Search research

EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural networks the technical means to provide such evidence remain an open problem. We address this gap for a vision-based aircraft landing system: we propose that a minimally assurable model must at least be shown to separate content from style in its own situation representation. Showing that the model's predictions then rely largely on the contentful representation components leads to a concrete assurance path. To demonstrate this assurance path on a concrete model we train a vision transformer model for runway keypoint regression on the LARDv2 dataset. The model, which acts as the subject for our assurance demonstration, produces per-patch embeddings that we decompose into interpretable atoms via K-SVD sparse dictionary learning. A qualitative visualization confirms that contentful atoms track task-relevant runway structure and stylistic atoms track domain-specific appearance, and the regression head is shown to place almost all of its linear weight on contentful atoms. We further build on the content/style separation and define out-of-model-scope (OOMS) detection, a novel runtime assurance approach directly monitoring the model's situation representation. OOMS monitoring is complementary to operational design domain and output-space out-of-distribution monitoring and addresses concrete requirements of the recent EASA guidance. By directly analyzing a model's situation representation both at test time and runtime, this work delivers the first concrete piece of the representation-level evidence that EASA learning-assurance guidance demands, and points to mechanistic interpretability as a practical building block of future aviation safety cases.

Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability remains limited, as most TGNNs fail to identify which historical interactions most influence a given prediction. Despite promising progress on interpretable TGNNs, existing methods predominantly focus on previously seen historical interactions, which we term stability patterns, while overlooking newly emerging first-time interactions, which we term transition patterns. Both types of patterns are essential for faithful temporal explanations. To address this limitation, we propose ST-TGExplainer, a self-explainable TGNN that disentangles Stability and Transition patterns in temporal graphs for a more faithful Temporal GNN Explainer. Guided by a disentangled information bottleneck objective, ST-TGExplainer learns a compact explanatory subgraph that remains predictive of the event label while explicitly suppressing label-conditioned redundancy between stability and transition patterns. Extensive experiments demonstrate that ST-TGExplainer achieves strong predictive performance and yields more faithful explanations. Code is available at https://github.com/hjchen-hdu/ST-TGExplainer.

Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical drivers. While recent machine learning approaches achieve strong predictive skill, they remain largely opaque and provide limited guarantees of fidelity to ground-truth physics. We introduce OceanCBM, the first concept bottleneck model (CBM) for spatiotemporal prediction and mechanistic interrogation of ocean dynamics. OceanCBM uses mixed supervision to predict mixed layer heat content, a key precursor of marine heatwaves, while routing information through an intermediate layer of prescribed concepts derived from geophysical fluid dynamics and a 'free' concept. This design imposes soft physical structure without over-constraining the model, and the free concept both regularizes concept predictions and captures residual physical processes. Across ensemble initializations, we show that mixed supervision yields consistent mechanistic representations, whereas prediction-only and prescription-only baselines learn highly variable latent structures despite similar predictive performance. OceanCBM achieves interpretable, physically grounded representations without sacrificing skill, explicitly characterizing the interpretability-performance trade-off.

AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because these tool-use decisions are difficult to diagnose and control. Agents may skip required tool calls, invoke tools unnecessarily, or take actions whose consequences become visible only after execution. Existing observability methods are external: prompts reveal correlations, evaluations score outputs, and logs arrive only after the model has already acted. In long-horizon settings, these failures are costly because an early tool mistake can alter the rest of the execution trajectory, increase token consumption, and create downstream safety and security risk. We introduce a mechanistic-interpretability toolkit built on Sparse Autoencoders (SAEs), which decompose activations into sparse internal features, and linear probes, lightweight classifiers that read signals from those features. The framework reads model states before each action and infers whether a tool is needed and how risky the next tool action is. It identifies the model layers and features most associated with tool decisions and tests their functional importance through feature ablation. We train the probes on multi-step agent execution traces from the NVIDIA Nemotron function-calling dataset and apply the same workflow to GPT-OSS 20B and Gemma 3 27B models. The goal is not to replace external evaluation, but to add a missing layer: visibility into what the model signaled internally before action. This helps surface deeper causes of agent failure, especially in long-horizon runs where an early mistake can impact subsequent agent behavior. More broadly, the paper shows how mechanistic interpretability can support internal observability for monitoring tool calls and risk in agent systems.

