# Process-Guided Concept Bottleneck Model

arXiv: https://arxiv.org/abs/2601.10562 · HTML: https://mlsanity.com/paper/2601.10562/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 84 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Interventional Causal Representation Learning](https://mlsanity.com/paper/2209.11924/) (2022)
- [Do Concept Bottleneck Models Learn as Intended?](https://mlsanity.com/paper/2105.04289/) (2021)
- [Probabilistic Concept Bottleneck Models](https://mlsanity.com/paper/2306.01574/) (2023)
- [A high-resolution canopy height model of the Earth](https://mlsanity.com/paper/2204.08322/) (2022)
- [Foundation Models for Remote Sensing and Earth Observation: A Survey](https://mlsanity.com/paper/2410.16602/) (2024)
- [Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles](https://mlsanity.com/paper/2001.11086/) (2020)
- [Stochastic Concept Bottleneck Models](https://mlsanity.com/paper/2406.19272/) (2024)
- [Semantic Segmentation of Remote Sensing Images with Sparse Annotations](https://mlsanity.com/paper/2101.03492/) (2021)
- [Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward](https://mlsanity.com/paper/2305.08413/) (2023)
- [Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?](https://mlsanity.com/paper/2401.13544/) (2024)
- [Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles](https://mlsanity.com/paper/2103.03975/) (2021)
- [On Rademacher Complexity-based Generalization Bounds for Deep Learning](https://mlsanity.com/paper/2208.04284/) (2022)
- [Unified Deep Learning Model for Global Prediction of Aboveground Biomass, Canopy Height and Cover from High-Resolution, Multi-Sensor Satellite Imagery](https://mlsanity.com/paper/2408.11234/) (2024)

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

- [OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting](https://mlsanity.com/paper/2605.12639/) (2026)
- [StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels](https://mlsanity.com/paper/2605.19931/) (2026)

## Abstract (arXiv)

Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their dependence on complete concept labels limits applicability in scientific domains where supervision is sparse but processes are well defined. To address this, we propose the Process-Guided Concept Bottleneck Model (PG-CBM), an extension of CBMs which constrains learning to follow domain-defined causal mechanisms through biophysically meaningful intermediate concepts. Using above ground biomass density estimation from Earth Observation data as a case study, we show that PG-CBM reduces error and bias compared to multiple benchmarks, whilst leveraging multi-source heterogeneous training data and producing interpretable intermediate outputs. Beyond improved accuracy, PG-CBM enhances transparency, enables detection of spurious learning, and provides scientific insights, representing a step toward more trustworthy AI systems in scientific applications.