ArticleNature communications2024
Thermodynamics-inspired explanations of artificial intelligence.
Article in Nature communications, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 16 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
16 citing papers in PubMed.
- Intelligent Computing for Future Layered Cathodes in Sodium-Ion Batteries.Small (Weinheim an der Bergstrasse, Germany) · 2026Review
- A Comparative Analysis of Explainable AI (XAI) Techniques for Transparent and Reliable Image Classification.Entropy (Basel, Switzerland) · 2026Article
- Detecting and quantifying overparametrization in RNA language models with REDIAL.bioRxiv : the preprint server for biology · 2026Article
- Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications.Chemical reviews · 2026Review
- ZENN: A thermodynamics-inspired computational framework for heterogeneous data-driven modeling.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Enhanced Sampling and Free Energy Calculations in Protein Simulations.Advances in experimental medicine and biology · 2026Review
- Artificial intelligence-assisted remote sensing observation, understanding, and decision.Innovation (Cambridge (Mass.)) · 2025Review
- Information-Theoretic Cost-Benefit Analysis of Hybrid Decision Workflows in Finance.Entropy (Basel, Switzerland) · 2025Article
- A thermodynamic inspired AI based search algorithm for solving ordinary differential equations.Scientific reports · 2025Article
- AlphaFold2's training set powers its predictions of some fold-switched conformations.Protein science : a publication of the Protein Society · 2025Article
- SENSITIVITY BASED MODEL AGNOSTIC SCALABLE EXPLANATIONS OF DEEP LEARNING.bioRxiv : the preprint server for biology · 2025Article
- Machine learning in molecular biophysics: Protein allostery, multi-level free energy simulations, and lipid phase transitions.Biophysics reviews · 2025Review
- Emerging AI approaches for cancer spatial omics.GigaScience · 2025Review
- Psychiatry in the age of AI: transforming theory, practice, and medical education.Frontiers in public health · 2025Review
- A machine learning-based depression risk prediction model for healthy middle-aged and older adult people based on data from the China health and aging tracking study.Frontiers in public health · 2025Article
- AlphaFold2's training set powers its predictions of fold-switched conformations.bioRxiv : the preprint server for biology · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
Abstract
In recent years, predictive machine learning models have gained prominence across various scientific domains. However, their black-box nature necessitates establishing trust in them before accepting their predictions as accurate. One promising strategy involves employing explanation techniques that elucidate the rationale behind a model's predictions in a way that humans can understand. However, assessing the degree of human interpretability of these explanations is a nontrivial challenge. In this work, we introduce interpretation entropy as a universal solution for evaluating the human interpretability of any linear model. Using this concept and drawing inspiration from classical thermodynamics, we present Thermodynamics-inspired Explainable Representations of AI and other black-box Paradigms, a method for generating optimally human-interpretable explanations in a model-agnostic manner. We demonstrate the wide-ranging applicability of this method by explaining predictions from various black-box model architectures across diverse domains, including molecular simulations, text, and image classification.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.