arXiv Machine Learning August 4, 2026 By Xizhe Zhang

The Label Defines the Timescale: Trait-State Limits of Temporal-Aggregate Learning

Read the original on arXiv Machine Learning →

arXiv:2608. 01587v1 Announce Type: cross Abstract: Machine-learning benchmarks often pair a label that aggregates a long temporal horizon with input observed through one or a few short windows.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Jun 17

When Dynamics Models Read the Wrong Time Steps: Label-Free Event Credit Re-Anchoring for Robust Global Readouts

arXiv:2606. 17572v1 Announce Type: new Abstract: Learned dynamics models often answer global physical questions, such as fault severity or impact stiffness, by pooling a per-step feature sequence into one readout vector.

By Yifan Wang

arXiv Machine Learning

Sep 1

Behavioral Latency as Weak Event-Time Supervision for EEG Reaction-Time Decoding

arXiv:2608.29428v1 Announce Type: new Abstract: Single-trial EEG analyses are often organized around events and latencies, yet EEG-based reaction-time (RT) prediction is posed as scalar regression on...

By Anuar Aimoldin, Ayana Mussabayeva, Yedige Mussabayev, Xue Liu, Kun Zhang

safety

arXiv AI

Jun 15

Recovering Stranded Discrimination in Knowledge Tracing: Per-Item Bias Correction via Empirical-Bayes Shrinkage

arXiv:2606. 14123v1 Announce Type: cross Abstract: Deployed knowledge-tracing models are typically frozen after training, yet systematic per-item logit bias arises, from limited per-item expressivity in backbone architectures and from post-deployment shifts in item properties, degrading prediction quality.

By Xiaoran Yan, Cheng Tang, Atsushi Shimada

safety

arXiv AI

Aug 17

Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning

arXiv:2608. 13621v1 Announce Type: new Abstract: A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emission back to observation space.

By Yongchao Huang

rag

arXiv Machine Learning

Jun 16

Inference-Time Decision Calibration for Temporal Classification

arXiv:2606. 16034v1 Announce Type: new Abstract: Temporal classification errors are often treated as representation failures, but they can also arise from how available evidence is converted into decisions.

By Arthur Chagas, Arthur Buzelin, Yan Aquino, Pedro Bento, Gisele L. Pappa, Wagner Meira Jr., Cristiano Arbex Valle

arXiv Machine Learning

Jul 15

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking

arXiv:2607. 12735v1 Announce Type: new Abstract: Companion work showed the grokking delay is causally the time to form task-structured representations, injectable via a contrastive prior.

By Gunner Levi Howe

safety

One email a morning, machine-written

Related stories

When Dynamics Models Read the Wrong Time Steps: Label-Free Event Credit Re-Anchoring for Robust Global Readouts

Behavioral Latency as Weak Event-Time Supervision for EEG Reaction-Time Decoding

Recovering Stranded Discrimination in Knowledge Tracing: Per-Item Bias Correction via Empirical-Bayes Shrinkage

Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning

Inference-Time Decision Calibration for Temporal Classification

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking