# Early Warning

Published articles for Early Warning.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Towards Early Warning of Real-World Vulnerabilities: An Evidence-Aware Decoupled Method for CVSS Vector Prediction Based on Unstructured Disclosures

DevFeed: [Towards Early Warning of Real-World Vulnerabilities: An Evidence-Aware Decoupled Method for CVSS Vector Prediction Based on Unstructured Disclosures](<https://devfeed.tech/articles/towards-early-warning-of-real-world-vulnerabilities-an-evidence-aware-decoupled-method-for-cvss-vector-prediction-based-on-unstructured-disclosures-118713.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06477>)

Author: Jianhong Ma, Wenhao Li, Xixing Li, Chenyu Yan, Haowen Chen

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [CVSS v4.0](<https://devfeed.tech/topics/cvss-v4-0.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [NVD](<https://devfeed.tech/topics/nvd.md>), [OSINT](<https://devfeed.tech/topics/osint.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [absolute](<https://devfeed.tech/tags/absolute.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [based](<https://devfeed.tech/tags/based.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bert](<https://devfeed.tech/tags/bert.md>), [can](<https://devfeed.tech/tags/can.md>), [class](<https://devfeed.tech/tags/class.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cvss](<https://devfeed.tech/tags/cvss.md>), [disclosures](<https://devfeed.tech/tags/disclosures.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [warning](<https://devfeed.tech/tags/warning.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

VPre predicts CVSS vectors from noisy, incomplete vulnerability disclosures, with the benchmark showing earlier estimates than official NVD scoring. Its two-level method first screens reports and sentences for security evidence, then routes each of the eight CVSS metrics according to evidence availability: large-language-model reasoning for scattered evidence and lightweight supervised classification for explicit evidence. On an 851-report held-out split of VPre-Bench (5,581 reports total), it achieves mean absolute error 0.7239, reported as 44.7% below a reproduced BERT-Small-NVD early-transfer baseline. Across the benchmark, predictions precede official scoring by 38 days on average (observed range 21-60 days). In the stated 38:1 PARSE-Triage noise setting, STDU report screening reaches 0.98 precision, 1.00 recall and 0.99 F1. The abstract reports controlled ablations supporting both decoupling levels.

### Source excerpt

arXiv:2611.06477v1 Announce Type: new Abstract: Early assessment of Common Vulnerability Scoring System (CVSS) vectors from Open Source Intelligence (OSINT) can reduce the delay between initial public disclosure and official National Vulnerability Database (NVD) scoring. Existing predictors, trained mainly on standardized late-stage descriptions, degrade on noisy and incomplete pre-NVD reports. We introduce PARSE, a vulnerability-disclosure lifecycle model, and VPre, an early assessment framework built on two-level Evidence-Aware Decoupling. Decoupling Level I, Security-Evidence Screening, separates security-relevant evidence from noisy early reports at the report and sentence levels. Decoupling Level II, Evidence-Matched Routing, decouples the prediction task of the eight CVSS metrics into a scattered-evidence class and an explicit-evidence class based on validation-set measurements, matching each with a targeted predictor: large-language-model reasoning for the former, lightweight supervised classification for the latter. On the 851-report held-out test split of the 5,581-report VPre-Bench, VPre achieves a mean absolute error of 0.7239 -- 44.7% below the reproduced BERT-Small-NVD early-transfer baseline; paired timestamps across the full benchmark show an average 38-day lead before official scoring (observed range 21-60 days). Under the 38:1 PARSE-Triage noise setting, STDU's report-level screening reaches 0.98 precision, 1.00 recall, and 0.99 F1. Controlled ablations support the contributions of both decoupling levels.

## TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models

DevFeed: [TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models](<https://devfeed.tech/articles/topoquant-topological-framework-to-characterize-behavioral-shifts-in-quantized-large-language-models-115071.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.00631>)

Author: Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg, Rafet Sifa, Murat Kantarcioglu, Carson K. Leung, Cuneyt Gurcan Akcora

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [behavioral-shifts](<https://devfeed.tech/tags/behavioral-shifts.md>), [compression](<https://devfeed.tech/tags/compression.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [features](<https://devfeed.tech/tags/features.md>), [framework](<https://devfeed.tech/tags/framework.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [precision](<https://devfeed.tech/tags/precision.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [r2](<https://devfeed.tech/tags/r2.md>), [signal](<https://devfeed.tech/tags/signal.md>), [stable](<https://devfeed.tech/tags/stable.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

TopoQuant applies topological data analysis to self-attention weights to measure structural drift in quantized large language models. Across four model families, the authors report that drift stays stable at moderate compression, then rises sharply below 4-bit precision as attention agreement declines. Lightweight machine-learning models use topological features to predict attention consistency, with reported R² scores up to 0.85. The authors propose this as an early warning for behavioral degradation that could help assess compression limits without expensive downstream tasks; the evidence here is limited to the abstract.

### Source excerpt

arXiv:2611.00631v1 Announce Type: new Abstract: Post-training quantization (PTQ) reduces the com putational cost of large language models (LLMs), but it can introduce internal structural and behavioral changes that are not captured by traditional metrics such as accuracy and per plexity. We present TopoQuant, a topological framework that uses topological data analysis (TDA) to quantify structural drift in self-attention weights and relate it to behavioral changes in quantized LLMs. Across four LLM families and multiple quantization levels, we show that topological drift remains stable at moderate compression levels but increases sharply below 4 bit precision, closely tracking declines in attention agreement. Our results reveal a strong relationship between topological drift and attention agreement, indicating that structural changes in model parameters closely reflect behavioral degradation under quantization. We further demonstrate that topological features can accurately predict attention consistency using lightweight machine learning models, achieving R2 scores of up to 0.85. Predicting attention agreement enables efficient assessment of be havioral consistency in quantized LLMs, allowing quantization induced degradation to be detected without running expensive downstream tasks. The results indicate that topological drift pro vides an efficient early-warning signal for quantization-induced degradation and can help identify safe compression limits without extensive downstream evaluation.

## A Geometry-Informed Neural Operator surrogate of LISFLOOD-FP for rapid pluvial-fluvial flood forecasting: the case of Forl\\\`i, Italy

DevFeed: [A Geometry-Informed Neural Operator surrogate of LISFLOOD-FP for rapid pluvial-fluvial flood forecasting: the case of Forl\\\`i, Italy](<https://devfeed.tech/articles/a-geometry-informed-neural-operator-surrogate-of-lisflood-fp-for-rapid-pluvial-fluvial-flood-forecasting-the-case-of-forl-i-italy-114794.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03381>)

Author: Samuele Maria Garofalo, Fabio Limardo, Simonetta Bodojra, Mohammad Amin Nabian, Mehdi Taghizadeh

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [implementation](<https://devfeed.tech/topics/implementation.md>), [World models](<https://devfeed.tech/topics/world-models.md>)

Tags: [autoregressive](<https://devfeed.tech/tags/autoregressive.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [italy](<https://devfeed.tech/tags/italy.md>), [neural](<https://devfeed.tech/tags/neural.md>), [operator](<https://devfeed.tech/tags/operator.md>), [physics-geo-ph](<https://devfeed.tech/tags/physics-geo-ph.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [rapid](<https://devfeed.tech/tags/rapid.md>)

### AI overview

For Forlì, Italy, an autoregressive geometry-informed neural operator (GINO) surrogate of LISFLOOD-FP produces 72-hour flood forecasts from river-stage and rain-gauge observations. Its training pipeline uses calibrated water-surface boundary conditions driven by downstream stage gauges and SCS-CN effective rainfall; it predicts volume-conserving polygon-mean depths on a 659-node exposure-based Voronoi mesh at 20-minute steps. Tested on 38 independent observed events, it reports CSI values of 0.934 at 0.05 m and 0.844 at 0.3 m, depth RMSE of 0.008 m, and maximum-depth-map R² of 0.984. On an NVIDIA A10G, a forecast takes 1.7 seconds versus 55 seconds for LISFLOOD-FP; a batched 50-member ensemble takes 6.2 seconds versus about 46 minutes. These results are reported for the Forlì case study.

