vraven 0.9.0a1__tar.gz

vraven-0.9.0a1/LICENSE

@@ -0,0 +1,201 @@
+Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorised by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorised to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Do not include
+      the brackets.) The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Daniel Jeremiah and VRAVEN contributors
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

vraven-0.9.0a1/NOTICE

@@ -0,0 +1,5 @@
+VRAVEN
+Copyright 2026 Daniel Jeremiah and VRAVEN contributors.
+
+VRAVEN stands for Visual Reasoning and Activation Visualisation for Explainable Networks.
+The project includes original source code, documentation and scientific visual contracts.

vraven-0.9.0a1/PKG-INFO

@@ -0,0 +1,453 @@
+Metadata-Version: 2.4
+Name: vraven
+Version: 0.9.0a1
+Summary: Compiler-assisted causal decompilation and scientific visual explanation of PyTorch models
+Author: Daniel Jeremiah and VRAVEN contributors
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/vraven-ai/vraven
+Project-URL: Repository, https://github.com/vraven-ai/vraven
+Project-URL: Issues, https://github.com/vraven-ai/vraven/issues
+Keywords: explainable-ai,deep-learning,pytorch,mechanistic-interpretability,causal-decompilation,visualisation
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: numpy>=1.26
+Requires-Dist: torch>=2.2
+Requires-Dist: plotly>=6.1
+Requires-Dist: networkx>=3.2
+Provides-Extra: publication
+Requires-Dist: kaleido>=1.0; extra == "publication"
+Provides-Extra: sklearn
+Requires-Dist: scikit-learn>=1.4; extra == "sklearn"
+Provides-Extra: analysis
+Requires-Dist: scipy>=1.11; extra == "analysis"
+Requires-Dist: scikit-learn>=1.4; extra == "analysis"
+Provides-Extra: darkside
+Requires-Dist: scipy>=1.11; extra == "darkside"
+Requires-Dist: scikit-learn>=1.4; extra == "darkside"
+Requires-Dist: ripser>=0.6.8; extra == "darkside"
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: pandas>=2.0; extra == "dev"
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Requires-Dist: ruff>=0.9; extra == "dev"
+Requires-Dist: mypy>=1.13; extra == "dev"
+Requires-Dist: scikit-learn>=1.4; extra == "dev"
+Requires-Dist: scipy>=1.11; extra == "dev"
+Requires-Dist: svgwrite>=1.4; extra == "dev"
+Requires-Dist: tomli>=2.0; python_version < "3.11" and extra == "dev"
+Dynamic: license-file
+
+# VRAVEN
+
+<p align="center">
+  <img src="assets/branding/avatars/vraven-avatar-256.png" alt="VRAVEN raven signature" width="220">
+</p>
+
+**Visual Reasoning and Activation Visualisation for Explainable Networks**
+
+## Compiler-assisted causal decompilation of PyTorch models
+
+VRAVEN is an experimental framework for reverse engineering a trained PyTorch model into a compact, executable and experimentally tested high-level decision mechanism.
+
+It addresses a different question from ordinary feature attribution:
+
+```text
+SHAP / LIME:
+Which input variables influenced the prediction?
+
+VRAVEN:
+What computation was recovered, what internal concepts appeared, how did they interact,
+which relationships survived intervention, can the mechanism execute as a compact programme,
+what would change the decision, and what remains unexplained?
+```
+
+The central pipeline is:
+
+```text
+Trained Model
+    ↓
+Internal Concept Discovery
+    ↓
+Concept Evolution
+    ↓
+Causal Mechanism Graph
+    ↓
+Executable Decision Programme
+    ↓
+Contrastive Explanation
+    ↓
+Counterfactual Proof
+    ↓
+Validity and Coverage Certificate
+```
+
+VRAVEN does **not** claim to recover one uniquely true explanation of every model. It recovers the smallest tested high-level programme found under the configured search and reports a validity envelope, fidelity evidence and unresolved model dark matter.
+
+## What is implemented in 0.9.0a1
+
+### Multi-route model capture
+
+VRAVEN attempts:
+
+1. `torch.export`
+2. `torch.fx`
+3. Runtime operator dispatch
+4. Module-hook fallback
+
+The preferred route produces a normalised ATen-level graph. Failed attempts and fallback limitations are retained in the certificate.
+
+### VRAVEN Mechanism IR
+
+The architecture-neutral intermediate representation records:
+
+* Operators, parameters and buffers
+* Tensor-flow edges
+* Shapes, data types, devices and strides
+* Dynamic-shape constraints and guards
+* Source and module provenance
+* Operator semantics
+* Autograd-path availability
+* Graph intervention points
+* Numerical equivalence
+* Unsupported computation
+
+### Automatic internal concept discovery
+
+VRAVEN currently supports:
+
+* Deterministic PCA concepts
+* Sparse-autoencoder concepts
+* Class preference and effect size
+* Top activating samples
+* Conservative association with supplied domain feature groups
+* Explicit unresolved concepts where meaning is not established
+
+### Cross-layer concept evolution
+