We introduce the metagame, a conceptual framework for quantifying second-order interaction effects of model explanations. For any first-order attribution $φ(f)$ explaining a model $f$, we measure the directional influence of feature $j$ on the attribution of feature $i$, denoted as meta-attribution $\varphi_{j \to i}(f)$, by treating the attribution method itself as a cooperative game and computing its Shapley value. Theoretically, we prove that attributions hierarchically decompose into meta-attributions, and establish these as directional extensions of existing interaction indices. Empirically, we demonstrate that the metagame delivers insights across diverse interpretability applications: (i) quantifying token interactions in instruction-tuned language models, (ii) explaining cross-modal similarity in vision-language encoders, and (iii) interpreting text-to-image concepts in multimodal diffusion transformers.

We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system runs two coupled loops: (1) explanation refinement, where an agent proposes competing hypotheses and iteratively tests them with targeted prompt controls and a multi-metric evaluation; and (2) feature discovery, where an agent generates prompt sets, constructs a k-nearest-neighbor graph in activation space, and retrieves candidate features using statistical separability and semantic coherence criteria. On Gemma-2 family models and MLP neurons in weight-sparse transformers, our agent improves over one-shot auto-interpretations, discovers language-specific and safety-relevant features, and produces auditable explanation traces, showing that agent-driven empirical loops yield sharper and more falsifiable explanations than one-shot labels.

Every RLHF-trained language model is shaped by a reward model, yet the mechanistic interpretability toolkit -- logit lens, direct logit attribution, activation patching, sparse autoencoders -- was built for generative LLMs whose primitives all project onto a vocabulary unembedding. Reward models replace that with a scalar regression head, breaking each tool. We present reward-lens, an open-source library that ports this toolkit to reward models, organised around one observation: the reward head's weight vector $w_r$ is the natural axis for every interpretability question. The library provides a Reward Lens, component attribution, three-mode activation patching, a reward-hacking probe suite, TopK SAE feature attribution, cross-model comparison, and five theory-grounded extensions (distortion index, divergence-aware patching, misalignment cascade detection, reward-term conflict analysis, concept-vector analysis). A ten-method adapter protocol covers Llama, Mistral, Gemma-2, and ArmoRM multi-objective heads, with a generic adapter for any HuggingFace sequence classification model. We validate on two production reward models across ~695 RewardBench pairs. The central empirical finding is negative: linear attribution does not predict causal patching effects (mean Spearman $ρ= -0.256$ on Skywork, $-0.027$ on ArmoRM). The framework treats this disagreement as a property to expose, not a bug -- motivating a design that keeps observational and causal views first-class and directly comparable.

While mechanistic interpretability tools like Sparse Autoencoders (SAEs) can uncover meaningful features within Large Language Models (LLMs), a critical gap remains in transforming these insights into practical actions for model optimization. We bridge this gap with the hypothesis that data selection guided by a model's internal task features is a effective training strategy. Inspired by this, we propose Interpretability-Guided Data Selection (IGDS), a framework that first identifies these causal task features through frequency recall and interventional filtering, then selects ``Feature-Resonant Data'' that maximally activates task features for fine-tuning. We validate IGDS on mathematical reasoning, summarization, and translation tasks within Gemma-2, LLaMA-3.1, and Qwen3 models. Our experiments demonstrate exceptional data efficiency: on the Math task, IGDS surpasses full-dataset fine-tuning by a remarkable 17.4% on Gemma-2-2B while using only 50% of the data, and outperforms established baselines focused on data quality and diversity. Analysis confirms a strong positive correlation between feature amplification and task performance improvement. IGDS thus provides a direct and effective framework to enhance LLMs by leveraging their internal mechanisms, validating our core hypothesis.

