baselines: complete native author-code audit

2 files changed, 311 insertions, 0 deletions

diff --git a/results/native/dualprop_cifar10_vgg16_a0_b0p1_seed1988.json b/results/native/dualprop_cifar10_vgg16_a0_b0p1_seed1988.json
new file mode 100644
index 0000000..519c883
--- /dev/null
+++ b/results/native/dualprop_cifar10_vgg16_a0_b0p1_seed1988.json
@@ -0,0 +1,287 @@
+{
+  "audit": {
+    "complete": true,
+    "expected_epochs": 130,
+    "finite": true,
+    "selection_semantics_frozen": true,
+    "source_revision_match": true,
+    "source_tracked_clean": true
+  },
+  "dataset": "CIFAR-10",
+  "dataset_artifacts": [
+    {
+      "bytes": 170498071,
+      "path": "/home/yurenh2/sdrn/data/cifar-10-python.tar.gz",
+      "sha256": "6d958be074577803d12ecdefd02955f39262c83c16fe9348329d7fe0b5c001ce"
+    },
+    {
+      "bytes": 169566452,
+      "path": "/scratch/yurenh2/cifar10-binary-converted-v1.tar.gz",
+      "sha256": "0b97b0a786c64f4cd0996cace20e81e189669aba9f4b4e517eb529f9c7105cec"
+    }
+  ],
+  "gpu": {
+    "driver_version": "535.183.01",
+    "memory_total_mib": "8192",
+    "name": "NVIDIA GeForce GTX 1080",
+    "physical_index": "7",
+    "uuid": "GPU-df3d5933-c3e9-9ea1-d595-9d2a3b68c14b"
+  },
+  "importer_provenance": {
+    "path": "/home/yurenh2/sdil",
+    "revision": "04de9326e60bb9e3592c0ddb5474265d228cbce0",
+    "tracked_dirty": false
+  },
+  "method": "Dual Propagation",
+  "metrics": {
+    "epochs_observed": 130,
+    "final_epoch": 130,
+    "final_train_accuracy_percent": 99.96444702148438,
+    "final_validation_accuracy_percent": 92.76000213623047,
+    "primary_test_accuracy_percent": 92.45999908447266,
+    "primary_test_loss": 0.33965352177619934,
+    "primary_test_top5_accuracy_percent": 99.80000305175781,
+    "test_evaluations": 1,
+    "test_selected_test_accuracy_percent": null,
+    "test_wall_s": 3.2275850772857666,
+    "training_wall_s": 23052.372897148132,
+    "validation_selected_epoch": 118,
+    "validation_selected_test_accuracy_percent": 92.45999908447266,
+    "validation_selected_validation_accuracy_percent": 92.86000061035156,
+    "validation_wall_s": 64.21902823448181,
+    "wall_definition": "sum of author-measured train, validation, and final test runtimes; excludes setup, checkpoint I/O, and diagnostic plotting",
+    "wall_s": 23119.8195104599
+  },
+  "protocol": {
+    "command": [
+      "python",
+      "train.py",
+      "--model",
+      "VGG16",
+      "--dataset",
+      "cifar10",
+      "--num-epochs",
+      "130",
+      "--batch-size",
+      "100",
+      "--alpha",
+      "0.0",
+      "--beta",
+      "0.1",
+      "--loss",
+      "sce",
+      "--inference-sequence",
+      "fwK",
+      "--inference-passes-nudged",
+      "16",
+      "--learning-rate",
+      "0.025",
+      "--learning-rate-final",
+      "0.000002",
+      "--warmup-learning-rate",
+      "0.001",
+      "--learning-algorithm",
+      "dualprop-lagr-ff",
+      "--activation",
+      "relu",
+      "--decay-epochs",
+      "120",
+      "--warmup-epochs",
+      "10",
+      "--momentum",
+      "0.9",
+      "--weight-decay",
+      "5e-4",
+      "--dtype",
+      "float32",
+      "--param-dtype",
+      "float32",
+      "--percent-train",
+      "90",
+      "--percent-val",
+      "10",
+      "--seeds",
+      "1988",
+      "--experiment-name",
+      "sdil-dp-full-a0-b0p1-seed1988-v1"
+    ],
+    "dataset": "CIFAR-10",
+    "expected_epochs": 130,
+    "expected_gpu": {
+      "name": "NVIDIA GeForce GTX 1080",
+      "physical_index": "7"
+    },
+    "method": "Dual Propagation",
