aiqbench analysis
This paper introduces standardized benchmark datasets for Lead-Lag Forecasting, addressing a critical gap in the time-series community by providing high-volume, long-horizon traces from arXiv and GitHub. By rigorously validating lead-lag dynamics and avoiding survivorship bias, the work establishes a robust empirical foundation for modeling delayed impact patterns in social and usage data. This resource enables systematic exploration of novel forecasting paradigms that were previously fragmented across disparate research efforts.
Benchmark Datasets for Lead-Lag Forecasting on Social Platforms
arXiv:2511.03877v2 Announce Type: replace Abstract: Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are followed, sometimes months or years later, by higher impact like citations, sales, or reviews. We formalize this setting as Lead-Lag Forecasting (LLF): given an early usage channel (the lead), predict a correlated but temporally shifted outcome channel (the lag). Despite the ubiquity of such patterns, LLF has not been treated as a unified forecasting problem within the time-series community, largely due to the absence of standardised datasets. To anchor research in LLF, here we present two high-volume benchmark datasets: arXiv (accesses -> citations of 2.3M papers) and GitHub (pushes/stars -> forks of 3M repositories). Our datasets provide ideal testbeds for lead-lag forecasting, by capturing long-horizon dynamics across years, spanning the full spectrum of outcomes, and avoiding survivorship bias in sampling. We documented all technical details of data curation and cleaning, verified the presence of lead-lag dynamics through statistical and classification tests, and benchmarked parametric and non-parametric baselines for regression. Our study establishes LLF as a novel forecasting paradigm and lays an empirical foundation for its systematic exploration in social and usage data.
Authors:Kimia Kazemian (1), Zhenzhen Liu (1), Yangfanyu Yang (2), Katie Luo (3), Shuhan Gu (1), Audrey Du (1), Xinyu Yang (2), Jack Jansons (1), Kilian Q. Weinberger (1), John Thickstun (1), Yian Yin (2), Sarah Dean (1) ((1) Department of Computer Science, Cornell University (Ithaca, USA), (2) Department of Information Science, Cornell University (Ithaca, USA), (3) Department of Computer Science, Stanford University (Palo Alto, USA))
Abstract:Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are followed, sometimes months or years later, by higher impact like citations, sales, or reviews. We formalize this setting as Lead-Lag Forecasting (LLF): given an early usage channel (the lead), predict a correlated but temporally shifted outcome channel (the lag). Despite the ubiquity of such patterns, LLF has not been treated as a unified forecasting problem within the time-series community, largely due to the absence of standardised datasets. To anchor research in LLF, here we present two high-volume benchmark datasets: arXiv (accesses -> citations of 2.3M papers) and GitHub (pushes/stars -> forks of 3M repositories). Our datasets provide ideal testbeds for lead-lag forecasting, by capturing long-horizon dynamics across years, spanning the full spectrum of outcomes, and avoiding survivorship bias in sampling. We documented all technical details of data curation and cleaning, verified the presence of lead-lag dynamics through statistical and classification tests, and benchmarked parametric and non-parametric baselines for regression. Our study establishes LLF as a novel forecasting paradigm and lays an empirical foundation for its systematic exploration in social and usage data.
11 pages, 8 figures, includes supplementary material (6 pages, 5 figures). Accepted at ACM SIGKDD 2026 (KDD '26). Code and data: this https URL
Machine Learning (cs.LG)
arXiv:2511.03877 [cs.LG]
(or arXiv:2511.03877v2 [cs.LG] for this version)
https://doi.org/10.1145/3770855.3817523 DOI(s) linking to related resources
Full text under the publisher's open licence · 299 words
Related coverage
FinVerse: Financial Time-Series Benchmark
arXiv · Aug 5, 2026
Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance
arXiv · Oct 8, 2026
FETS Benchmark: Foundation Models Enable Scalable and Generalizable Energy Time Series Forecasting
arXiv · Jul 21, 2026
WPBench: A Comprehensive Benchmark for Wind Power Forecasting
arXiv · Sep 22, 2026