Molecular biomarker testing in pathology is often costly and tissue-consuming, limiting scalable clinical deployment. Artificial intelligence applied to hematoxylin and eosin (HE)-stained histology could enable rapid biomarker screening, but clinical translation requires models that are both accurate and interpretable. Here we introduce Hireca, a biomarker-focused pathology foundation model pretrained on more than 80,000 whole-slide images spanning 38 organ types from three medical centers, together with CytoMap, an interpretability module that localizes cellular-scale evidence underlying predictions. Across 10 biomarker tasks encompassing morphological, molecular, genetic, and spatial-transcriptomic-proxy readouts, Hireca ranked first in five tasks and outperformed comparable models overall. In evaluation by eight pathologists from two countries, CytoMap was consistently preferred over alternative visualization approaches and revealed error patterns in difficult cases. These results position Hireca and CytoMap as a transparent framework for clinically reviewable biomarker assessment directly from routine HE histology.

Sparse Autoencoders (SAEs) decompose language-model activations into sparse, interpretable features, but standard encoders usually treat the latent dictionary as a flat set of independent coordinates, leaving hierarchy and feature interactions to emerge only implicitly. We propose KronSAE, a design that factorizes the latent space into heads and forms post-latent features as pairwise compositions of lower-dimensional pre-latents using mAND, a differentiable AND-like interaction. This imposes a compositional co-activation prior while remaining compatible with standard SAE objectives and variants such as TopK, Matryoshka, and Switch SAEs. KronSAE matches strong baselines on the EV-FLOPs frontier, improves interpretability of the latents, better captures the underlying correlated feature structure, and reduces encoder computational cost as an additional benefit. Code is available at https://github.com/corl-team/kronsae.

Tensorizing a neural network involves reshaping some or all of its dense weight matrices into higher-order tensors and approximating them using low-rank tensor network decompositions. This technique has shown promise as a model compression strategy for large-scale neural networks. However, despite encouraging empirical results, tensorized neural networks (TNNs) remain underutilized in mainstream deep learning. In this position paper, we offer a perspective on both the potential and current limitations of TNNs. We argue that TNNs represent a powerful yet underexplored framework for deep learning--one that deserves greater attention from both engineering and theoretical communities. Beyond compression, we highlight the value of TNNs as a flexible class of architectures with distinctive scaling properties and increased interpretability. A central feature of TNNs is the presence of bond indices, which introduce new latent spaces not found in conventional networks. These internal representations may provide deeper insight into the evolution of features across layers, potentially advancing the goals of mechanistic interpretability. We conclude by outlining several key research directions aimed at overcoming the practical barriers to scaling and adopting TNNs in modern deep learning workflows.

Deep reinforcement learning (DRL) has successfully addressed many complex control problems. However, the neural networks representing policies or values remain opaque, undermining trust in high-stakes applications. While concept-based methods have shown promise in deciphering internal representations in computer vision, applying them to DRL is impeded by the absence of pre-defined semantic concepts in continuous state spaces. In this work, we propose a novel concept-based explanation framework designed to provide fine-grained, neuron-level insights into DRL models. Unlike previous approaches that rely on manual feature engineering, our framework automatically aligns neuron activations with logical formulas composed of semantic predicates. To bridge the gap between continuous signals and symbolic reasoning, we introduce a value-sensitive discretization mechanism that transforms raw state features into interpretable atomic concepts. This ensures that the vocabulary used for explanation captures strategic decision boundaries relevant to the agent's value assessment. By composing these interpretable concepts and matching them with neuron behaviors, we derive explicit explanations for the network's internal representations. Experimental results on both continuous and discrete environments demonstrate that our method effectively identifies meaningful decision-making patterns, offering faithful explanations that align with human intuition.

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitoring and auditing to understand what models learn and ensure safe alignment. Mechanistic interpretability tools are essential to bridge this gap, among which Sparse Autoencoders (SAEs) serve as a cornerstone by isolating interpretable features for model inspection and steering. In this paper, we introduce SAEScientist-Bench to evaluate whether AI agents can act as scientists utilizing SAE tools for autonomous mechanistic discovery. Given a target concept, an agent designs contrastive probes and navigates a Gemma Scope dictionary of 131K+ features in Gemma-2-9B-IT to discover the optimal feature, evaluated against curated expert reference features anchored on Neuronpedia across activation rank, concept selectivity on contrastive texts, and causal steering. Across 10 agent configurations and 20 tasks, frontier agents demonstrate genuine discovery capabilities and lead different evaluation dimensions, but remain well behind the expert baseline, approaching expert levels on separating target concepts from contrastive controls while lagging substantially in causal generation steering. Further analysis reveals that although agents can design contrasts to rule out spurious candidates, they frequently misinterpret experimental measurements. These results establish experimental model understanding as a measurable capability for closed-loop autonomous AI R&D. Our code is available at https://github.com/Trae1ounG/SAEScientist.

Drug toxicity prediction is critical for reducing late-stage attrition in drug discovery, yet remains challenging due to severe class imbalance, scaffold-based generalization, and the clinical need for interpretable predictions. Single-modality approaches-SMILES Transformers or graph neural networks capture complementary aspects of molecular structure, while sequence-only models cannot directly provide graph-attributed explanations. We present SMILESGNN, a multimodal architecture that fuses a SMILES Transformer encoder and a GATv2 graph encoder via cross-attention, and SMILESGNN-PT, a variant using a ChemBERTa-2 pretrained backbone. The design retains an explicit graph branch within the predictive pipeline, supporting GNNExplainer-based analysis of substructures associated with toxic predictions. On ClinTox, SMILESGNN achieves AUC-ROC 0.987 and F1 0.906 with only 0.4M parameters, performing competitively with a strong SMILESTransformer and a larger ChemBERTa-2/GATv2 concat-fusion baseline. On Tox21 (12 tasks), SMILESGNN-PT obtains mean AUC-ROC 0.750, comparable to ChemBERTa-2 alone and the same-backbone concat-fusion baseline. Overall, the results suggest that cross-attention is a practical fusion alternative that preserves competitive predictive performance while enabling graph-based interpretability support.

Dynamic Time Warping (DTW) is the dominant approach for measuring similarity between time series, yet standard practice discards the optimal warping path after computing a single distance value, losing local alignment information most relevant to clinical diagnosis. We introduce DiaSeg, a framework that extracts diagonal segments from DTW paths with controlled breaks, characterizing each segment by five geometric features (effective length, interruption count, cost variation, temporal position, and path context), and enabling unsupervised pattern discovery without domain-specific feature engineering. Validated on 91 subjects across six clinical conditions (healthy aging, Parkinson's, Huntington's, ALS, brain tumor, and stroke), three findings emerge. First, diagonal segments form consistent unsupervised patterns (silhouette 0.33) aligned with biomechanical phase annotations, with label-based validation confirming near-perfect separation of healthy and pathological gait (ARI up to 0.986). Second, segments discriminate pathology at 69% (supervised) and 75% (patient-level clustering), with pathology manifesting through distributional shifts in segment length; combining segment and cycle-level features further improves classification to 91.7%. Third, while cycle-based methods achieve higher accuracy (91%), diagonal segments provide phase-specific interpretability unavailable in global representations, localizing where coordination breaks down within the gait cycle. DiaSeg thus transforms DTW from a black-box distance into a source of interpretable temporal features for neurodegenerative disease assessment.

