analiza aiqbench
This research introduces Event Signature Transfer (EST), a training-free, model-agnostic operator that constructs explicit forecast scenarios by scaling historical event signatures onto native predictions. By operating solely on output quantiles without accessing model internals, EST significantly reduces error metrics across multiple time-series forecasting architectures like Chronos and TimesFM. The method offers a practical advancement in handling imminent events with unknown shapes or timings, enhancing scenario planning capabilities for complex temporal data.
Event Signature Transfer: Model-Agnostic Forecast Scenario Construction from Historical Events
arXiv:2609.23074v1 Announce Type: cross Abstract: Forecasters often know an event is imminent but not the shape, size, or timing of its effect. We introduce Event Signature Transfer (EST), a training-free, model-agnostic operator that turns a completed past event into an explicit forecast scenario. EST removes a source event's own trend and seasonality, then scales and retimes the remaining event signature onto a native forecast, preserving the forecast's linked structure and reducing to it exactly at zero strength. Because it reads only output quantiles, EST applies to any quantile forecaster, with no training, no model internals, at transfer time. Across twelve real episodes and ten synthetic scenarios on Chronos-2, TimesFM-2.5 and Toto-2.0, manually configured EST reduces real-episode WQL by 21.7-90\% in-sample. On Chronos-2, it leads eleven of twelve matched comparisons against covariate conditioning, activation editing and raw replay. The operator builds a scenario; it does not estimate its likelihood.
Abstract:Forecasters often know an event is imminent but not the shape, size, or timing of its effect. We introduce Event Signature Transfer (EST), a training-free, model-agnostic operator that turns a completed past event into an explicit forecast scenario. EST removes a source event's own trend and seasonality, then scales and retimes the remaining event signature onto a native forecast, preserving the forecast's linked structure and reducing to it exactly at zero strength. Because it reads only output quantiles, EST applies to any quantile forecaster, with no training, no model internals, at transfer time. Across twelve real episodes and ten synthetic scenarios on Chronos-2, TimesFM-2.5 and Toto-2.0, manually configured EST reduces real-episode WQL by 21.7-90\% in-sample. On Chronos-2, it leads eleven of twelve matched comparisons against covariate conditioning, activation editing and raw replay. The operator builds a scenario; it does not estimate its likelihood.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2609.23074 [cs.AI]
(or arXiv:2609.23074v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.23074 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 240 cuvinte
Subiecte conexe
Deconfusing Corrigibility
AI Alignment Forum · 17 oct. 2026
Game-Theoretic Disempowerment: Loss of Control to Agencyless AI
LessWrong · 27 sept. 2026
The hard physics and complex economics of AI’s insatiable hunger for power
SiliconANGLE · 11 sept. 2026
DI Series: Serving Kimi-K3 MXFP4 Wide-EP Disaggregated on AMD Instinct MI300X and MI325X
AMD · 8 oct. 2026