### Source excerpt

arXiv:2611.03381v1 Announce Type: new Abstract: Physically based two-dimensional hydraulic models are too slow for real-time inundation forecasting and large ensembles. We present a time-dependent geometry-informed neural operator (GINO) surrogate of LISFLOOD-FP for the municipality of Forl\`i (Italy), severely affected by the May 2023 Emilia-Romagna floods. The surrogate is designed for an operational setting in which only river stage gauges and rain gauges are available. A reproducible pipeline turns public regional observations into a physically based training set: each river inflow is driven by the first stage gauge downstream of it through a calibrated water-surface boundary condition, and rain enters as SCS-CN effective rainfall. The surrogate is an autoregressive GINO trained on 216 simulations of 24 observed events with scaled forcing. It predicts volume-conserving polygon-mean depths on an exposure-based Voronoi mesh of 659 nodes, with a 20 min step over 72 h. The surrogate is tested on 38 independent observed events that it never saw during training. On these events it reaches a critical success index (CSI) of 0.934 at 0.05m and 0.844 at 0.3 m, a depth RMSE of 0.008m and an $R^2$ of 0.984 for maximum-depth maps. On one NVIDIA A10G GPU a 72-h forecast takes 1.7 s instead of 55 s with LISFLOOD-FP, and a 50-member ensemble, computed in a single batched rollout, takes 6.2 s instead of about 46 min, which makes probabilistic flood forecasting practical. These results show that neural-operator surrogates can deliver accurate pluvial-fluvial flood forecasts driven by river stage for operational early warning.

## Multi-output LSTM soft sensors for industrial anaerobic co-digestion using LSTM-beta-VAE generative data augmentation

DevFeed: [Multi-output LSTM soft sensors for industrial anaerobic co-digestion using LSTM-beta-VAE generative data augmentation](<https://devfeed.tech/articles/multi-output-lstm-soft-sensors-for-industrial-anaerobic-co-digestion-using-lstm-beta-vae-generative-data-augmentation-108231.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.39768>)

Author: Rohit Murali, Benaissa Dekhici, Tao Chen, Dongda Zhang, Michael Short

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [failure](<https://devfeed.tech/tags/failure.md>), [feature](<https://devfeed.tech/tags/feature.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generative](<https://devfeed.tech/tags/generative.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [long-short-term-memory](<https://devfeed.tech/tags/long-short-term-memory.md>), [lstm](<https://devfeed.tech/tags/lstm.md>), [mo](<https://devfeed.tech/tags/mo.md>), [model](<https://devfeed.tech/tags/model.md>), [modelling](<https://devfeed.tech/tags/modelling.md>), [sensors](<https://devfeed.tech/tags/sensors.md>), [vae](<https://devfeed.tech/tags/vae.md>)

### AI overview

Industrial anaerobic digestion data are sparse and weighted toward steady operation, making Random Forest, XGBoost, and unaugmented LSTMs poor at recognizing transitions to instability and estimating stability indicators. The study combines an LSTM-beta-Variational Autoencoder with a multi-output LSTM soft sensor, using one year of full-scale plant data to synthesize physically valid sequences of unstable transitions. The augmented model reportedly estimated all targets simultaneously and robustly, offering a basis for early-warning soft sensors. The supplied text provides no numerical performance results.

### Source excerpt

arXiv:2610.39768v1 Announce Type: cross Abstract: Anaerobic digestion (AD) requires close monitoring of key process variables, including pH, the ratio of volatile organic acids to alkaline buffer capacity and biogas production, to maintain biological stability and prevent process failure. While mechanistic frameworks such as the Anaerobic Digestion Model No. 1 are highly parameterised, computationally expensive, and difficult to calibrate for real-time applications, data-driven Long Short-Term Memory (LSTM) networks offer a potentially more adaptable alternative. However, current data-driven approaches in AD are predominantly limited to single-output architectures that focus solely on production yields, as opposed to simultaneous prediction of vital stability indicators. Furthermore, industrial AD datasets are typically sparse and skewed toward steady-state operations. Baseline evaluations demonstrated this scarcity prevents standard algorithms (Random Forest, XGBoost) and unaugmented LSTMs from recognising the transition to unstable operations, resulting in poor estimation of stability indicators. To overcome these challenges, this study proposes a novel generative data augmentation framework using an LSTM-beta-Variational Autoencoder coupled with a multi-output LSTM (MO-LSTM) soft sensor. By synthesising physically valid sequences of these transitions to unstable operations from one year of full-scale plant data, the method safely populates sparse regions of the feature space. Trained on this augmented dataset, the MO-LSTM achieved robust simultaneous estimation across all targets. This approach mitigates data sparsity, providing a basis for hybrid mechanistic-data-driven modelling and early-warning soft sensors in industrial bioprocesses.