Detecting phases of matter in general relies on identifying the correct order parameter - a task that remains notoriously difficult for unknown transitions and traditionally is guided by physical intuition and educated guess. Neural networks have recently offered an alternative route by locating phase transitions in known models without any a priori physical knowledge. Yet these approaches remain black boxes and only identify phases without elucidating their properties. Moreover, they often struggle when confronted with realistic, noisy experimental data, which constitute the ultimate testbed for automated methods in physics. Here, we bridge these perspectives by introducing TetrisCNN, a convolutional architecture with parallel branches of differently shaped filters, reminiscent of Tetris blocks, that learns sparse, interpretable latent representations directly in terms of spin correlators. Applied to experimental snapshots of two-dimensional Ising and XY quantum simulators measured in multiple bases, the network not only detects phase transitions and crossovers but also expresses its latent representation and decision boundaries as symbolic formulas built from experimentally measurable spin correlators. This framework opens the way to integrating interpretable neural networks with quantum simulators to uncover and understand new phases of matter.

While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This paper explores whether NLI can be performed using only interpretable, graph-based representations of evidence. We introduce a fully graph-based pipeline where the classifier never directly processes the input text. Instead, sentences are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and represented as three graphs per pair: premise, hypothesis, and a retrieved ConceptNet subgraph. These graphs are then fed into a fine-tuned 0.8-billion-parameter language model. On the SNLI dataset, our pipeline achieves 89.7% accuracy, just 1.9 points below an identically trained text-based model. On ANLI, it matches the published performance of RoBERTa-large on rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) but trails by 16 points on R1, resulting in an overall gap of 9 to 14 points compared to its text counterpart. We term this gap the price of interpretability and demonstrate that it stems from representational limitations rather than data constraints. Ablation studies further reveal that graphs and text are complementary: combining both modalities achieves 92.1% accuracy on SNLI.

The introduction of human-robot collaboration (HRC) in industrial assembly operations is revolutionizing the manufacturing landscape. In this evolving environment, operators are required to seamlessly coordinate their manual tasks with real-time task information and robotic behaviors. These demands fluctuate during operation, yet conventional workload assessments depend on body-worn physiological sensors that complicate practical deployment. Here, we present a vision-based attention--action framework for continuous and interpretable workload-related assessment in HRC assembly. The framework combines RGB-D observations with robot states and calibrated task-related areas to construct a temporally confirmed representation of operator behavior. This representation identifies where task demand is concentrated and explains how it develops when attention and action diverge, the task context changes, or the operator hesitates. We evaluated the framework in a three-level collaborative gearbox assembly experiment with ten participants, using subjective ratings and synchronized physiological signals as independent references. Raw NASA-TLX ratings confirmed increasing perceived workload across conditions, with significant effects on overall workload and its mental and temporal dimensions. The vision-derived HRC-CWL output was significantly associated with ECG-derived features in seven of nine participants with complete correlation data. Synchronized interaction episodes further showed temporal correspondence between detected hesitation and physiological activity. Real-time deployment demonstrated that the framework can operate without requiring operators to wear additional sensors. These findings support HRC-CWL as an interpretable behavioral proxy for cognitive ergonomics analysis and adaptive robot assistance, rather than a direct psychophysiological measure of workload.

The Abstraction and Reasoning Corpus (ARC) benchmarks cognitive generalization, the ability to infer and apply abstract rules from limited examples. This paper presents a multi-stage rule-chaining framework that performs compositional reasoning across symbolic, structural, and conceptual levels. The framework integrates three complementary solvers: (1) a deterministic rule discovery module that induces atomic transformations through geometric, color, and object-based analysis; (2) a pattern-composition engine that reconstructs outputs via block merging, repetition, and spatial heuristics; and (3) a structural abstraction layer that infers hierarchical and nested relationships across grids. These solvers operate sequentially within a progressive fallback hierarchy, where each stage reuses prior reasoning traces to enhance interpretability and generalization. Training passed for 995 tasks out of 1000, further evaluated on 105 tasks out of 120 and solved 230 test tasks out of 240 ARC-AGI-2 tasks. The system achieved strong coverage across deterministic, compositional, and abstract categories, demonstrating an overall accuracy exceeding 95 percent. The proposed architecture bridges symbolic reasoning and pattern synthesis, providing interpretable insight into cognitive generalization. The results suggest that rule chaining and hierarchical composition can advance machine reasoning toward transparent, human-aligned abstraction without relying on task-specific tuning.

