli: Pauli
) -> QuantumCircuit:
    """Strip measurements, append basis rotations for `pauli`, and re-measure."""
    out = circuit.remove_final_measurements(inplace=False)
    for q in range(pauli.num_qubits):
        if pauli.x[q]:
            if pauli.z[q]:
                out.sdg(q)
            out.h(q)
    out.measure_all()
    return out


def expectation(counts: dict, pauli: Pauli) -> float:
    """Expectation value of `pauli` from counts measured in the Z basis.

    Pads with identity on any qubits beyond the support of `pauli`, such as the
    check ancillas that appear in the postselected counts.
    """
    if not counts:
        return float("nan")
    n = pauli.num_qubits
    sign = -1 if int(pauli.phase) % 4 == 2 else 1
    total = len(next(iter(counts)))
    label = "".join(
        "Z" if q < n and (pauli.x[q] or pauli.z[q]) else "I"
        for q in range(total - 1, -1, -1)
    )
    return sign * sampled_expectation_value(counts, label)


def cum_mean_sem(values: np.ndarray):
    """Cumulative mean and standard error of the mean, ignoring NaNs."""
    valid = ~np.isnan(values)
    total = np.cumsum(np.where(valid, values, 0.0))
    total_sq = np.cumsum(np.where(valid, values**2, 0.0))
    count = np.maximum(np.cumsum(valid).astype(float), 1)
    mean = total / count
    sem = np.sqrt(np.maximum(total_sq / count - mean**2, 0) / count)
    return np.where(np.cumsum(valid) > 0, mean, np.nan), sem

num_qubits = 12
depth = 4
seed = 1764
rng = np.random.default_rng(seed)
np.random.seed(seed)

circuit = random_clifford_circuit(num_qubits, depth, rng)
circuit.measure_all()
circuit.draw("mpl", fold=-1, scale=0.6)

service = QiskitRuntimeService()
backend = service.least_busy(operational=True, simulator=False)

print(f"Backend: {backend.name}")

# Search for a low-error path, then pair each target qubit with a neighboring ancilla
layout = find_check_layout(backend, num_qubits, rng)
target_qubits, ancilla_qubits = get_check_qubits(backend, layout)
num_checks = len(target_qubits)

print(f"Target qubits:  {target_qubits}")
print(f"Ancilla qubits: {ancilla_qubits}")
plot_coupling_map(
    num_qubits=backend.num_qubits,
    qubit_coordinates=getattr(
        backend.configuration(), "qubit_coordinates", None
    ),
    coupling_map=backend.configuration().coupling_map,
    figsize=(12, 12),
    qubit_color=[
        "#4CAF50"
        if i in set(layout)
        else "#FF9800"
        if i in set(ancilla_qubits)
        else "#DDDDDD"
        for i in backend.coupling_map.graph.node_indices()
    ],
    qubit_size=220,
    line_width=2,
    font_size=90,
)

pm = generate_preset_pass_manager(
    optimization_level=0, backend=backend, initial_layout=layout
)
circuit_isa = pm.run(circuit)
circuit_isa.draw("mpl", fold=-1, scale=0.6)

noise_model = NoiseModel.from_backend(
    backend, layout, uniform_gate_noise=True
)
print(noise_model)

checked = add_pauli_checks(
    circuit_isa,
    target_qubits,
    noise_model,
    ancilla_qubits=ancilla_qubits,
    cost="gamma",
    method="windowed",
    seed=seed,
)

print(f"Physical layout of payload and ancillas: {layout + ancilla_qubits}")
print("Checked circuit:")
checked[-1].circuit.draw("mpl", fold=-1, idle_wires=False)

depth = 24
num_stabilizers = 20
num_shots = 1_000

circuit = random_clifford_circuit(num_qubits, depth, rng)

