feat(benchmarks): WiFlow-STD reproduction harness + measurement (a) results (ADR-152 §2.2)

Shipped checkpoint REFUTED (0.08% PCK@20, wrong keypoint normalization);
6 reproducibility defects documented (broken imports, corrupted dataset
tail with float32-max garbage that NaN-poisons fp16 BatchNorm, unreachable
test phase). After repairs, retraining with upstream defaults reproduces
96.09% PCK@20 full-test / 96.61% corruption-free (published 97.25%) on
RTX 5080. Claims graded MEASURED-EQUIVALENT; 2.23M params + ~0.055 GFLOPs
verified. Third-party code/weights/data stay out of tree (gitignored).

Co-Authored-By: claude-flow <ruv@ruv.net>

benchmarks/wiflow-std/remote/clean_v2.py

@@ -0,0 +1,14 @@
+import numpy as np, os
+d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
+csi = np.load(os.path.join(d, 'csi_windows.npy'), mmap_mode='r+')
+zeroed = 0
+chunk = 4000
+for i in range(0, len(csi), chunk):
+    block = csi[i:i+chunk]
+    finite = np.isfinite(block)
+    bad = (~finite).any(axis=(1, 2)) | (np.abs(np.where(finite, block, 0)).max(axis=(1, 2)) > 1.5)
+    if bad.any():
+        block[bad] = 0.0
+        zeroed += int(bad.sum())
+csi.flush()
+print(f'zeroed {zeroed} corrupted windows entirely')

benchmarks/wiflow-std/remote/eval_retrained.py

@@ -0,0 +1,93 @@
+"""Evaluate the retrained WiFlow-STD checkpoint (ADR-152 §2.2a fallback).
+
+Scores the model produced by run.py (train_output/best_pose_model.pth or similar)
+on the seed-42 test split: full test set AND NaN-free subset (excluding windows
+that were zero-filled by clean_nan.py — file indices 487-499).
+"""
+import json, os, random, sys
+
+import numpy as np
+import torch
+from torch.utils.data import DataLoader, Subset
+
+sys.path.insert(0, os.path.expanduser('~/wiflow-std-bench/upstream'))
+from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders
+from models.pose_model import WiFlowPoseModel
+from utils.metrics import calculate_pck, calculate_mpjpe
+
+
+def find_checkpoint():
+    cands = []
+    for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/train_output')):
+        for f in files:
+            if f.endswith('.pth'):
+                cands.append(os.path.join(root, f))
+    # also upstream/test default output dir
+    for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/upstream')):
+        for f in files:
+            if f.endswith('.pth') and 'best' in f and 'cross_dataset' not in root:
+                p = os.path.join(root, f)
+                if os.path.getmtime(p) > os.path.getmtime(os.path.expanduser('~/wiflow-std-bench/train.log')) - 86400 * 2:
+                    cands.append(p)
+    cands = [c for c in cands if not c.endswith('upstream/best_pose_model.pth')]
+    if not cands:
+        sys.exit('no retrained checkpoint found')
+    return max(cands, key=os.path.getmtime)
+
+
+def evaluate(model, loader, device):
+    model.eval()
+    totals = {t: 0.0 for t in (0.1, 0.2, 0.3, 0.4, 0.5)}
+    total_mpe, n = 0.0, 0
+    with torch.no_grad():
+        for bx, by in loader:
+            bx, by = bx.to(device), by.to(device)
+            out = model(bx)
+            bs = by.size(0)
+            total_mpe += calculate_mpjpe(out, by) * bs
+            pck = calculate_pck(out, by, thresholds=list(totals))
+            for t in totals:
+                totals[t] += pck[t] * bs
+            n += bs
+    return {'samples': n, 'mpjpe': total_mpe / n,
+            **{f'pck@{int(t*100)}': totals[t] / n for t in totals}}
+
+
+random.seed(42); np.random.seed(42); torch.manual_seed(42)
+torch.cuda.manual_seed_all(42)
+torch.backends.cudnn.deterministic = True
+
+d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
+dataset = PreprocessedCSIKeypointsDataset(data_dir=d, keypoint_scale=1000.0,
+                                          enable_temporal_clean=True)
+_, _, test_loader = create_preprocessed_train_val_test_loaders(
+    dataset=dataset, batch_size=256, num_workers=2, random_seed=42)
+
+device = torch.device('cuda')
+ckpt = find_checkpoint()
+print('checkpoint:', ckpt)
+model = WiFlowPoseModel(dropout=0.5).to(device)
+state = torch.load(ckpt, map_location=device, weights_only=True)
+renames = {'att.': 'attention.', 'final_conv.': 'decoder.'}
+state = {next((new + k[len(old):] for old, new in renames.items()
+               if k.startswith(old)), k): v for k, v in state.items()}
+model.load_state_dict(state, strict=True)
+
+results = {'checkpoint': ckpt}
+print('=== full test set ===')
+results['test_full'] = evaluate(model, test_loader, device)
+print(json.dumps(results['test_full'], indent=2))
+
+# NaN-free subset: exclude windows from corrupted files 487-499
+test_subset = test_loader.dataset            # Subset(dataset, test_indices)
+w2f = dataset.window_to_file
+clean_idx = [i for i in test_subset.indices if w2f[i] < 487]
+print(f'=== NaN-free test subset ({len(clean_idx)} of {len(test_subset.indices)}) ===')
+clean_loader = DataLoader(Subset(dataset, clean_idx), batch_size=256, shuffle=False)
+results['test_clean'] = evaluate(model, clean_loader, device)
+print(json.dumps(results['test_clean'], indent=2))
+
+out = os.path.expanduser('~/wiflow-std-bench/eval_retrained.json')
+with open(out, 'w') as f:
+    json.dump(results, f, indent=2)
+print('wrote', out)