## An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning

DevFeed: [An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning](<https://devfeed.tech/articles/an-incremental-knowledge-graph-learner-digital-twin-for-evidence-grounded-early-warning-103192.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36820>)

Author: Ngoc Luyen Le, Marie-H\\'el\\\`ene Abel, Bertrand Laforge

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [digital-twin](<https://devfeed.tech/tags/digital-twin.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [graph](<https://devfeed.tech/tags/graph.md>), [incremental](<https://devfeed.tech/tags/incremental.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [learner](<https://devfeed.tech/tags/learner.md>)

### AI overview

The paper presents an incremental Learner Digital Twin, implemented as a lightweight knowledge graph, to connect early-warning risk alerts to inspectable learning evidence. At temporal checkpoints, it replays learning traces and assessment records; graph queries derive predictive features, while the graph stores features, attributions, alerts, evidence items, and raw records as queryable entities. On a public learning-analytics benchmark evaluated with a temporal protocol, graph-derived features reportedly preserved the predictive behavior of equivalent raw-table features across model families and checkpoints. Alerts were represented as evidence chains linking risk decisions to attributions, evidence items, and platform records, adding traceability and verifiability while preserving predictive performance.

### Source excerpt

arXiv:2610.36820v1 Announce Type: new Abstract: Early-warning models in learning analytics can identify learners at risk of failure or withdrawal, but the resulting alerts are often only weakly connected to inspectable learning evidence. A risk score may indicate that intervention is needed without showing which traces, assessment events, or temporal patterns justify the alert. This paper introduces an incremental Learner Digital Twin for evidence-grounded early warning, implemented as a lightweight knowledge graph. The twin is updated at temporal checkpoints by replaying learning traces and assessment records, and it serves both as a feature-extraction substrate and as an explanation-grounding substrate. Predictive features are derived through graph-mediated queries, while features, attributions, alerts, evidence items, and raw records are represented as queryable graph entities. The framework is instantiated and evaluated on a public learning-analytics benchmark under a temporal protocol. The results show that graph-mediated feature extraction preserves the predictive behavior of equivalent raw-table features across model families and checkpoints. Generated alerts are materialized as evidence chains linking risk decisions to feature attributions, evidence items, and raw platform records. The study shows that early-warning prediction can be routed through a semantic and provenance-aware representation while preserving predictive performance and adding traceability, verifiability, and evidence-grounded explanation.

## How Figma turned dbt tests into consistency checkers that catch 100+ bugs a month

DevFeed: [How Figma turned dbt tests into consistency checkers that catch 100+ bugs a month](<https://devfeed.tech/articles/how-figma-turned-dbt-tests-into-consistency-checkers-that-catch-100-bugs-a-month-101835.md>)

Original publisher: [Read original article](<https://www.getdbt.com/blog/figma-dbt-tests-data-quality-consistency-checks>)

Author: Daniel Poppy

Published: 2026-10-26T14:02:00Z

Content type: news

Language: en

Sources: [dbt Labs](<https://devfeed.tech/sources/dbt-labs.md>)

Topics: [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-features](<https://devfeed.tech/tags/ai-features.md>), [alerting](<https://devfeed.tech/tags/alerting.md>), [asana](<https://devfeed.tech/tags/asana.md>), [billing](<https://devfeed.tech/tags/billing.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [business](<https://devfeed.tech/tags/business.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [dagster](<https://devfeed.tech/tags/dagster.md>), [data](<https://devfeed.tech/tags/data.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [false-positive](<https://devfeed.tech/tags/false-positive.md>), [false-positive-rate](<https://devfeed.tech/tags/false-positive-rate.md>), [false-positives](<https://devfeed.tech/tags/false-positives.md>), [figma](<https://devfeed.tech/tags/figma.md>), [hex](<https://devfeed.tech/tags/hex.md>), [learn](<https://devfeed.tech/tags/learn.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