# Build the full stabilizer group, then sample from it uniformly at random
circ_no_meas = circuit.remove_final_measurements(inplace=False)
stabilizer_group = PauliList([Pauli("I" * num_qubits)])
for generator in (
    Pauli(label) for label in Clifford(circ_no_meas).to_labels(mode="S")
):
    stabilizer_group = stabilizer_group + stabilizer_group.compose(generator)

keep = np.where(
    stabilizer_group.x.any(axis=1) | stabilizer_group.z.any(axis=1)
)[0]
chosen = np.random.default_rng(seed).choice(
    keep, size=min(num_stabilizers, len(keep)), replace=False
)
stabilizers = [stabilizer_group[int(i)] for i in chosen]

two_qubit_depth = circuit.depth(lambda x: x.operation.num_qubits == 2)
print(
    f"Sampled {len(stabilizers)} stabilizers of a {circuit.num_qubits}-qubit "
    f"circuit with two-qubit depth {two_qubit_depth}: "
    f"{{{stabilizers[0]}, {stabilizers[1]}, ...}}"
)

noisy_circuits = []
checked_circuits = []
depths_2q = []
t0 = time.time()
for i, pauli in enumerate(tqdm(stabilizers)):
    noisy_circuits.append(pm.run(append_basis_rotation(circuit, pauli)))
    # Shuffle target and ancilla pairs together so each target keeps its ancilla
    targets, ancillas = zip(
        *random.sample(
            list(zip(target_qubits, ancilla_qubits, strict=True)),
            k=len(target_qubits),
        ),
        strict=True,
    )
    checked_circuits.append(
        add_pauli_checks(
            noisy_circuits[-1],
            list(targets),
            noise_model,
            ancilla_qubits=list(ancillas),
            cost="gamma",
            method="windowed",
            seed=seed + 1 + i,
        )
    )
    depths_2q.append(
        checked_circuits[-1][-1].circuit.depth(lambda x: len(x.qubits) == 2)
    )

print(
    f"Added {num_checks} checks to {len(stabilizers)} circuits "
    f"in {(time.time() - t0):.0f}s."
)
print(
    f"On average, two-qubit depth increased from "
    f"{circuit.depth(lambda x: len(x.qubits) == 2)} to {int(np.mean(depths_2q))} "
    f"when adding {num_checks} checks."
)

aer_nm = AerNoiseModel()
aer_nm.add_all_qubit_quantum_error(
    depolarizing_error(noise_model.gate_noise, 2), ["cz"]
)
p = noise_model.readout_noise
aer_nm.add_all_qubit_readout_error(ReadoutError([[1 - p, p], [p, 1 - p]]))
noisy_sim = AerSimulator(method="stabilizer", noise_model=aer_nm)

counts = []
for i, checked_circ_result in enumerate(tqdm(checked_circuits)):
    noisy_counts = (
        noisy_sim.run(
            noisy_circuits[i], shots=num_shots, seed_simulator=seed * i + 1
        )
        .result()
        .get_counts()
    )
    checked_counts_per_variant = []
    for k, ck in enumerate(checked_circ_result):
        variant_counts = (
            noisy_sim.run(
                ck.circuit, shots=num_shots, seed_simulator=seed * i + 2 + k
            )
            .result()
            .get_counts()
        )
        checked_counts_per_variant.append(variant_counts)
    counts.append((noisy_counts, checked_counts_per_variant))

rate_per_variant = []
kept_per_stab = []
for i, (_, checked_counts_per_variant) in enumerate(counts):
    rates = []
    kept_at_num_checks = None
    for k, variant_counts in enumerate(checked_counts_per_variant):
        ps_fn = checked_circuits[i][k].get_postselection_method()
        kept = {
            bs: n for bs, n in variant_counts.items() if not ps_fn(bs).any()
        }
        rates.append(sum(kept.values()) / num_shots)
        if k == num_checks:
            kept_at_num_checks = kept
    rate_per_variant.append(rates)
    kept_per_stab.append(kept_at_num_checks)

max_len = max(len(s) for s in rate_per_variant)
rates_arr = np.full((len(rate_per_variant), max_len), np.nan)
for i, s in enumerate(rate_per_variant):
    rates_arr[i, : len(s)] = s
ks = np.arange(max_len)

