Shesha Logo

Shesha

Pronunciation: SHAY-shuh (/ˈʃeɪʃə/)

Self-consistency metrics for representational stability analysis.

Shesha measures the geometric stability of high-dimensional representations by quantifying the self-consistency of their pairwise distance structure (RDMs) under controlled internal perturbations.

Full documentation at shesha-geometry.readthedocs.io

Installation

pip install shesha-geometry

For single-cell biology workflows (shesha.bio), install with the bio extra, which adds anndata and scikit-learn:

pip install shesha-geometry[bio]

Quick Start

import numpy as np
import shesha

X = np.random.randn(500, 768)  # (n_samples, n_features)

stability = shesha.feature_split(X, n_splits=30, seed=320)
print(f"Feature-split stability: {stability:.3f}")

For the full API reference, installation guide, and usage examples, see the documentation.

Tutorials

Explore shesha with these interactive notebooks (most take < 5 minutes; the vision tutorial is longer because it loads several pretrained models):

LLM Embeddings - Analyze embedding stability across layers and models using feature_split.
Steering Vectors - Compute steering vectors from contrastive pairs and measure their consistency.
Vision Models - Compare geometric stability across ResNets, ViTs, and other architectures.
Representational Drift - Measure drift from Gaussian noise injection and LoRA fine-tuning.
Training Dynamics - Track geometric stability during training to detect representation collapse.
CRISPR (Bio) - Use shesha.bio to analyze coherence in single-cell CRISPR perturbation experiments.

Citation

If you use shesha-geometry, please cite:

@software{shesha2026,
  title = {Shesha: Self-Consistency Metrics for Representational Stability},
  author = {Raju, Prashant C.},
  year = {2026},
  howpublished = {Zenodo},
  doi = {10.5281/zenodo.18227453},
  url = {https://doi.org/10.5281/zenodo.18227453},
  copyright = {MIT License}
}

@article{raju2026geometric,
  title = {Geometric Stability: The Missing Axis of Representations},
  author = {Raju, Prashant C.},
  journal = {arXiv preprint arXiv:2601.09173},
  year = {2026}
}

If you use the supervised variants (supervised_alignment, lda_stability, variance_ratio, class_separation_ratio), please also cite:

@inproceedings{raju2026canary,
  title = {The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability},
  author = {Raju, Prashant C.},
  booktitle= {ICML Mechanistic Interpretability Workshop},
  year= {2026}
}

If you use the shesha.bio module, please also cite:

@article{raju2026crispr,
  title = {Directional coherence and effect magnitude in single-cell CRISPR perturbation responses},
  author = {Raju, Prashant C.},
  journal = {arXiv preprint arXiv:2604.16642},
  year = {2026}
}

License

MIT

_{Logo generated by Nano Banana Pro}

shesha geometry representation learning representation analysis representational geometry representational similarity analysis neural networks geometric stability geometric analysis manifold analysis model evaluation latent space single-cell crispr perturb-seq anndata functional genomics phenotypic coherence computational biology scanpy llm alignment concept drift model steering ai safety interpretability perturbation analysis

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

shesha_geometry-0.2.28.tar.gz (49.3 kB view details)

Uploaded Sep 5, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

shesha_geometry-0.2.28-py3-none-any.whl (54.2 kB view details)

Uploaded Sep 5, 2026 Python 3

File details

Details for the file shesha_geometry-0.2.28.tar.gz.

File metadata

Download URL: shesha_geometry-0.2.28.tar.gz
Upload date: Sep 5, 2026
Size: 49.3 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for shesha_geometry-0.2.28.tar.gz
Algorithm	Hash digest
SHA256	`3ae2dd3d722e44ebd8caec488f948c34771890e02d5cf9b744279a5b142dc169`
MD5	`b24c261284c7115642f566b0c0ad51ad`
BLAKE2b-256	`a47809a6d7d54caac6e9f5dc04084d38edec64788e9ee6092ce0f728eb9f2330`

See more details on using hashes here.

File details

Details for the file shesha_geometry-0.2.28-py3-none-any.whl.

File metadata

Download URL: shesha_geometry-0.2.28-py3-none-any.whl
Upload date: Sep 5, 2026
Size: 54.2 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for shesha_geometry-0.2.28-py3-none-any.whl
Algorithm	Hash digest
SHA256	`5819cd9897a3b6fa2a35fa8bce8443d1fde4722bf51258a470a4d0317d4e6bc3`
MD5	`e67b457747c43682980c226dfb01dead`
BLAKE2b-256	`9a531e9ff82bde13c78d08cfa530d12eb6ea81f12df4b9dd4fb1c867d4768d0d`