AI Paper Atlas

Research map / Time series / Causal and generative time series

From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting

Xilin Dai, Zhijian Xu, Wanxu Cai, Qiang Xu

ICLR 2026 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting

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
increase number of scenarios N from 16 to 256 (ablation)TimePrism · ElectricityCRPS: 0.414 -> 0.162Improved
increase number of scenarios N from 256 to 625 (ablation)TimePrism · ElectricityCRPS: 0.162 -> 0.133Improved
increase number of scenarios N from 625 to 1024 (ablation)TimePrism · ElectricityCRPS: 0.133 -> 0.139No clear effect
increase number of scenarios N from 625 to 1024 (ablation)TimePrism · SolarDistortion: 0.101 -> 0.0917Improved
increase number of scenarios N from 1 to 625 (ablation)TimePrism · SolarCRPS: 0.199 -> 0.0852Improved
increase number of scenarios N from 1 to 16 (ablation)TimePrism · ElectricityDistortion: 0.733 -> 0.911Hurt
use explicit scenario probabilities with a probability head instead of resampling from fixed set (TimeMCL)TimePrism vs TimeMCL · ElectricityCRPS: 0.370 -> 0.133Improved
use TimePrism with only 16 scenarios versus TimeMCL (16 hypotheses)TimePrism-16 · SolarCRPS: 0.290 -> 0.137Improved
replace sampling with single-pass scenario generationTimePrism vs TimeGrad · Exchange inference, S=1inference FLOPs: 1.9 x 10^8 -> 5.1 x 10^5Improved
Winner-Takes-All reconstruction loss in place of full likelihoodTimePrism · Distortion across 5 datasetsDistortionImproved
TimePrism versus TACTiS-2 on WikipediaTimePrism · WikipediaCRPS: 0.484 -> 0.506Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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