hypedarhypedar
feedtrendsdiscovershowcasearchive
login
login
login
FeedTrendsDiscoverShowcaseArchiveDashboard
Submit Showcase

Trending now

Evaluation + Agents + Llm66Math + Games56Agents + Workflow56
View all trends →

hypedar

AI trend radar for developers. Catch emerging papers, repos, and discussions before the hype peaks.

AboutGitHubDiscord

By the makers of hypedar

Codepawl

Open-source tools for developers.

Explore our tools →
AboutPrivacyTermsX

© 2026 Codepawl

Built by Codepawl·© 2026

About·Terms·Privacy·Security

GitHub·Discord·X

feedtrendsdiscovershowcasearchive
← feed
arXiv13h ago
4.6

Fun-TSG: A Function-Driven Multivariate Time Series Generator with Variable-Level Anomaly Labeling

Pierre Lotte (EPE UT, IRIT), Andr\'e P\'eninou (UT2J, IRIT-SIG, IRIT), Olivier Teste (IRIT-SIG, IRIT, UT2J, Comue de Toulouse)

View original ↗

Analysis

Viral velocity
low
Implementation gapYES
Novelty6/10
Categorypaper
Topics
time-seriesanomaly-detectiondata-gen

Opportunity Brief

Build a synthetic data generator for multivariate time series with embedded anomaly labels. This fills the gap for developers building and evaluating time-series monitoring tools.

Suggested repo: ts-anomalist

"Generate endless, labeled multivariate anomaly datasets for your detection models."

Estimated effort: 30h