# Failing Conceptually: Concept-Based Explanations of Dataset Shift

arXiv: https://arxiv.org/abs/2104.08952 · HTML: https://mlsanity.com/paper/2104.08952/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 6 of 6)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [Now You See Me (CME): Concept-based Model Extraction](https://mlsanity.com/paper/2010.13233/) (2020)

## Built on by (most cited first, 7 of 7)

- [GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks](https://mlsanity.com/paper/2107.11889/) (2021)
- [ECLAD: Extracting Concepts with Local Aggregated Descriptors](https://mlsanity.com/paper/2206.04531/) (2022)
- [Algorithmic Concept-based Explainable Reasoning](https://mlsanity.com/paper/2107.07493/) (2021)
- [Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts](https://mlsanity.com/paper/2504.17921/) (2025)
- [A unified framework for dataset shift diagnostics](https://mlsanity.com/paper/2205.08340/) (2022)
- [How many classes do we need to see for novel class discovery?](https://mlsanity.com/paper/2509.15585/) (2025)
- [Learning to Detect Shifts in Unstructured Data Streams via Monitoring-by-Betting](https://mlsanity.com/paper/2610.17399/) (2026)

## Abstract (arXiv)

Despite their remarkable performance on a wide range of visual tasks, machine learning technologies often succumb to data distribution shifts. Consequently, a range of recent work explores techniques for detecting these shifts. Unfortunately, current techniques offer no explanations about what triggers the detection of shifts, thus limiting their utility to provide actionable insights. In this work, we present Concept Bottleneck Shift Detection (CBSD): a novel explainable shift detection method. CBSD provides explanations by identifying and ranking the degree to which high-level human-understandable concepts are affected by shifts. Using two case studies (dSprites and 3dshapes), we demonstrate how CBSD can accurately detect underlying concepts that are affected by shifts and achieve higher detection accuracy compared to state-of-the-art shift detection methods.