cat-cog
Cognitive assessment and visual scoring powered by LLMs.
cat-cog provides LLM-powered evaluation of hand-drawn images for neuropsychological testing. It builds on cat-stack, the shared classification engine for the CatLLM ecosystem.
Installation
pip install cat-cog
This automatically installs cat-stack (the LLM classification engine).
CERAD Constructional Praxis Scoring
Score hand-drawn shapes (circle, diamond, overlapping rectangles, cube) using LLM vision models. The function sends images to the LLM, classifies drawing features, then applies CERAD scoring rules.
from catcog import cerad_drawn_score
# Score circle drawings (max score: 2)
results = cerad_drawn_score(
shape="circle",
image_input="./circle_drawings/",
api_key=OPENAI_KEY,
user_model="gpt-4o",
)
print(results[["image_file", "score"]])
Supported shapes
| Shape | Max Score | Features Assessed |
|---|---|---|
| circle | 2 | Closure, circularity |
| diamond | 3 | 4 sides, equal sides, resemblance |
| rectangles | 2 | Overlap, crossing pattern |
| cube | 4 | Front face, internal lines, parallel faces, 3D quality |
Using with multiple models
All catstack.classify() parameters are available via **kwargs:
results = cerad_drawn_score(
shape="cube",
image_input="./cube_drawings/",
api_key=OPENAI_KEY,
models=[
("gpt-4o", "openai", OPENAI_KEY),
("claude-sonnet-4-20250514", "anthropic", ANTHROPIC_KEY),
],
)
Future
- Fine-tuned vision models for shape quality assessment (circle classifier, etc.)
- Additional cognitive screening instruments (clock drawing tests, etc.)
Ecosystem
| Package | Domain |
|---|---|
| cat-stack | General-purpose classification engine (base) |
| cat-cog | Cognitive assessment & visual scoring (this package) |
| cat-survey | Survey response classification |
| cat-vader | Social media text |
| cat-ademic | Academic papers & PDFs |
| cat-pol | Political text |
License
GPL-3.0-or-later
Metadata
Release files for cat-cog 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| cat_cog-0.2.1.tar.gz | 17.2 kB | Without provenance | Details for cat_cog-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| cat_cog-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for cat_cog-0.2.1-py3-none-any.whl |
Total release size: 35.4 kB
Release files / cat_cog-0.2.1.tar.gz
| Download URL | cat_cog-0.2.1.tar.gz |
|---|---|
| Size | 17.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3499539454b397fe7f99e6f846ca2dffc7ea2a6d47d97624a9244d43b89c63ee
|
|
BLAKE2b-256 checksum How to use checksums |
fc6f1d826773490e329193add0a0f3e9dfcc8a4747c41d59dc05a3823dcbf546
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.14
|
Release files / cat_cog-0.2.1-py3-none-any.whl
| Download URL | cat_cog-0.2.1-py3-none-any.whl |
|---|---|
| Size | 18.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ce0ad63e24c84f77bac5aa24b3eec526a83afeaaf01955ab0511b14f098eb776
|
|
BLAKE2b-256 checksum How to use checksums |
49114e2d272d9dcb5bf8e5bba2c35df114a8e0cadd742f5718d0f68e82cc6b9e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.14
|
Security for cat-cog 0.2.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.