fig, ax = plt.subplots(figsize=(8, 4))
ax.plot(ks, rates_arr.T, color="#ff8c00", alpha=0.15, linewidth=1)
ax.plot(
    ks,
    np.nanmedian(rates_arr, axis=0),
    color="black",
    linewidth=1,
    linestyle="--",
    label="median",
)
ax.set_xlabel("Checks committed")
ax.set_ylabel("Postselection rate")
ax.set_ylim((0, 1.05))
ax.set_title(
    f"Per-stabilizer postselection rate ({len(rates_arr)} stabilizers)"
)
ax.legend()
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

results = []
for i, ((noisy_counts, _), kept) in enumerate(
    zip(counts, kept_per_stab, strict=True)
):
    results.append(
        (
            expectation(noisy_counts, stabilizers[i]),
            expectation(kept, stabilizers[i]),
            sum(kept.values()) / num_shots,
        )
    )

fidelity_noisy = float(np.nanmean([r[0] for r in results]))
fidelity_postsel = float(np.nanmean([r[1] for r in results]))
psr = float(np.mean([r[2] for r in results]))
print(
    f"ideal fidelity:          1.0\n"
    f"noisy fidelity:          {fidelity_noisy:.4f}\n"
    f"postselected fidelity:   {fidelity_postsel:.4f}\n"
    f"mean postselection rate: {psr:.3f}"
)

evs_ideal = np.ones(len(results))
evs_noisy = np.array([r[0] for r in results])
evs_post = np.array([r[1] for r in results])
idx = np.arange(len(results))


def strip(ax, ys, color, label):
    m, s = np.nanmean(ys), np.nanstd(ys)
    ax.axhspan(
        m - s, m + s, color=color, alpha=0.15, label=f"{label} mean and std"
    )
    ax.axhline(
        m, color=color, linewidth=1, linestyle="--", label=f"{label} fidelity"
    )


fig, ax = plt.subplots(figsize=(8, 4))
ax.axhline(np.nanmean(evs_ideal), color="black", linewidth=1.5, label="ideal")
strip(ax, evs_noisy, "red", "noisy")
strip(ax, evs_post, "green", "postselected")
ax.scatter(idx, evs_noisy, color="red", s=22, alpha=0.7, label="noisy EVs")
ax.scatter(
    idx,
    evs_post,
    color="green",
    s=22,
    alpha=0.7,
    label="postselected EVs",
)
ax.set_xlabel("stabilizer index")
ax.set_ylabel(r"$\langle G \rangle$")
ax.set_ylim((-0.1, 1.1))
ax.set_title("Per-stabilizer expectation values")
ax.legend(loc="lower left")
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

M = np.arange(1, len(results) + 1)
fig, ax = plt.subplots(figsize=(8, 4))
for ys, color, label in [
    (evs_ideal, "black", "ideal"),
    (evs_noisy, "red", "noisy"),
    (evs_post, "green", "postselected"),
]:
    cm, sem = cum_mean_sem(ys)
    ax.plot(M, cm, color=color, linewidth=1.5, label=label)
    ax.fill_between(M, cm - sem, cm + sem, color=color, alpha=0.15)
ax.set_xlabel("number of stabilizers averaged")
ax.set_ylabel("running fidelity estimate")
ax.set_title("Fidelity convergence versus number of stabilizers")
ax.legend()
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

stab_scores = [
    [variant.cost for variant in checked_circ_result]
    for checked_circ_result in checked_circuits
]
max_len = max(len(s) for s in stab_scores)
scores = np.full((len(stab_scores), max_len), np.nan)
for i, s in enumerate(stab_scores):
    scores[i, : len(s)] = s
ks = np.arange(max_len)

fig, ax = plt.subplots(figsize=(8, 4))
ax.plot(ks, scores.T, color="#4682b4", alpha=0.15, linewidth=1)
ax.plot(
    ks,
    np.nanmedian(scores, axis=0),
    color="black",
    linewidth=1,
    linestyle="--",
    label="median",
)
ax.set_xlabel("Checks committed")
ax.set_ylabel("Gamma")
ax.set_yscale("log")
ax.set_title(f"Per-stabilizer gamma curves ({len(scores)} stabilizers)")
ax.legend()
ax.grid(True, alpha=0.3, which="both")
plt.tight_layout()
plt.show()

