factor interpretation

This study addresses a critical limitation in traditional reproducible research, where sharing only code and results fails to expose the implicit assumptions, expectations, and premises underlying an analyst’s reasoning—thereby hindering thorough evaluation of analytical quality. To overcome this, the paper proposes a formal modeling framework that explicitly translates the analyst’s tacit reasoning process into structured logical representations, statically capturing the construction logic of the analysis. This approach enables systematic scrutiny of the analytical chain of reasoning, assumption sensitivity, and conclusion robustness—even in the absence of the original data. Empirical validation on representative data analysis tasks demonstrates the framework’s effectiveness, achieving both logical visualization and data-free static assessment of analytical integrity.

Factor interpretability in Exploratory Factor Analysis (EFA) lacks quantifiable criteria and effective guidance mechanisms. Method: We propose PrioriMax, a novel differentiable pairwise target rotation framework that supports the seamless incorporation of arbitrary prior knowledge—such as semantic constraints—thereby overcoming the rigidity of conventional orthogonal or oblique rotations in interpretability control. PrioriMax jointly optimizes matrix rotation and differentiable factor loading reconstruction to maximize a newly defined interpretability objective. An open-source Python package, *interpretablefa*, enables plug-and-play deployment. Results: Evaluated on the Experiences in Close Relationships (ECR) scale, PrioriMax significantly improves semantic consistency of extracted factors and boosts researchers’ interpretation accuracy by 23.6%. Our core contribution is the establishment of a computable, intervenable, and generalizable paradigm for factor interpretability in EFA.

This study investigates key factors influencing analysts’ ability to identify domain elements—concepts, processes, and requirements—during requirements elicitation, focusing on their “visibility”: the degree to which such elements are accurately recognized and articulated. Employing 14 controlled experiments with 134 participants across two distinct problem domains, the research quantitatively analyzes visibility determinants. Results reveal that verbal rehearsal significantly enhances visibility, exposing a systematic gap between knowledge reportability and actual domain understanding; domain complexity, element criticality, and interview script design also exert significant effects, whereas analyst experience and client interaction intensity do not. Critically, this work provides the first empirical evidence that information presentation modality—particularly feedback modality—is the dominant determinant of visibility. These findings offer foundational theoretical insights and methodological guidance for improving requirements elicitation practices and requirements documentation quality.

Current AI interpretability methods are fragmented and lack a unified theoretical foundation. Method: This paper proposes the first unified analytical framework spanning three attribution paradigms—feature-, data-, and model-component-level attribution. By rigorously establishing the mathematical equivalence among perturbation analysis, gradient backpropagation, and linear approximations (e.g., Taylor expansions), it reveals their shared underlying mechanism: local sensitivity modeling. Contribution/Results: The framework standardizes terminology, aligns conceptual definitions, and unifies evaluation criteria—thereby significantly enhancing method interpretability, transferability, and reusability. It lowers entry barriers for newcomers while enabling advanced applications such as model editing, controllable steering, and AI governance. As a foundational contribution, it provides both theoretical grounding and practical scaffolding for next-generation interpretable AI systems.

This study addresses the limitations of traditional linear dynamic factor models under nonlinear, non-Gaussian, and small-sample conditions. It proposes a novel nonlinear dynamic factor model by integrating the Transformer architecture into dynamic factor analysis. To enhance estimation stability in small samples, the approach incorporates a conventional factor model as a prior regularizer. The model leverages attention mechanisms to capture the time-varying contributions of individual variables and their lags to latent factors, thereby enabling the identification of economic regime shifts. Empirical results demonstrate that the proposed framework substantially outperforms standard methods in settings that deviate from linearity and Gaussianity, and it successfully constructs a coincident index of U.S. real economic activity.

This study addresses the limited real-world impact of current explainability research, which often fails to support actionable decision-making and interventions in practical settings. To bridge this gap, the work proposes a novel, systematic redefinition of explainability centered on "actionability," articulated through two key dimensions: concreteness and verifiability. Building upon this reconceptualization, the authors develop an application-oriented evaluation framework grounded in both conceptual analysis and cross-domain use cases. Through this integrative approach, they identify five distinct domains with high potential for impactful deployment. By prioritizing tangible outcomes over abstract interpretability, the proposed framework offers both theoretical grounding and practical pathways to enhance the real-world relevance and effectiveness of explainable AI research.

Existing feature attribution methods struggle to characterize how attention mechanisms in intermediate Transformer layers propagate and combine feature information. This work proposes an “internal interpretability” framework that, for the first time, introduces Doeblin–Dobrushin contraction theory into attention analysis by modeling attention rollout as a row-stochastic operator and establishing its quantitative relationship with rank-one matrices, thereby endowing the propagation process with a rigorous mathematical interpretation. Experiments on a metabolomic age-prediction Transformer reveal that rollout contractivity intensifies with network depth, and trained models exhibit markedly different propagation profiles compared to randomly initialized ones. Although the method shows local agreement with PCA and GradientExplainer on top-ranked features, overall ranking correlations remain weak.

This study addresses the challenge of limited interpretability in machine learning models within manufacturing contexts, where opaque predictions often hinder effective decision-making. To bridge this gap, the authors propose a novel paradigm that leverages large language models to dynamically retrieve relevant triples from domain-specific knowledge graphs, thereby structurally linking expert knowledge with model predictions and generating user-friendly natural language explanations. Integrating knowledge graphs, large language models, and explainable artificial intelligence (XAI), the approach was evaluated on 33 manufacturing-related tasks. Results demonstrate superior performance across both quantitative metrics—such as accuracy and consistency—and qualitative dimensions, including clarity and practical utility, significantly enhancing model interpretability and decision support capabilities in real-world industrial settings.

This study addresses the longstanding challenge of treating machine learning interpretability as a non-functional requirement lacking quantifiable metrics and validation mechanisms. To bridge this gap, the work proposes an innovative approach that reframes interpretability as a verifiable functional requirement through the integration of data and model provenance. By synergizing principles from requirements engineering and machine learning engineering, the authors develop a systematic and operational verification framework. This framework enables, for the first time, the explicit specification and empirical validation of interpretability requirements, thereby substantially enhancing the engineering rigor and trustworthiness of machine learning system development.

Existing model explanation methods often suffer from attribution bias or even erroneous interpretations due to inadequate consideration of baseline selection. This work reformulates the model explanation task by unifying gradient-based methods, Integrated Gradients (IG), and Taylor expansion approaches, thereby systematically revealing— for the first time—the pivotal role of the baseline in attribution. Building on this insight, the authors propose an evaluation framework grounded in attribution error and develop a general-purpose explanation method with a well-defined, principled baseline that supports feature attribution at arbitrary network layers. The refined IG variant significantly improves explanation accuracy across multiple benchmarks, and attributions derived from different layers coherently reflect the hierarchical nature of feature extraction in deep networks.