Figma turned scheduled dbt singular tests into actionable "consistency checkers" to catch product and business issues. Dagster runs them against Snowflake; failures feed PagerDuty and Slack alerts, Asana and Linear tasks, and Hex investigations, where engineers can mark expected failures. During a billing remodel, more than 100 checkers caught at least five serious discrepancies; the system now spans 450+ checks across 15 functions and catches over 100 real code or data issues in a typical month. Early false positives affected 67% of failures, often due to stale syncs, faulty SQL, or permission gaps. Checking a later sync, using AI agents to iterate on SQL, and obtaining legal approval for fuller datasets reduced that rate to 33%. Figma keeps routine model-breaking tests in the dbt DAG and reserves consistency checkers for product- or business-facing problems, with software engineering owning them and data science partnering on complex SQL.

### Source excerpt

Figma's data science team built an early warning system for billing bugs out of nothing more exotic than dbt tests.

## EVOLVE: Uncertainty-Aware Multivariate Time Series Anomaly Prediction with Adaptive Prototype Memories

DevFeed: [EVOLVE: Uncertainty-Aware Multivariate Time Series Anomaly Prediction with Adaptive Prototype Memories](<https://devfeed.tech/articles/evolve-uncertainty-aware-multivariate-time-series-anomaly-prediction-with-adaptive-prototype-memories-99577.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.32189>)

Author: Jianxin Jin, Kai Zhao, Shiyan Hu, Yang Shu, Peng Chen, Meng Wang, Zhongwen Rao, Yijie Li, Jing Wang, Bin Yang, Chenjuan Guo

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Time Series](<https://devfeed.tech/topics/time-series.md>), [Temporal data](<https://devfeed.tech/topics/temporal-data.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [complex-systems](<https://devfeed.tech/tags/complex-systems.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [future](<https://devfeed.tech/tags/future.md>), [history](<https://devfeed.tech/tags/history.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [memory](<https://devfeed.tech/tags/memory.md>), [models](<https://devfeed.tech/tags/models.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [plausible](<https://devfeed.tech/tags/plausible.md>), [proactive](<https://devfeed.tech/tags/proactive.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [random](<https://devfeed.tech/tags/random.md>), [time-series](<https://devfeed.tech/tags/time-series.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

EVOLVE predicts future anomaly risk in multivariate time series by adapting simulated perturbations to each variable and its context. Its adaptive anomaly prototype memory updates and retrieves relevant perturbations. To account for multiple plausible futures, the method samples latent historical states and decodes them under smooth and deviation-amplifying evolution hypotheses; disagreement between the resulting trajectories estimates risk. The abstract reports that EVOLVE outperforms state-of-the-art anomaly prediction baselines on six real-world benchmark datasets.

### Source excerpt

arXiv:2610.32189v1 Announce Type: new Abstract: Unsupervised multivariate time series anomaly prediction (AP) aims to estimate future anomaly risks from current observations, providing early-warning signals for proactive intervention and maintenance in complex systems. Existing unsupervised AP methods follow a perturbation-based paradigm, where predefined or random perturbations are injected into historical windows to simulate abnormal future evolution. However, these methods share perturbations across different variables and contexts, and learn deterministic history-to-future evolution. In reality, anomaly evolution is variable- and context-dependent: the same perturbation may be amplified into abnormal future dynamics in one variable or context, while being absorbed as normal fluctuation in another. In addition, future evolution is not uniquely determined by a historical window, since similar histories may lead to multiple plausible trajectories, such as gradual degradation or abrupt changes. To address these problems, we propose EVOLVE, a unified framework that models unsupervised AP via variable- and context-conditioned perturbations and uncertainty-aware future reasoning. EVOLVE constructs context-specific anomaly perturbations through an adaptive anomaly prototype memory, which can dynamically update and retrieve relevant perturbations at the variable level. EVOLVE models uncertainty by sampling multiple latent historical states and decoding through complementary smooth and deviation-amplifying evolution hypotheses, and the disagreement among decoded future trajectories is used to estimate future anomaly risk. Extensive experiments on six real-world benchmark datasets demonstrate that EVOLVE consistently outperforms state-of-the-art anomaly prediction baselines.