# -------------------------Step 1: build a larger payload and sample stabilizers-------------------------
hw_num_qubits = 20
hw_depth = 36
hw_num_stabilizers = 10
hw_num_shots = 40_000

hw_circuit = random_clifford_circuit(hw_num_qubits, hw_depth, rng)
hw_no_meas = hw_circuit.remove_final_measurements(inplace=False)

# Enumerating all 2^n stabilizers is infeasible at this size, so draw each
# stabilizer by composing a random subset of the group generators
hw_generators = [
    Pauli(label) for label in Clifford(hw_no_meas).to_labels(mode="S")
]
sample_rng = np.random.default_rng(seed)
hw_stabilizers = []
while len(hw_stabilizers) < hw_num_stabilizers:
    mask = sample_rng.integers(0, 2, hw_num_qubits).astype(bool)
    if not mask.any():
        continue  # skip the identity
    stabilizer = Pauli("I" * hw_num_qubits)
    for generator, chosen in zip(hw_generators, mask, strict=True):
        if chosen:
            stabilizer = stabilizer.compose(generator)
    hw_stabilizers.append(stabilizer)

# -------------------------Step 2: find a 20-qubit layout, learn its noise, and add checks-------------------------
# A single bad coupler or bad-readout qubit on the path drags every
# stabilizer down, so search harder and with tighter error thresholds
hw_layout = find_check_layout(
    backend,
    hw_num_qubits,
    rng,
    num_trials=500,
    max_gate_error=0.015,
    max_readout_error=0.05,
)
hw_target_qubits, hw_ancilla_qubits = get_check_qubits(backend, hw_layout)
hw_pm = generate_preset_pass_manager(
    optimization_level=0, backend=backend, initial_layout=hw_layout
)
print(f"Layout with {len(hw_target_qubits)} check pairs: {hw_layout}")

# ----- learn a Pauli-Lindblad noise model on this layout -----
# The simulator example scored checks against a uniform depolarizing channel
# inferred from calibration data. Here, learn the noise instead: NoiseLearner
# runs its own job on the QPU and returns a Pauli-Lindblad channel per unique
# entangling layer, so the checks are placed against the noise this layout
# actually has, including its spatial structure. All the sampled stabilizers
# share the same entangling layers and differ only in their final basis
# rotation, so learning on the bare payload covers all of them.
learner = NoiseLearner(
    mode=backend,
    options={
        "max_layers_to_learn": 4,
        "num_randomizations": 32,
        "shots_per_randomization": 128,
        "environment": {"job_tags": ["TUT_ASPC_LEARN"]},
    },
)
learner_job = learner.run([hw_pm.run(hw_circuit)])
print(f"Submitted noise-learner job {learner_job.job_id()}")
hw_layer_errors = learner_job.result().data

# To see how much the learned model helps, swap the next line for the
# simulator example's uniform model - a one-line change:
# hw_noise_model = NoiseModel.from_backend(backend, hw_layout, uniform_gate_noise=True)
hw_noise_model = learned_noise_model(hw_layer_errors, hw_layout)
# NoiseLearner characterizes gate noise only, so keep the readout estimate
# from calibration data rather than leaving it unset
hw_noise_model.readout_noise = NoiseModel.from_backend(
    backend, hw_layout, uniform_gate_noise=True
).readout_noise
print(
    f"Learned {len(hw_layer_errors)} layers; "
    f"readout noise {hw_noise_model.readout_noise:.5f}"
)