benchmarks/wiflow-std/remote/setup_and_train.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+set -ex
+cd ~/wiflow-std-bench
+
+# 1. clone upstream at the pinned commit
+if [ ! -d upstream ]; then
+  git clone https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling upstream
+fi
+cd upstream && git checkout 06899d294a0f44709d601a53e91dbf24759daefb && cd ..
+
+# 2. documented deviation: fix upstream import bug (TemporalConvNet does not exist)
+sed -i 's/from .tcn import TemporalConvNet/from .tcn import TemporalBlock/; s/'"'"'TemporalConvNet'"'"'/'"'"'TemporalBlock'"'"'/' upstream/models/__init__.py
+
+# 3. venv: torch cu128 (RTX 5080 = sm_120 needs >=2.7; their pin 2.3.1 predates Blackwell)
+if [ ! -d venv ]; then
+  python3 -m venv venv
+  ./venv/bin/pip install -q --upgrade pip
+  ./venv/bin/pip install -q torch --index-url https://download.pytorch.org/whl/cu128
+  ./venv/bin/pip install -q numpy pandas matplotlib seaborn scikit-learn opencv-python-headless scipy tqdm psutil kagglehub
+fi
+./venv/bin/python -c "import torch; print(torch.__version__, torch.cuda.is_available(), torch.cuda.get_device_name(0))"
+
+# 4. dataset via kagglehub (anonymous, public dataset)
+DS=$(./venv/bin/python -c "import kagglehub; print(kagglehub.dataset_download('kaka2434/wiflow-dataset'))")
+echo "dataset at: $DS"
+
+# 5. run.py hardcodes ../preprocessed_csi_data relative to upstream/
+ln -sfn "$DS/preprocessed_csi_data" ~/wiflow-std-bench/preprocessed_csi_data
+
+# 6. train with upstream defaults (seed 42 set inside run.py)
+../venv/bin/python ../clean_nan.py 2>/dev/null || venv/bin/python clean_nan.py
+cd upstream
+../venv/bin/python run.py --gpu 0 --batch_size 64 --epochs 50 --output_dir ../train_output