Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations

• URL: http://arxiv.org/abs/2607.00956v1
• Date: Wed, 01 Jul 2026 13:54:20 GMT
• Title: Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
• Abstract summary: Aionoscope is a diagnostic tool for inspecting latent-state accessibility in frozen time-series representations.<n>Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels.
• Score: 59.34593956287438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time-series models are often evaluated by what they can forecast or classify, but those scores do not show whether their representations preserve the process state a user may want to inspect: event timing, phase, amplitude, frequency, or regime variables. We introduce Aionoscope, a generator-based diagnostic tool for debugging latent-state accessibility in frozen time-series representations. Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels across mixture complexity and nuisance variation. We instantiate Aionoscope as Primitive Process Mixtures and evaluate 37 model-plus-adapter systems with a common pooled linear-probe protocol. The main result is a mismatch between coarse and fine-grained accessibility. Most systems make component presence easy to recover, but expose dense process state much less reliably: the highest observed dense-probe row reaches 0.689 mean masked $R^2$, while a dense-feature oracle reaches 0.999. This is the failure mode Aionoscope is designed to surface: a representation can look informative at the level of "what kind of signal is present" while hiding the timing, phase, amplitude, frequency, or regime variables needed for debugging.

Related papers

• Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection [0.2160500132391863]
  This work formulates time-series OOD detection as representation learning with hyperspherical embeddings.<n>The learned representation combines time- and frequency-domain views of the input signal via domain-specific encoders.<n>We evaluate the approach at scale on the complete UCR and UEA time-series archives under a cross-dataset protocol.
  arXiv  Detail & Related papers  (2026-05-29T11:04:34Z)
• MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification [60.41879345743941]
  We propose MedMamba, an end-to-end architecture that integrates state space models with domain-specific inductive biases.<n>MedMamba achieves state-of-the-art performance while maintaining linear computational complexity.
  arXiv  Detail & Related papers  (2026-05-24T09:23:39Z)
• LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection [53.191369031661885]
  Unsupervised time series anomaly detection aims to build a model for identifying abnormal timestamps without assuming the availability of annotations.<n>We present Learnable Fusion of Tri-view Tokens (LEFT), a unified unsupervised TSAD framework that models anomalies as inconsistencies across complementary representations.<n>Experiments on real-world benchmarks show that LEFT yields the best detection accuracy against SOTA baselines, while achieving a 5x reduction on FLOPs and 8x speed-up for training.
  arXiv  Detail & Related papers  (2026-02-09T13:33:49Z)
• SMKC: Sketch Based Kernel Correlation Images for Variable Cardinality Time Series Anomaly Detection [0.0]
  In operational environments, monitoring systems frequently experience sensor churn.<n>We propose SMKC, a framework that decouples the dynamic input structure from the anomaly detector.<n>We find that a detector using random projections and nearest neighbors on the SMKC representation performs competitively with fully trained baselines.
  arXiv  Detail & Related papers  (2026-01-28T21:15:11Z)
• Supervised Machine Learning for Predicting Open Quantum System Dynamics and Detecting Non-Markovian Memory Effects [0.0]
  We present a emphnovel and scalable supervised machine learning framework to predict open-quantum system dynamics and detect non-Markovian memory.<n>A feedforward neural network, trained on short sliding windows of supplementary data from the past, forecasts the observable system $langle Z_(S)(t)rangle$ without state tomography or knowledge of the bath.<n>To quantify memory, we introduce a normalized revival-based metric that counts upward 'turn-backs' in emphpredicted $langle Z_(S)(
  arXiv  Detail & Related papers  (2025-09-26T10:40:44Z)
• Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values [67.76168547245237]
  We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-11T10:10:16Z)
• AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Scheme [0.7216399430290167]
  Anomaly detection task for time series, especially for unlabeled data, has been a challenging problem. We address it by applying a suitable data degradation scheme to self-supervised model training. Inspired by the self-attention mechanism, we design a Transformer-based architecture to recognize the temporal context.
  arXiv  Detail & Related papers  (2023-05-08T05:42:24Z)
• Tripletformer for Probabilistic Interpolation of Irregularly sampled Time Series [6.579888565581481]
  We present a novel encoder-decoder architecture called "Tripletformer" for probabilistic of irregularly sampled time series with missing values. This attention-based model operates on sets of observations, where each element is composed of a triple time, channel, and value. Results indicate an improvement in negative loglikelihood error by up to 32% on real-world datasets and 85% on synthetic datasets.
  arXiv  Detail & Related papers  (2022-10-05T08:31:05Z)
• Multi-scale Anomaly Detection for Big Time Series of Industrial Sensors [50.6434162489902]
  We propose a reconstruction-based anomaly detection method, MissGAN, iteratively learning to decode and encode naturally smooth time series. MissGAN does not need labels or only needs labels of normal instances, making it widely applicable.
  arXiv  Detail & Related papers  (2022-04-18T04:34:15Z)
• Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [76.89426311082927]
  Existing models are trained on clean data, which causes a textitgap between clean data training and real-world inference. We propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Experiments on the widely-used dataset, Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment.
  arXiv  Detail & Related papers  (2021-04-13T17:54:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.