mi-crow 1.0.0.post9__tar.gz → 1.0.0.post10__tar.gz

{mi_crow-1.0.0.post9 → mi_crow-1.0.0.post10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mi-crow
-Version: 1.0.0.post9
+Version: 1.0.0.post10
 Summary: Python library for mechanistic interpretability research on Large Language Models. Designed for researchers, provides unified interface for SAE training, activation hooks, and concept manipulation.
 Author: Hubert Kowalski
 Author-email: Adam Kaniasty <adam.kaniasty@gmail.com>
@@ -61,6 +61,15 @@ Requires-Dist: mike>=2.1; extra == "docs"
 - **Hierarchical Data Persistence** - Efficient storage and management of large-scale experiment data
 - **Research Focused** - Comprehensive testing (85%+ coverage), extensive documentation, and designed for interpretability research workflows
 
+## Acknowledgements
+This project was developed as part of an engineering thesis at the Faculty of Mathematics and Information Science, Warsaw University of Technology (WUT).
+
+We extend our sincere gratitude to our thesis supervisors:
+- **mgr inż. Vladimir Zaigrajew**
+- **prof. dr hab. inż. Przemysław Biecek**
+
+for their invaluable guidance, insightful feedback, and continuous support throughout the course of this work.
+
 ## Installation
 
 ### Install from PyPI
@@ -257,10 +266,6 @@ See the main repository for license information: [Mi-Crow License](https://githu
 - **Email**: adam.kaniasty@gmail.com
 - **GitHub**: [@AdamKaniasty](https://github.com/AdamKaniasty)
 
-## Acknowledgments
-
-This work was developed in collaboration with the **Bielik** team and represents a contribution to the open-source mechanistic interpretability community.
-
 ---
 
 ## Backend (FastAPI) quickstart

{mi_crow-1.0.0.post9 → mi_crow-1.0.0.post10}/README.md

@@ -19,6 +19,15 @@
 - **Hierarchical Data Persistence** - Efficient storage and management of large-scale experiment data
 - **Research Focused** - Comprehensive testing (85%+ coverage), extensive documentation, and designed for interpretability research workflows
 
+## Acknowledgements
+This project was developed as part of an engineering thesis at the Faculty of Mathematics and Information Science, Warsaw University of Technology (WUT).
+
+We extend our sincere gratitude to our thesis supervisors:
+- **mgr inż. Vladimir Zaigrajew**
+- **prof. dr hab. inż. Przemysław Biecek**
+
+for their invaluable guidance, insightful feedback, and continuous support throughout the course of this work.
+
 ## Installation
 
 ### Install from PyPI
@@ -215,10 +224,6 @@ See the main repository for license information: [Mi-Crow License](https://githu
 - **Email**: adam.kaniasty@gmail.com
 - **GitHub**: [@AdamKaniasty](https://github.com/AdamKaniasty)
 
-## Acknowledgments
-
-This work was developed in collaboration with the **Bielik** team and represents a contribution to the open-source mechanistic interpretability community.
-
 ---
 
 ## Backend (FastAPI) quickstart
@@ -265,4 +270,4 @@ uv run --group server pytest tests/server/test_api.py --cov=server --cov-fail-un
 Notes:
 - Job manager is in-memory/lightweight: jobs disappear on process restart; idempotency is best-effort via payload key.
 - Training/inference currently run in-process threads; add your own resource guards when running heavy models.
-- Optional API key protection: set `SERVER_API_KEY=<value>` to require `X-API-Key` on protected endpoints (delete).
+- Optional API key protection: set `SERVER_API_KEY=<value>` to require `X-API-Key` on protected endpoints (delete).

{mi_crow-1.0.0.post9 → mi_crow-1.0.0.post10}/src/mi_crow.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mi-crow
-Version: 1.0.0.post9
+Version: 1.0.0.post10
 Summary: Python library for mechanistic interpretability research on Large Language Models. Designed for researchers, provides unified interface for SAE training, activation hooks, and concept manipulation.
 Author: Hubert Kowalski
 Author-email: Adam Kaniasty <adam.kaniasty@gmail.com>
@@ -61,6 +61,15 @@ Requires-Dist: mike>=2.1; extra == "docs"
 - **Hierarchical Data Persistence** - Efficient storage and management of large-scale experiment data
 - **Research Focused** - Comprehensive testing (85%+ coverage), extensive documentation, and designed for interpretability research workflows
 
+## Acknowledgements
+This project was developed as part of an engineering thesis at the Faculty of Mathematics and Information Science, Warsaw University of Technology (WUT).
+
+We extend our sincere gratitude to our thesis supervisors:
+- **mgr inż. Vladimir Zaigrajew**
+- **prof. dr hab. inż. Przemysław Biecek**
+
+for their invaluable guidance, insightful feedback, and continuous support throughout the course of this work.
+
 ## Installation
 
 ### Install from PyPI
@@ -257,10 +266,6 @@ See the main repository for license information: [Mi-Crow License](https://githu
 - **Email**: adam.kaniasty@gmail.com
 - **GitHub**: [@AdamKaniasty](https://github.com/AdamKaniasty)
 
-## Acknowledgments
-
-This work was developed in collaboration with the **Bielik** team and represents a contribution to the open-source mechanistic interpretability community.
-
 ---
 
 ## Backend (FastAPI) quickstart