Glassbox AI — Mechanistic Interpretability for EU AI Act Compliance
====================================================================

Copyright (C) 2026 Ajay Pravin Mahale <mahale.ajay01@gmail.com>
All rights reserved.

DUAL LICENSE NOTICE
-------------------

This software is distributed under a dual-license model:

  1. MIT License (see LICENSE)
     Applies to the core attribution engine and utilities:
       glassbox/core.py
       glassbox/composition.py
       glassbox/sae_attribution.py
       glassbox/telemetry.py
       glassbox/types.py
       glassbox/utils.py
       glassbox/cli.py
       glassbox/widget.py
       glassbox/audit.py
       glassbox/__init__.py

  2. Business Source License 1.1 (see LICENSE-COMMERCIAL)
     Applies to the commercial compliance engine:
       glassbox/compliance.py       — EU AI Act Annex IV report generation
       glassbox/circuit_diff.py     — CircuitDiff mechanistic diff (Article 72)
       glassbox/risk_register.py    — Persistent risk tracking (Article 9)
       glassbox/bias.py             — Bias/fairness analysis (Articles 10, 15)
       glassbox/audit_log.py        — Tamper-evident audit chain

     BSL Summary: Free for non-commercial and internal production use.
     Commercial redistribution or SaaS use requires a separate license.
     Contact: mahale.ajay01@gmail.com

THIRD-PARTY COMPONENTS
-----------------------

This software builds upon the following open-source works:

  TransformerLens
    Author: Neel Nanda and contributors
    License: MIT
    URL: https://github.com/neelnanda-io/TransformerLens

  PyTorch
    Copyright (c) Facebook, Inc. (Meta Platforms, Inc.) and its affiliates.
    License: BSD-3-Clause (with additional terms)
    URL: https://pytorch.org

ACADEMIC ATTRIBUTION
---------------------

If you use Glassbox AI in academic research, please cite:

  Mahale, A. P. (2026). Glassbox: Causal Circuit Analysis for EU AI Act
  Annex IV Technical Documentation. ICML 2026.

  Wang, K., et al. (2022). Interpretability in the Wild: a Circuit for
  Indirect Object Identification in GPT-2 small. arXiv:2211.00593.

  Nanda, N., et al. (2023). Attribution Patching: Activation Patching At
  Industrial Scale. arXiv:2310.10348.

PATENT NOTICE
--------------
See PATENTS.md for patent-pending disclosures relating to methods
implemented in this software.
