AbductiveLearning/ABLkit
An efficient Python toolkit for Abductive Learning (ABL), a novel paradigm that integrates machine learning and logical reasoning in a unified framework.
Supports pluggable knowledge bases including Prolog-based reasoning engines, with a unified wrapper architecture that bridges instance-level ML models (scikit-learn or PyTorch) to example-level ABL tasks. The framework provides built-in evaluation metrics (`SymbolAccuracy`, `ReasoningMetric`) and uses a consistency-minimization approach to resolve ambiguities in abductive reasoning over multiple candidate pseudo-labels.
Available on PyPI.
Stars
86
Forks
8
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AbductiveLearning/ABLkit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
msinamsina/AI-Graph
A powerful and flexible AI Graph framework for building processing pipelines and state machines
PeterOvermann/TriadicMemory
Cognitive Computing with Associative Memory
zenoxml/SciREX
SciREX is an open-source scientific AI and machine learning framework designed for researchers...
jacobphillips99/ares
ARES - Automatic Robot Evaluation System. A simple, scalable solution for robotics research
Neo-Cybernetics/Neo-Cybernetics-Main
Official Github Repository for Neo-Cybernetics, a discipline that introduces a holistic paradigm...