## Spherical Physics-informed Neural Operator with Multi-scale Coupling for Meteorological Downscaling

DevFeed: [Spherical Physics-informed Neural Operator with Multi-scale Coupling for Meteorological Downscaling](<https://devfeed.tech/articles/spherical-physics-informed-neural-operator-with-multi-scale-coupling-for-meteorological-downscaling-93347.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.24708>)

Author: Yiqiang Ye, Yichi Wang, Haodi Zhang, Jiawei Wen, Jiahui Jiang, Zhaoyu Zhong, Jiangjian Yu, Chunxia Xiao

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [climate](<https://devfeed.tech/tags/climate.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [coupling](<https://devfeed.tech/tags/coupling.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [disaster](<https://devfeed.tech/tags/disaster.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fields](<https://devfeed.tech/tags/fields.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [framework](<https://devfeed.tech/tags/framework.md>), [global](<https://devfeed.tech/tags/global.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [learning](<https://devfeed.tech/tags/learning.md>), [mappings](<https://devfeed.tech/tags/mappings.md>), [neural](<https://devfeed.tech/tags/neural.md>), [operator](<https://devfeed.tech/tags/operator.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-ao-ph](<https://devfeed.tech/tags/physics-ao-ph.md>), [physics-informed](<https://devfeed.tech/tags/physics-informed.md>), [scale](<https://devfeed.tech/tags/scale.md>)

### AI overview

The proposed Spherical Physics-informed Neural Operator targets meteorological downscaling by combining three mechanisms: Spherical Laplacian Decomposition separates atmospheric fields into hierarchical frequency components while preserving point-wise correspondence across scales; a localized spherical integral operator uses geometry-aware attention to evaluate them at arbitrary locations; and differentiable constraints enforce dynamical consistency during learning. The abstract reports superior accuracy and zero-shot generalization across meteorological variables and unseen queries, but provides no experiment details or quantitative results.

### Source excerpt

arXiv:2610.24708v1 Announce Type: cross Abstract: Meteorological downscaling is crucial for high-resolution regional climate forecasting and disaster early warning. While neural operators have emerged as a promising paradigm for modeling complex spatiotemporal mappings, existing frameworks often struggle with spherical manifold geometric distortions, inherent atmospheric multi-scale coupling mismatches, and lack of explicit atmospheric laws. We propose the Spherical Physics-informed Neural Operator, which utilizes a Spherical Laplacian Decomposition to partition atmospheric fields into hierarchical frequency components, maintaining exact point-wise correspondence across scales. To evaluate these representations at arbitrary locations, we introduce a localized spherical integral operator that approximates continuous kernel transforms via geometry-aware attention. Dynamical consistency is further enforced by embedding differentiable constraints into the learning process. Extensive experiments demonstrate that our framework attains superior accuracy and zero-shot generalization across various meteorological variables and unseen queries, representing a robust and interpretable solution for global-to-regional meteorological downscaling.

## PHP warns admins of two critical flaws, emergency patches coming tomorrow

DevFeed: [PHP warns admins of two critical flaws, emergency patches coming tomorrow](<https://devfeed.tech/articles/php-warns-admins-of-two-critical-flaws-emergency-patches-coming-tomorrow-91347.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/php-warns-admins-of-two-critical-flaws-emergency-patches-coming-tomorrow/>)

Author: Lawrence Abrams

Published: 2026-10-20T20:56:43Z

Content type: news

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [PHP](<https://devfeed.tech/topics/php.md>), [Security research](<https://devfeed.tech/topics/security-research.md>), [patches](<https://devfeed.tech/topics/patches.md>)

Tags: [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cve-2026-109618](<https://devfeed.tech/tags/cve-2026-109618.md>), [cve-2026-109619](<https://devfeed.tech/tags/cve-2026-109619.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [infosec-computer-security](<https://devfeed.tech/tags/infosec-computer-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [php](<https://devfeed.tech/tags/php.md>), [rce](<https://devfeed.tech/tags/rce.md>), [security](<https://devfeed.tech/tags/security.md>), [security-updates](<https://devfeed.tech/tags/security-updates.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [warning](<https://devfeed.tech/tags/warning.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

PHP plans to release emergency security updates on October 21 at 14:00 UTC for two vulnerabilities, each officially rated 9.2 under CVSS v4.0; administrators are urged to install the updates promptly. The PHP team has not yet published affected versions, technical details, or fixed releases, and says it may release earlier if details become public or active exploitation appears. Researchers at watchTowr describe the flaws as remote code execution vulnerabilities affecting PHP 5 through 8, report reproducing one, and say they have not observed exploitation; they withhold technical details until patches are available. Their reported CVSS 10.0 ratings and Thursday disclosure timing differ from PHP's official scores and schedule. PHP says full details will accompany the updates.