sEMG is vulnerable to various contaminants that distort signal morphology and spectral content. Accurate signal quality assessment (SQA) is essential for identifying such degradation and ensuring reliable clinical analyses and decisions. Recent neural network-based SQA methods achieve accurate quality estimation by learning complex contamination patterns, yet their black-box nature prevents clinicians from understanding or validating the reported scores and limits adaptability to application-specific quality definitions without retraining. To address these limitations, we propose Prism-SQA, an interpretable and adaptable neural framework that reformulates SQA as a physiology-aware source-separation and verification process. Prism-SQA decomposes each input signal into a clean sEMG component and five contaminant-specific components using a U-Net with bidirectional long short-term memory. Each separated contaminant component is examined by a Contaminant Fingerprint Verifier, which enforces physiological plausibility by comparing its temporal and spectral structure with canonical contaminant signatures. This design allows clinicians to inspect how each contaminant affects signal quality, grounding the assessment in transparent, signal-level evidence rather than opaque latent representations. Quality indices computed from the verified components further enable customization of quality criteria across clinical contexts without retraining. We evaluate Prism-SQA on continuous quality-score estimation using synthesized noisy sEMG from public Ninapro datasets and on binary quality classification using a clinical dysphagia dataset. Results show that Prism-SQA achieves competitive or better performance than contemporary black-box neural methods while providing explicit interpretability and adaptability, advancing toward practical and clinically aligned sEMG SQA.

Hyperspectral unmixing decomposes mixed pixels into material endmembers and their abundances from contiguous spectral observations. In modular sensing pipelines, endmembers are often first identified and then treated as fixed during abundance estimation. When this fixed endmember prior is inaccurate, spatially structured mismatch arising from illumination changes, sensor artifacts, or material boundaries may be incorrectly captured by the abundance variables, leading to unstable decompositions. This study presents an interpretable stage-wise hyperspectral unmixing framework (I-HyperSU) under fixed endmember priors, which is explicitly decomposed into a fixed endmember matrix $\mathbf{A}$, an abundance block $\mathbf{X}$, and a structural residual refinement block $\mathbf{S}$. The X-block estimates abundances using FISTA with nonnegativity and sparsity enhancement, and a soft penalty that approximately enforces sum-to-one constraints. The S-block jointly applies low-rank SVD structural regularization and a lightweight deep image prior (DIP) to refine structured residuals. This staged design makes the interaction between abundance and residual components transparent and interpretable. Experiments on Samson, Urban, and Jasper Ridge datasets demonstrate that, under fixed and imperfect endmember priors, soft abundance relaxation consistently outperforms hard simplex projection. Under the default N-FINDR endmember prior, the proposed framework reduces the joint reconstruction error by 61.7%--69.5% compared with a fixed-$\mathbf{A}$ UCLS baseline, while keeping the abundance RMSE nearly unchanged, indicating that the residual refinement branch accounts for structured model mismatch without degrading the abundance estimates. For example, on Urban, the reconstruction SAM decreases from $5.99^\circ$ for the X-only model to $1.92^\circ$ for the full model.

Timed Partial Orders (TPOs), originally proposed for workflows, provide an interpretable framework for robot task specification with planning algorithms based on mixed-integer linear programming (MILP). However, TPOs are limited in expressivity, capturing only partial-order events with simple timing constraints. In this paper, we introduce Conditional TPOs (cTPOs), which extend TPOs with richer relative-timing constraints and conditional event activations based on environmental conditions. We show that planning for cTPOs also reduces to an MILP problem; however, the added expressivity results in significantly larger MILPs that can become computationally intractable. To address this challenge, we propose a decomposition algorithm that partitions a cTPO into smaller sub-TPOs, yielding a sequence of smaller MILP problems. We prove that this decomposition is complete and preserves plan optimality while improving the interpretability of complex tasks. Experimental results demonstrate the effectiveness of cTPOs as a task specification framework and the efficiency of our decomposition approach, achieving up to four orders of magnitude speedup over the monolithic MILP.