+A regularised optimal-transport alignment represents concept birth, persistence, splitting, merging and termination without treating independent embeddings as literal movement.
+
+### Graph-compiled causal interventions
+
+VRAVEN rewrites the captured FX or Export graph and inserts explicit intervention modules. Supported interventions include:
+
+```text
+zero
+replace
+scale
+add
+erase_direction
+set_concept
+set_concept_mean
+clamp
+```
+
+Effects are measured using a target-versus-alternatives logit margin and reported with bootstrap intervals, sign stability and prediction flips.
+
+### Intervention-constrained executable programme
+
+The programme is fitted jointly against:
+
+* Normal target margins
+* Tested internal intervention effects
+
+This is important because a conventional observational surrogate can achieve very high predictive fit while failing to reproduce the model under intervention.
+
+VRAVEN reports:
+
+```text
+observational validation R²
+observational decision agreement
+interventional correlation
+interventional mean absolute error
+interventional sign agreement
+counterfactual programme and model agreement
+```
+
+No opaque combined trust score is emitted.
+
+### Contrastive and counterfactual explanation
+
+VRAVEN explains why the selected class was preferred over its strongest alternative and can search for bounded concept-level counterfactuals. Candidates are verified by executing graph-compiled interventions in the original captured model.
+
+Internal counterfactual validity and domain validity are reported separately.
+
+### Explanation certificate
+
+Every result includes:
+
+* Validity envelope
+* Operator coverage
+* Parameter coverage
+* Gradient coverage
+* Intervention coverage
+* Validated semantic coverage
+* Association-only semantic coverage
+* Causally weighted unresolved responsibility
+* Observational fidelity
+* Interventional fidelity
+* Counterfactual evidence
+* Claim lattice
+* Known limitations
+
+## Signature scientific visualisations
+
+Each figure is standalone and supports the same scientific values in two modes:
+
+```text
+interactive_dark
+publication_light
+```
+
+| VRAVEN visual | Scientific object |
+|---|---|
+| **Raven Eye** | Full-stack model X-ray and capture coverage |
+| **Raven Flight** | Cross-layer concept genome |
+| **Raven Brain** | Bidirectional causal proof graph |
+| **Raven Code** | Executable programme proof tree |
+| **Raven Contrast** | Why the selected class defeated its alternative |
+| **Raven Shadow** | Original versus counterfactual mechanism |
+| **Raven Dark Matter** | Explained, associated, intervention-inaccessible and unresolved computation |
+
+The figures are not generic dashboards. Every node, edge, width, colour and pattern has a declared scientific meaning stored in Plotly metadata.
+
+### Trace-level Scientific Evidence Audit
+
+The standard `vraven.explain(..., mode="causal")` report now tests whether local
+activation–gradient rankings agree with measured zero-output ablations. It exposes evidence
+entropy, effective layer count, participation ratio, Gini concentration, signed cancellation,
+causal coverage, rank/sign/cosine concordance, L1 discrepancy and permutation significance as
+separate quantities. HTML reports lead with critical findings and a complete layer evidence
+ledger; no composite trust score is emitted.
+
+```python
+report = vraven.explain(model, inputs, target=1, mode="causal")
+audit = report.scientific_audit()
+report.mechanism_concordance(mode="publication_light")
+report.export_html("vraven_report.html")
+```
+
+Definitions, assumptions and validation limits are in `docs/EVIDENCE_AUDIT.md`.
+
+### Run every applicable analysis from one self-describing artefact
+
+When a model bundle contains `model.pt`, `meta.json`, `reference.npz` and optional ordered
+checkpoints, the complete research suite can be launched with the artefact directory as its
+only argument:
+
+```bash
+python scripts/run_vraven_artifact.py Models/image_pattern_cnn2d
+```
+
+The runner reconstructs the declared architecture with safe state-dictionary loading, records
+SHA-256 provenance, executes capture, decompilation, adversarial stress, Proof, Atlas, Watch,
+Compare and every scientifically applicable DarkSide analysis, then writes an indexed HTML
+gallery under `vraven_outputs/artifact_runs/`. Non-estimable analyses are recorded with their
+missing evidence contract; they are never replaced with synthetic results.
+
+## Installation
+
+### Editable development installation
+
+```bash
+python -m pip install -e ".[analysis,publication,dev]"
+vraven doctor
+```
+
+### Local wheel
+
+Build and validate the wheel:
+
+```bash
+bash scripts/build_package.sh
+python -m pip install dist/vraven-0.9.0a1-py3-none-any.whl
+```
+
+To publish later, install the standard `build` and `twine` tools, build both wheel and source distribution, test with TestPyPI, and only then upload the reviewed release to public PyPI. See `docs/PYPI_RELEASE_GUIDE.md`.