### Source excerpt

The PHP security team is warning administrators to prepare for emergency security updates tomorrow to address two critical vulnerabilities, as information about the flaws has reportedly leaked ahead of their scheduled disclosure. [...]

## Using AI to expand global access to reliable flood forecasts

DevFeed: [Using AI to expand global access to reliable flood forecasts](<https://devfeed.tech/articles/using-ai-to-expand-global-access-to-reliable-flood-forecasts-28566.md>)

Original publisher: [Read original article](<http://blog.research.google/2024/03/using-ai-to-expand-global-access-to.html>)

Author: Google AI (noreply@blogger.com)

Published: 2024-03-20T16:06:00Z

Content type: article

Language: en

Sources: [Google Research](<https://devfeed.tech/sources/google-research.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Climate / Weather / Ocean Modeling](<https://devfeed.tech/topics/climate-weather-ocean-modeling.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [africa](<https://devfeed.tech/tags/africa.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [android](<https://devfeed.tech/tags/android.md>), [asia](<https://devfeed.tech/tags/asia.md>), [climate](<https://devfeed.tech/tags/climate.md>), [climate-change](<https://devfeed.tech/tags/climate-change.md>), [data](<https://devfeed.tech/tags/data.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [ecmwf](<https://devfeed.tech/tags/ecmwf.md>), [environment](<https://devfeed.tech/tags/environment.md>), [europe](<https://devfeed.tech/tags/europe.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [global](<https://devfeed.tech/tags/global.md>), [google](<https://devfeed.tech/tags/google.md>), [google-research](<https://devfeed.tech/tags/google-research.md>), [google-search](<https://devfeed.tech/tags/google-search.md>), [hub](<https://devfeed.tech/tags/hub.md>), [machine](<https://devfeed.tech/tags/machine.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>)

### AI overview

Google Research reports that machine learning models trained on streamflow records from 5,680 gauged watersheds can forecast floods in ungauged basins, where gauge data are unavailable. Its two-stage LSTM model combines historical and forecast weather with watershed characteristics and produces probabilistic river-flow predictions. In comparisons with GloFAS version 4, the model achieved reliability at four- to five-day lead times similar to or better than GloFAS nowcasts, and performed better on larger, rarer events by the article's reported precision and recall measures. The work supports Flood Hub forecasts up to seven days ahead across river reaches in more than 80 countries. The authors note that coverage still needs to expand, including for flash and urban floods.

### Source excerpt

Posted by Yossi Matias, VP Engineering & Research, and Grey Nearing, Research Scientist, Google Research Floods are the most common natural disaster, and are responsible for roughly $50 billion in annual financial damages worldwide. The rate of flood-related disasters has more than doubled since the year 2000 partly due to climate change. Nearly 1.5 billion people, making up 19% of the world's population, are exposed to substantial risks from severe flood events. Upgrading early warning systems to make accurate and timely information accessible to these populations can save thousands of lives per year. Driven by the potential impact of reliable flood forecasting on people's lives globally, we started our flood forecasting effort in 2017. Through this multi-year journey, we advanced research over the years hand-in-hand with building a real-time operational flood forecasting system that provides alerts on Google Search, Maps, Android notifications and through the Flood Hub. However, in order to scale globally, especially in places where accurate local data is not available, more research advances were required. In "Global prediction of extreme floods in ungauged watersheds", published in Nature, we demonstrate how machine learning (ML) technologies can significantly improve global-scale flood forecasting relative to the current state-of-the-art for countries where flood-related data is scarce. With these AI-based technologies we extended the reliability of currently-available global nowcasts, on average, from zero to five days, and improved forecasts across regions in Africa and Asia to be similar to what are currently available in Europe. The evaluation of the models was conducted in collaboration with the European Center for Medium Range Weather Forecasting (ECMWF). These technologies also enable Flood Hub to provide real-time river forecasts up to seven days in advance, covering river reaches across over 80 countries. This information can be used by people, communi