Patients with depression present with diverse symptom profiles, yet clinical practice routinely reduces this variation to a single severity score. Large language models (LLMs) can potentially capture various symptoms and their severity from patient speech. However, how depressive symptoms are represented inside LLMs remains poorly understood, limiting clinical trust. To examine whether internal model activations match clinician judgment, we analyzed the residual stream of Gemma-3-27B-PT using mechanistic interpretability techniques. Recording activations across symptom descriptions drawn from validated clinical instruments, we found that symptom groups geometrically separated the most at layer 21 across multiple distance metrics. Using Semantic Projection, we then projected held-out naturalistic text onto Symptom Vectors constructed from these instruments. The resulting per-symptom coefficients preserved clinician-annotated rank ordering across mood, somatic, and suicidality axes. Furthermore, a single depression vector in Layer 21 separates held-out depressive from non-depressive text (AUC = 0.789), which can be used as an emotional valence gate that restricts symptom projection to depressive speech. These results reveal a decorrelated, clinician-aligned symptom signal readable directly from internal activations, offering a mechanistic foundation for interpretable depression-assessment tools.

Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burdened by complex, multi-stage training pipelines and heavily rely on auxiliary regularization to prevent prototype collapse. To overcome these limitations, we introduce Orthonormal Prototype Alignment Learning (OPAL), a single-stage, end-to-end framework that simplifies interpretable classification. Our approach anchors the latent space using predefined orthonormal bases, embedding each class within a dedicated subspace spanned by fixed part-prototypes. To achieve precise part localization, OPAL enforces spatial competition across feature maps. This mechanism isolates sparse, discriminative regions, directing each prototype to consistently attend to the same semantic concept across different images. By framing classification as a direct representation alignment task, our method eliminates the need for auxiliary losses. Extensive experiments on fine-grained benchmarks demonstrate that OPAL outperforms both its non-interpretable counterparts and state-of-the-art part-prototype methods, delivering granular visual explanations by explicitly revealing the specific image regions driving every prediction. Code is available at https://github.com/ilancarretero/OPAL.

Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches. Existing methods often fail to capture the unique inner properties of these components, lack interpretability, or suffer from heavy memory and runtime overhead. To address these limitations, we propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework that explicitly decomposes time series into trend and seasonal components by applying domain-specific inductive biases. The trend stream enforces structural smoothness using a differential regularizer on the latent trajectory, analogous to the Hodrick-Prescott filter. Concurrently, the seasonal stream operates in the frequency domain via a complex Gaussian VAE, natively capturing the amplitude and phase of periodic patterns. Extensive evaluations across seven real-world benchmarks show that DecoVAE consistently outperforms strong baselines. It achieves reductions of up to 14.96% in CRPS and 23.30% in NMAE for short-term forecasting, and up to 52.68% and 26.51% for long-term horizons. Crucially, DecoVAE yields these accuracy gains while remaining highly efficient, reducing model weight by up to 93% and accelerating speed by up to 74% compared to the second-best method.

Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conventional metrics such as FID provide only scalar scores with limited diagnostic insight. Widely adopted CLIP-based metrics enable semantic evaluation beyond simple training class labels, but inherit limitations from CLIP's training paradigm that restrict attribute-wise analysis. We propose RA-CLIPScore, a novel metric that mitigates these issues and extends CLIP-based evaluation to spatial distribution alignment, measuring whether generated objects adhere to the positional priors found in the training data. RA-CLIPScore introduces dual prompts to decouple competing attributes and leverages local patch tokens to capture fine-grained regional semantics. We evaluate image generative models on their ability to match both attribute and spatial distributions of the training data. Extensive experiments show that RA-CLIPScore provides more robust and interpretable evaluations than prior methods, particularly under distribution misalignment or partially irrelevant textual attributes. We further demonstrate how it reveals spatial biases in generative models. User evaluations confirm that Regional Single Attribute Divergence based on our RA-CLIPScore aligns more closely with human perception of visual diversity than existing semantic metrics.

