On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “misattribution”

Common Functional Decompositions Can Mis-attribute Differences in Outcomes Between Populationsstat.ME

New decompositions misattribute differences between populations, even when outcomes are identical.

problem Misattribution of differences between populations using common functional decompositions.

method Extending the Kitagawa-Oaxaca-Blinder decomposition to nonlinear functional decompositions.

result Functional ANOVA and Accumulated Local Effects can misattribute differences even when outcomes are identical in two populations.

functional decomposition Kitagawa-Oaxaca-Blinder misattribution nonlinear machine learning

2025-04-23abs ↗pdf ↗

MISA: Online Defense of Trojaned Models using Misattributionscs.CR

MISA detects Trojan triggers in neural networks at inference time.

problem Trojan attacks on neural networks that respond to specific trigger patterns.

method MISA uses misattributions to detect anomalous feature activations.

result MISA achieves 96% AUC in detecting Trojan triggers without assumptions.

Trojan attacks Neural networks Feature attribution Anomaly detection Online defense

2021-03-29abs ↗pdf ↗

DCD: Decomposition-based Causal Discovery from Autocorrelated and Non-Stationary Temporal Datacs.LG

Framework isolates causal effects from time series data, improving accuracy under non-stationarity and autocorrelation.

problem Causal inference in non-stationary, autocorrelated time series data.

method Decomposes time series into trend, seasonal, and residual components; performs component-specific causal analysis.

result Framework more accurately recovers ground-truth causal structure than state-of-the-art baselines, especially under strong non-stationarity and temporal autocorrelation.

causal discovery time series analysis non-stationary data autocorrelation seasonality

2026-02-01abs ↗pdf ↗

Deep Learning using Rectified Linear Units (ReLU)cs.NE

The Rectified Linear Unit (ReLU) is a foundational activation function in artficial neural networks. Recent literature frequently misattributes its origin to the 2018 (initial) version of this paper, which exclusively investigated ReLU at the classification layer. This paper formally corrects the citation record by tra…

2018-03-22abs ↗pdf ↗

Using the Path of Least Resistance to Explain Deep Networkscs.LG

Proposes Geodesic Integrated Gradients (GIG) for more accurate feature attributions in deep networks.

problem Flawed attributions using straight paths from Integrated Gradients (IG).

method Introduces a model-induced Riemannian metric and computes attributions along geodesics.

result GIG produces more faithful attributions than IG on benchmarks.

Integrated Gradients Geodesic Integrated Gradients Path-based attributions Deep networks Feature importance

2025-02-17abs ↗pdf ↗

Theoretical Behavior of XAI Methods in the Presence of Suppressor Variablescs.LG

XAI methods often misattribute importance to suppressor variables, limiting their reliability.

problem XAI methods lack theoretical and empirical evidence for the correctness of their explanations.

method Analytical expressions for XAI methods on a simple binary classification problem.

result XAI methods will often attribute non-zero importance to non-class-related suppressor features.

explainable artificial intelligence XAI suppressor variables interpretability binary classification

2023-06-02abs ↗pdf ↗