+
+This repository has not been published to the public PyPI index.
+
+## Quick Python example
+
+```python
+import torch
+import vraven
+
+model = YourModel().eval()
+reference = torch.load("reference_inputs.pt", weights_only=True)
+
+config = vraven.DecompileConfig.quick()
+
+result = vraven.reverse(
+    model,
+    (reference,),
+    focus_args=(reference[:1],),
+    target=1,
+    class_names={0: "Benign", 1: "Malware"},
+    config=config,
+)
+
+print(result.summary())
+
+result.save("vraven_decision_proof")
+result.write_report(
+    "vraven_decision_proof/report.html",
+    initial_mode="interactive_dark",
+)
+
+result.figure(
+    "causal_proof",
+    mode="publication_light",
+).write_html("causal_proof.html")
+```
+
+## Command line
+
+### Verify the environment
+
+```bash
+vraven doctor
+```
+
+### Capture an unknown state-dictionary model into Mechanism IR
+
+```bash
+vraven capture model.pt \
+  --model-factory my_project.models:Classifier \
+  --factory-kwargs '{"input_dim":476,"num_classes":2}' \
+  --input sample.npy \
+  --output mechanism_ir.json
+```
+
+### Run full decompilation
+
+```bash
+vraven reverse model.pt \
+  --model-factory my_project.models:Classifier \
+  --factory-kwargs '{"input_dim":476,"num_classes":2}' \
+  --reference reference.npy \
+  --labels labels.npy \
+  --target 1 \
+  --class-names Benign,Malware \
+  --input-groups feature_groups.json \
+  --profile standard \
+  --output-dir vraven_decision_proof
+```
+
+A `.pt` state dictionary contains weights, not an arbitrary architecture. A model factory is therefore required.
+
+### Run the planted-mechanism demonstration
+
+```bash
+vraven decompile-demo \
+  --profile quick \
+  --output-dir vraven_decompile_demo
+```
+
+## Profiles
+
+### Quick
+
+Designed for development and smoke testing. It uses deterministic PCA, bounded concept counts and smaller bootstrap budgets.
+
+### Standard
+
+Uses the default research configuration.
+
+### Publication
+
+Uses wider concept and causal searches, larger bootstrap budgets and more profiling repetitions. Publication profile does not make the result publication-ready by itself. Replication and matched baselines remain necessary.
+
+## Saved output structure
+
+```text
+vraven_decision_proof/
+├── mechanism_ir.json
+├── concept_atlas/
+├── concept_evolution.json
+├── causal_mechanism_graph.json
+├── executable_programme.json
+├── executable_programme.txt
+├── contrastive_explanation.json
+├── counterfactual_proof.json
+├── mechanism_certificate.json
+├── mechanism_profile.json
+├── decompilation_manifest.json
+└── report.html
+```
+
+## Known-mechanism benchmark
+
+The repository includes `VRAVEN-DecompileBench`, a small PyTorch-native development benchmark with planted causal concepts, distractors, inhibitory signals and redundant pathways.
+
+```bash
+python benchmarks/decompilebench.py \
+  --model planted_concept_mlp \
+  --samples 96 \
+  --output vraven_decompilebench
+```
+
+It is a development benchmark, not yet a complete community benchmark.
+
+
+## Research and PyTorch source basis
+
+The compiler design and research gap are documented in:
+
+```text
+docs/decompiler/PYTORCH_2_13_SOURCE_INDEX.md
+docs/decompiler/RESEARCH_SOURCE_INDEX.md
+docs/decompiler/IMPLEMENTATION_GAP_CLOSURE.md
+docs/decompiler/RESEARCH_POSITIONING.md
+REFERENCES.bib
+```
+
+The package records primary sources and open-access links rather than redistributing copyrighted books or publisher-controlled papers.
+
+## Scientific boundaries
+
+VRAVEN currently does not establish that:
+
+* Every PyTorch model can be fully captured
+* Every discovered latent direction has a human meaning
+* Every internal intervention corresponds to a naturally reachable state
+* The recovered programme is globally minimal or unique
+* The programme is faithful outside its validity envelope
+* The method is state of the art across architectures
+* A counterfactual is domain-valid without an application validator
+
+Unsupported operations, weak interventional fidelity and unresolved concepts are shown rather than hidden.
+
+## Documentation
+
+Start with:
+
+* `docs/decompiler/ARCHITECTURE.md`
+* `docs/decompiler/MECHANISM_IR.md`
+* `docs/decompiler/MATHEMATICAL_FOUNDATIONS.md`
+* `docs/decompiler/PYTORCH_2_13_BASIS.md`
+* `docs/decompiler/INTERVENTION_COMPILER.md`
+* `docs/decompiler/VALIDITY_CERTIFICATE.md`
+* `docs/decompiler/VISUAL_SYSTEM.md`
+* `docs/decompiler/RESEARCH_POSITIONING.md`
+* `docs/decompiler/LIMITATIONS.md`
+* `docs/decompiler/PUBLICATION_PLAN.md`
+* `docs/decompiler/QUICKSTART.md`
+
+## Security and privacy
+
+VRAVEN runs locally by default. Complete Python-pickled models are blocked unless the user explicitly enables trusted loading. Do not load untrusted pickles. Raw activations and input data are not persisted by the Mechanism IR unless a user explicitly exports them.
+
+## Licence
+
+Apache License 2.0. See `LICENSE` and `NOTICE`.