# Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping

arXiv: https://arxiv.org/abs/2505.13182 · HTML: https://mlsanity.com/paper/2505.13182/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 63 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 26 of 26)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [High-dimensional dynamics of generalization error in neural networks](https://mlsanity.com/paper/1710.03667/) (2017)
- [User-friendly introduction to PAC-Bayes bounds](https://mlsanity.com/paper/2110.11216/) (2021)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [The Ethics of AI Ethics -- An Evaluation of Guidelines](https://mlsanity.com/paper/1903.03425/) (2019)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [Convergence Analysis of Probability Flow ODE for Score-based Generative Models](https://mlsanity.com/paper/2404.09730/) (2024)
- [Tighter expected generalization error bounds via Wasserstein distance](https://mlsanity.com/paper/2101.09315/) (2021)
- [Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)](https://mlsanity.com/paper/2102.01564/) (2021)
- [Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability](https://mlsanity.com/paper/2307.07873/) (2023)
- [Worldwide AI Ethics: a review of 200 guidelines and recommendations for AI governance](https://mlsanity.com/paper/2206.11922/) (2022)
- [An Information Theoretic Interpretation to Deep Neural Networks](https://mlsanity.com/paper/1905.06600/) (2019)
- [Management of Machine Learning Lifecycle Artifacts: A Survey](https://mlsanity.com/paper/2210.11831/) (2022)
- [The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms](https://mlsanity.com/paper/2411.12030/) (2024)
- [A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges](https://mlsanity.com/paper/2306.15890/) (2023)
- [General Information Metrics for Improving AI Model Training Efficiency](https://mlsanity.com/paper/2501.02004/) (2025)
- [Ethics in AI through the Practitioner's View: A Grounded Theory Literature Review](https://mlsanity.com/paper/2206.09514/) (2022)

## Built on by (most cited first, 2 of 2)

- [Spontaneous High-Order Generalization in Neural Theory-of-Mind Networks](https://mlsanity.com/paper/2509.25343/) (2025)
- [Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints](https://mlsanity.com/paper/2511.19156/) (2025)

## Abstract (arXiv)

This paper addresses the current lack of a unified formal framework in machine learning theory, as well as the absence of robust theoretical foundations for interpretability and ethical safety assurance. We first construct a formal information model, employing sets of well-formed formulas (WFFs) to explicitly define the ontological states and carrier mappings for the core components of machine learning. By introducing learnable and processable predicates, as well as learning and processing functions, we analyze the logical inference and constraint rules underlying causal chains in models, thereby establishing the Machine Learning Theory Meta-Framework (MLT-MF). Building upon this framework, we propose universal definitions for model interpretability and ethical safety, and rigorously prove and validate four key theorems: the equivalence between model interpretability and information existence, the constructive formulation of ethical safety assurance and two types of total variation distance (TVD) upper bounds. This work overcomes the limitations of previous fragmented approaches, providing a unified theoretical foundation from an information science perspective to systematically address the critical challenges currently facing machine learning.