In regulated domains such as finance, a model that cannot be explained cannot be deployed, yet many interpretable classifiers defeat their own purpose by producing formulas with dozens of features that no regulator could read. We take the reverse direction. Starting from an interpretable classifier expressed as a single equation over the input features, we progressively simplify it into more readable forms, including a pruned monomial, a directional if--then rule, and the integer scorecards and tallies that finance already deploys. Because the equation is itself the predictive model rather than a post-hoc explanation we can directly quantify what is lost under each simplification. Across four financial datasets, we find that pruning is nearly free and that fidelity can erode faster than predictive performance, allowing simpler rules to remain effective classifiers without faithfully reproducing the original model. A human assessment shows that simplification improves perceived readability, while preferences for different representations vary by professional background. Beyond measuring these losses empirically, we show that some can be anticipated from the original model: we derive a bound on the change caused by pruning and predict how faithfully a rule retaining only the direction of each feature's effect preserves the original ranking.

Mixed strategy equilibrium predicts i.i.d play: past actions should not help predict future decisions. Human players, however, systematically depart from this benchmark, and in O'Neill's zero sum card game, these departures can be predicted by black box sequence models such as LSTMs. This paper asks whether that predictive power can be achieved by transparent alternatives that also reveal the behavioural structure behind it. Using 84,060 decisions from 2,802 pairs, the analysis first benchmarks naive and behavioral models against interpretable machine learning and deep learning models, then evaluates the modified EWA specifications of prior work against these benchmarks and uses the LASSO diagnostics to motivate a further nested frequency tracking extension. The results show that repeat or avoid behavior, especially players' management of their own recent action histories, accounts for most of the interpretable and strategically exploitable signal, while frequency tracking adds little out of sample.

Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence behind their decisions and abstain when they cannot decide reliably. We introduce Fast Evidential Rule Learning (FERL), a method that learns interpretable, accurate fuzzy rule models whose outputs are evidential. Unlike post-hoc calibration, FERL's belief, plausibility, and abstention capabilities arise directly from the fuzzy memberships in a single deterministic pass, with no auxiliary head, held-out set, or repeated inference. Our theoretical analysis further shows that FERL is Lipschitz stable, which means that its evidential outputs vary smoothly with the input. Against state-of-the-art rule learners, FERL is statistically significantly more accurate across a 30 tabular-dataset benchmark ($+2.6\%$ average accuracy over the second best). Its native set predictions attain the best utility-discounted accuracy among credal classifiers ($u_{65}/u_{80}=0.80/0.83$ vs.\ $0.79/0.80$ for the naive credal classifier), at higher set coverage ($0.92$ vs.\ $\le0.82$). FERL also matches dedicated out-of-distribution detectors on tabular near-OOD detection ($77.7$ vs.\ $77.4$ AUROC for the strongest baseline). Under detector-class-disjoint concept-bottleneck evaluation, its it is within $2.3$ AUROC points of the strongest dedicated detector on both CUB and AwA2, while attaining the best AwA2 AUPR-Out ($68.3$) and novel-class rejection ($57.2$), while being able to name which attributes are anomalous.

Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that spend the same compute on easy and difficult prompts. These fixed budgets are also difficult to inspect because they do not explain why a given prompt receives a particular number of samples. We propose adaptive} test-time scaling with a lightweight fuzzy controller that maps interpretable signals, including estimated prompt complexity and model confidence, to a per-query sampling budget. The controller assigns fewer samples to easier or more confident prompts and more samples to harder or less certain prompts, making inference-time compute inspectable rather than fixed or opaque. We evaluate under a fair-alignment protocol with matched decoding settings and controlled answer selection, and compare against best-of-$N$, compute-aware scaling, and self-certainty-based baselines on question-answering and mathematical reasoning tasks. Across models and datasets, adaptive fuzzy control improves over several standard baselines and remains close to a selector-matched full-budget control while reducing the average number of samples. These findings suggest that interpretable adaptive sampling is a practical direction for more efficient test-time reasoning in large language models.