+    "paper_url": "https://arxiv.org/abs/2402.08573",
+    "published_accuracy_percent_mean": 92.41,
+    "published_accuracy_percent_sd": 0.07,
+    "repository_url": "https://github.com/Rasmuskh/dualprop_icml_2024",
+    "required_dataset_sha256": [
+      "6d958be074577803d12ecdefd02955f39262c83c16fe9348329d7fe0b5c001ce",
+      "0b97b0a786c64f4cd0996cace20e81e189669aba9f4b4e517eb529f9c7105cec"
+    ],
+    "resolved_config": {
+      "alpha": 0.0,
+      "batch_size": 100,
+      "beta": 0.1,
+      "decay_epochs": 120,
+      "inference_passes_nudged": 16,
+      "inference_sequence": "fwK",
+      "learning_algorithm": "dualprop-lagr-ff",
+      "learning_rate": 0.025,
+      "model": "VGG16",
+      "momentum": 0.9,
+      "percent_train": 90,
+      "percent_val": 10,
+      "warmup_epochs": 10,
+      "weight_decay": 0.0005
+    },
+    "seed": 1988,
+    "selection_semantics": {
+      "primary": "single test evaluation from the best-validation checkpoint",
+      "test_selected": "not available; test is evaluated only once",
+      "validation_selected": "same as primary"
+    },
+    "source_revision": "7b2595b34421e1483a721dbfdeff8cdabda3a1ff"
+  },
+  "protocol_id": "dualprop_cifar10_vgg16_a0_b0p1_seed1988",
+  "resolved_config": {
+    "alpha": 0.0,
+    "batch_size": 100,
+    "beta": 0.1,
+    "decay_epochs": 120,
+    "inference_passes_nudged": 16,
+    "inference_sequence": "fwK",
+    "learning_algorithm": "dualprop-lagr-ff",
+    "learning_rate": 0.025,
+    "model": "VGG16",
+    "momentum": 0.9,
+    "percent_train": 90,
+    "percent_val": 10,
+    "warmup_epochs": 10,
+    "weight_decay": 0.0005
+  },
+  "run_artifacts": [
+    {
+      "bytes": 7579669,
+      "path": "/scratch/yurenh2/sdil-reference/dualprop_icml_2024/runs/sdil-dp-full-a0-b0p1-seed1988-v1/2026_07_22_05_23_43/hist.npy",
+      "sha256": "401f24e1780b1ae1b57524694e9b9daaa68c5607ea7f68ef0c08698de87608dc"
+    }
+  ],
+  "runtime_environment": {
+    "pip_freeze": [
+      "Markdown==3.10.2",
+      "MarkupSafe==3.0.3",
+      "PyYAML==6.0.3",
+      "Pygments==2.20.0",
+      "Werkzeug==3.1.8",
+      "absl-py==1.4.0",
+      "array_record==0.8.1",
+      "astunparse==1.6.3",
+      "attrs==26.1.0",
+      "certifi==2026.7.22",
+      "cffi==2.1.0",
+      "charset-normalizer==3.4.9",
+      "chex==0.1.7",
+      "click==8.4.2",
+      "contourpy==1.3.2",
+      "cryptography==49.0.0",
+      "cycler==0.12.1",
+      "dm-pix==0.4.1",
+      "dm-tree==0.1.10",
+      "einops==0.8.2",
+      "etils==1.13.0",
+      "flatbuffers==25.12.19",
+      "flax==0.7.0",
+      "fonttools==4.63.0",
+      "fsspec==2026.6.0",
+      "gast==0.7.0",
+      "google-auth-oauthlib==1.4.0",
+      "google-auth==2.56.2",
+      "google-pasta==0.2.0",
+      "grpcio==1.82.1",
+      "h5py==3.16.0",
+      "idna==3.18",
+      "importlib_resources==7.1.0",
+      "jax==0.4.14",
+      "jaxlib==0.4.14+cuda11.cudnn86",
+      "keras==2.15.0",
+      "kiwisolver==1.5.0",
+      "libclang==18.1.1",
+      "markdown-it-py==4.2.0",
+      "matplotlib==3.8.0",
+      "mdurl==0.1.2",
+      "ml-dtypes==0.3.2",
+      "msgpack==1.2.1",
+      "nest-asyncio==1.6.0",
+      "numpy==1.25.2",
+      "nvidia-cublas-cu117==11.10.1.25",
+      "nvidia-cublas-cu11==11.11.3.6",
+      "nvidia-cuda-cupti-cu117==11.7.50",
+      "nvidia-cuda-cupti-cu11==11.8.87",
+      "nvidia-cuda-nvcc-cu117==11.7.64",
+      "nvidia-cuda-nvcc-cu11==2022.5.4",
+      "nvidia-cuda-runtime-cu117==11.7.60",
+      "nvidia-cuda-runtime-cu11==11.8.89",
+      "nvidia-cudnn-cu116==8.4.0.27",
+      "nvidia-cudnn-cu11==8.6.0.163",
