AI Paper Atlas

Research map / Time series / Causal and generative time series

ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation

Shaocheng Lan, Shuqi Gu, Zhangzhi Xiong, Kan Ren

ICML 2026 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
evaluate condition adherence separately from generation fidelityConTSG-Bench evaluation · overall ranking of 11 modelsaverage rankImproved
use text conditioning instead of attribute or label conditioningconditional time series generators · ConTSG-Bench overall rankingaverage rankMixed
use conceptual instead of morphological conditions (ablation)conditional generators · PTB-XLDTW / CRPSNo clear effect
use conceptual instead of morphological conditions (ablation)conditional generators · WeatherDTW / CRPSImproved
text-conditioned generators versus naive retrieval baseline on segment-level patternstext-conditioned generators · Synth-U shapelet joint accuracyjoint accuracyMixed
increase candidate pool size for segment retrieval (ablation)text-conditioned generators · TelecomTS-SegmentAcc@1Hurt
segment-level temporal order controlall evaluated generators · TelecomTS-Segmenttemporal order accuracyNo clear effect
move test conditions from near to far from training attribute combinations (ablation)most generators · compositional generalization (Hamming distance kNN)normalized retrieval accuracyHurt
stronger condition adherence (e.g. VerbalTS) under novel combinationsVerbalTS · compositional generalizationnormalized retrieval accuracyMixed
train downstream classifier on generated instead of real dataconditional generators · downstream attribute classificationdrop rateMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy