New Framework Jointly Models Observation Likelihood and Values in Incomplete Time Series Forecasting
Researchers have proposed Timeflies, a machine learning framework that reformulates time series forecasting as a joint problem of predicting both whether a future observation will exist and what its value will be. Existing methods, including Neural ODEs and continuous-time graph networks, implicitly assume that the timestamps of future valid observations are known in advance—an unrealistic condition in many real-world systems with sensor dropouts and irregular sampling. The work addresses a fundamental gap in forecasting under missingness, with potential relevance to industrial monitoring, healthcare, and other domains relying on incomplete sensor data.
A preprint submitted to arXiv introduces Timeflies, a unified forecasting framework designed for real-world time series that are incomplete and irregularly sampled due to sensor dormancy, transmission delays, or event-driven collection. The authors argue that prior approaches—ranging from impute-then-forecast pipelines to continuous-time models—share a hidden 'oracle assumption': they presume the timestamps of future valid observations are known at inference time, which is rarely true in practice. Timeflies addresses this by coupling an observation stream and a value stream through three dedicated modules handling reliability-aware embedding, observation-guided dependency modeling, and joint prediction. To support evaluation, the authors also introduce Shadow, a benchmark combining natural missingness from public datasets with real industrial data, and propose a new metric called Observation-Value Joint Entropy (OVJE) to measure coupled predictability. Extensive experiments reported in the paper show Timeflies consistently outperforms existing baselines. The work was submitted on June 11, 2026, and code and datasets are publicly available.
What's missing
As a preprint, Timeflies has not yet undergone formal peer review. The paper does not detail the specific industrial domains from which the real-world data in the Shadow benchmark was drawn, nor does it discuss potential failure modes when observation missingness is non-random or adversarially structured. Scalability to very high-dimensional sensor networks is not explicitly characterized.
What different sources said
- arXiv cs.AICenter
Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.