Changelog

This changelog is generated automatically from GitHub Releases.

seapig - Initial Zenodo Release

2026-05-03 · GitHub

Initial Release for Zenodo. See the original release notes.

seapig v0.1.0 - Initial Release

2026-05-03 · GitHub

A lightweight library for confidence‑based selective inference for deep models. seapig provides small, composable confidence scores operating on model embeddings (or logits), calibration utilities, and a PyTorch Lightning task + torchmetrics wrapper to evaluate selective systems.

Highlights

• Fast, interpretable confidence scores based on latent representations and logits.
• Calibration on an independent validation set to fix target coverage levels.
• Select/abstain decision utilities that produce per-sample scores and binary selections.
• Seamless integration with PyTorch Lightning via SelectiveInferenceTask and torchmetrics compatibility.
• Small, dependency‑scoped core with optional extras for recommended features, docs, and development.

Main features

• Score fitting APIs:
  • Fit from pre-computed embeddings or extract embeddings on the fly from models/loaders.
  • Calibration via empirical quantiles (set_threshold(q=...)).
• Built-in scores:
  • distance-based: EuclideanScore, CosineScore, MahalanobisScore
  • logit-based: EnergyScore, EntropyScore, LogitScore, MarginScore, SoftmaxScore
  • reconstruction-based: PCAScore
  • PyOD-based: PyODScore
  • Other: RandomScore
• SelectiveInferenceTask: evaluate and predict with Lightning models while applying selective inference
• SelectiveMetric: wraps any torchmetris Metric and MetricCollection to reporting metrics for full/selected/rejected subsets.
• Utilities: progress-control, logging adapter, lightweight helper functions.

Quick install

• PyPI: pip install seapig
• Latest: pip install git+https://github.com/goergen95/seapig.git
• Extras: seapig[suggested], seapig[dev], seapig[docs]

Docs & examples

• Getting started, API reference and tutorials: www.seapig.dev

Tests, quality & license

• Tests included (pytest) and type hints present (py.typed).
• CI and coverage badges maintained in repo.
• License: MIT (see LICENSE)
• Code of conduct: .github/CODE_OF_CONDUCT

Citation

• CITATION.cff included for academic use.

Contact / contribution

• Contributions welcome — follow the repository’s contributing guidelines and run make check (formatting, linting, tests) before submitting PRs.