+      "nvidia-cufft-cu117==10.7.2.50",
+      "nvidia-cufft-cu11==10.9.0.58",
+      "nvidia-curand-cu11==10.3.0.86",
+      "nvidia-cusolver-cu117==11.3.5.50",
+      "nvidia-cusolver-cu11==11.4.1.48",
+      "nvidia-cusparse-cu117==11.7.3.50",
+      "nvidia-cusparse-cu11==11.7.5.86",
+      "nvidia-nccl-cu11==2.19.3",
+      "oauthlib==3.3.1",
+      "opt_einsum==3.4.0",
+      "optax==0.1.7",
+      "orbax-checkpoint==0.3.5",
+      "packaging==26.0",
+      "pandas==2.3.3",
+      "pillow==12.3.0",
+      "promise==2.3",
+      "protobuf==3.20.3",
+      "psutil==7.2.2",
+      "pyasn1==0.6.4",
+      "pyasn1_modules==0.4.2",
+      "pycparser==3.0",
+      "pyparsing==3.3.2",
+      "python-dateutil==2.9.0.post0",
+      "pytz==2026.2",
+      "requests-oauthlib==2.0.0",
+      "requests==2.34.2",
+      "rich==15.0.0",
+      "scipy==1.11.4",
+      "seaborn==0.13.2",
+      "six==1.17.0",
+      "tensorboard-data-server==0.7.2",
+      "tensorboard==2.15.2",
+      "tensorflow-datasets==4.9.4",
+      "tensorflow-estimator==2.15.0",
+      "tensorflow-io-gcs-filesystem==0.37.1",
+      "tensorflow-metadata==1.15.0",
+      "tensorflow==2.15.1",
+      "tensorstore==0.1.74",
+      "termcolor==3.3.0",
+      "toml==0.10.2",
+      "toolz==1.1.0",
+      "tqdm==4.69.0",
+      "typing_extensions==4.16.0",
+      "tzdata==2026.3",
+      "urllib3==2.7.0",
+      "wrapt==1.14.2",
+      "zipp==4.1.0"
+    ],
+    "pip_freeze_sha256": "ea5bd886c4dcc61041aef10f12cf1a21ac018ae3e13cd64c64e3d90d5b1daf59",
+    "python_executable": "/scratch/yurenh2/venvs/dualprop/bin/python",
+    "python_version": "3.10.20 (main, Jun 11 2026, 15:17:37) [GCC 14.3.0]"
+  },
+  "schema_version": 1,
+  "seed": 1988,
+  "source_provenance": {
+    "path": "/scratch/yurenh2/sdil-reference/dualprop_icml_2024",
+    "revision": "7b2595b34421e1483a721dbfdeff8cdabda3a1ff",
+    "tracked_dirty": false
+  }
+}
diff --git a/results/native_baseline_audit.md b/results/native_baseline_audit.md
new file mode 100644
index 0000000..73262db
--- /dev/null
+++ b/results/native_baseline_audit.md
@@ -0,0 +1,24 @@
+# Native author-code baseline audit
+
+Both records passed the strict C4 artifact, source, protocol, environment,
+dataset, completeness, finiteness, selection, and cost-definition checks.
+These are method-native reproductions, not equal-compute comparisons with SDIL.
+
+| method | reproduced seed | primary test (%) | validation-selected test (%) | test-selected test (%) | published (%) | audited wall (s) |
+|:--|--:|--:|--:|--:|--:|--:|
+| BurstCCN | 0 | 80.070 | 80.100 | 80.250 | 82.97 ± 0.21 | 15451.3 |
+| Dual Prop | 1988 | 92.460 | 92.460 | — | 92.41 ± 0.07 | 23119.8 |
+
+BurstCCN's primary metric is its final epoch. Its validation-selected metric is
+the test accuracy from the minimum-validation-error epoch; its best test value
+is explicitly test-selected because the native trainer evaluates test every
+epoch. The `n_epochs=400` author configuration performs an epoch-0 evaluation
+and 399 optimization epochs. Dual Prop evaluates test once after restoring the
+best-validation checkpoint, so its primary and validation-selected values are
+identical and no test-selected value exists.
+
+The BurstCCN wall value is W&B run time through the final epoch log. The Dual
+Prop wall value sums author-measured train, validation, and final test time and
+excludes setup, checkpoint I/O, and diagnostic plotting. One reproduced seed
+establishes executable fidelity; published multi-seed uncertainty is retained
+for context and is not replaced by a one-seed error bar.