# ----- add the fully checked circuit per stabilizer -----
hw_noisy_circuits = []
hw_checked_circuits = []
for i, pauli in enumerate(tqdm(hw_stabilizers)):
    bare = hw_pm.run(append_basis_rotation(hw_circuit, pauli))
    hw_noisy_circuits.append(bare)
    variants = add_pauli_checks(
        bare,
        hw_target_qubits,
        hw_noise_model,
        ancilla_qubits=hw_ancilla_qubits,
        cost="gamma",
        method="windowed",
        seed=seed + 1 + i,
    )
    hw_checked_circuits.append(variants[-1])  # keep the fully checked circuit

# -------------------------Step 3: submit one Sampler job with the bare and checked circuits-------------------------
sampler = Sampler(mode=backend)
sampler.options.default_shots = hw_num_shots
sampler.options.environment.job_tags = ["TUT_ASPC"]

pubs = hw_noisy_circuits + [cc.circuit for cc in hw_checked_circuits]
job = sampler.run(pubs)
print(f"Submitted job {job.job_id()} with {len(pubs)} circuits")

# -------------------------Step 4: postselect and compare fidelity-------------------------
result = job.result()
n_stab = len(hw_stabilizers)

hw_results = []
for i in range(n_stab):
    noisy_counts = result[i].join_data().get_counts()
    checked_counts = result[n_stab + i].join_data().get_counts()
    ps_fn = hw_checked_circuits[i].get_postselection_method()
    kept = {bs: c for bs, c in checked_counts.items() if not ps_fn(bs).any()}
    hw_results.append(
        (
            expectation(noisy_counts, hw_stabilizers[i]),
            expectation(kept, hw_stabilizers[i]),
            sum(kept.values()) / sum(checked_counts.values()),
        )
    )

hw_fidelity_noisy = float(np.nanmean([r[0] for r in hw_results]))
hw_fidelity_postsel = float(np.nanmean([r[1] for r in hw_results]))
hw_psr = float(np.mean([r[2] for r in hw_results]))
print(
    f"noisy fidelity estimate:        {hw_fidelity_noisy:.4f}\n"
    f"postselected fidelity estimate: {hw_fidelity_postsel:.4f}\n"
    f"mean postselection rate:        {hw_psr:.4f} "
    f"(~{int(round(hw_psr * hw_num_shots))} kept shots per circuit)"
)

# Per-stabilizer breakdown. The postselection rate varies from stabilizer to
# stabilizer, so a stabilizer whose postselected value barely moves is usually
# one whose checks rejected little; the kept-shot count says how much of the
# gap is statistics rather than signal.
print("\nper-stabilizer results:")
print(
    f"{'idx':>3}  {'noisy':>8}  {'postsel':>8}  {'psr':>7}  {'kept shots':>10}"
)
for i, (noisy, post, psr_i) in enumerate(hw_results):
    print(
        f"{i:>3}  {noisy:>8.4f}  {post:>8.4f}  {psr_i:>7.4f}  "
        f"{int(round(psr_i * hw_num_shots)):>10}"
    )

hw_noisy = np.array([r[0] for r in hw_results])
hw_post = np.array([r[1] for r in hw_results])
idx = np.arange(n_stab)

fig, ax = plt.subplots(figsize=(9, 4))
ax.axhline(1.0, color="black", linewidth=1.5, label="ideal")
strip(ax, hw_noisy, "red", "noisy")
strip(ax, hw_post, "green", "postselected")
ax.scatter(idx, hw_noisy, color="red", s=22, alpha=0.7, label="noisy EVs")
ax.scatter(
    idx,
    hw_post,
    color="green",
    s=22,
    alpha=0.7,
    label="postselected EVs",
)
ax.set_xlabel("stabilizer index")
ax.set_ylabel(r"$\langle G \rangle$")
ax.set_ylim((-0.1, 1.1))
ax.set_xticks(idx)
ax.set_title("Per-stabilizer expectation values on hardware")
# Outside the axes so it cannot hide a data point
ax.legend(loc="center left", bbox_to_anchor=(1.02, 0.5), frameon=False)
ax.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()