arXiv Machine Learning
Sep 18
When Does Retrieval Help Time-Series Forecasting?
arXiv:2609. 20193v1 Announce Type: new Abstract: Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry.
What Does History Add? Calendar Controls and Information-Timing Audits for University Trajectory Forecasting
The study audits the predictive value of historical summaries in a rule-based university trajectory simulator. Seventeen ridge specifications and persistence models compare current plans, past-state and past-plan summaries, and calendar-only history-length indicators across training, validation, and two family-held-out evaluations, reconstructing 16,750 routes and 804,000 monthly records. Results show modest RMSE improvements with six-month history versus current-state prediction, but negligible differences from a length-only control, with uncertain generalization to all-history summaries and notable violations in fatigue predictions.
Related stories
arXiv AI
Aug 18
Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence
arXiv:2608. 14903v1 Announce Type: new Abstract: Quantitative forecasts of frontier artificial intelligence often connect dated targets to trends in benchmark scores, training compute, release time, or expert belief.
arXiv AI
Jul 23
CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning
arXiv:2607. 20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops.
arXiv Machine Learning
Jul 22
HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks
arXiv:2607. 18867v1 Announce Type: new Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks.
arXiv AI
Sep 4
RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting
RATL is a plug‑in method for multivariate time‑series forecasting that uses a frozen base forecaster to build a memory of its historical forecast residuals. During inference, RATL retrieves residual trajectories from similar past contexts and employs a set‑aware router to combine them, providing learned feedback correction. Experiments demonstrate that this residual‑retrieval approach improves the performance of the base forecaster across various benchmarks and backbones.
arXiv Machine Learning
Sep 25
Time-Series Foundation Models That Understand Data Revisions
The paper introduces VINTAGE-TS, a revision‑aware time‑series foundation model that separates observation time from information‑availability time. It predicts both the next period’s first‑published value and the value available after a fixed delay, maintaining a joint distribution to capture their dependence and uncertainty. The authors provide a detailed evaluation protocol, software tools for validity‑interval reconstruction and delayed‑label filtering, and a synthetic demonstration with a 25‑configuration sensitivity suite to illustrate performance variability and the impact of hindsight contamination.
arXiv Machine Learning
Oct 8
When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screen
The study investigates whether a neural network’s training history can better predict its future learning than its current state. Using small multilayer perceptrons trained under 42 different history regimes, the authors measured future learning at four checkpoints via a short probe that replicated the network for 100 updates on a new task. Results show that a low‑dimensional history state does not outperform a calibrated model of the current state for short‑term prediction, but in a companion screen of 1,560 synthetic regression runs, history models forecast final error better than current validation error after 12 epochs and remain comparable until 48 epochs.
arXiv Machine Learning
Aug 18
Do Language Models Consistently Encode the Current Year?
arXiv:2608. 15507v1 Announce Type: cross Abstract: A consistent concept of the current time is important for temporal reasoning, yet how language models represent the current time is not well understood.
arXiv AI
Jul 23
Predictive Extrema, Unprofitable Policies: An AI-Assisted Audit of Candle-Based Binance Spot Timing Models
arXiv:2607. 19453v1 Announce Type: cross Abstract: We audit whether candle-based machine-learning models can turn predictions of cryptocurrency extrema or short-horizon outcomes into positive Binance Spot paper policies after assumed costs.
arXiv AI
Oct 2
On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models
The paper introduces a formal framework and benchmark for time‑series world models (TSWMs) that separates state, actions, and exogenous inputs, and defines a new metric called mechanism consistency to evaluate whether model predictions move in the expected direction when actions change. Experiments on eight public datasets show that using a frozen latent prediction space and gated output fusion improves prediction accuracy, while prediction error and mechanism consistency often diverge, with the best‑performing models sometimes failing to exhibit consistent directional responses. Adding a directional supervision loss significantly boosts mechanism consistency without affecting mean‑absolute error, providing a practical recipe for building more reliable TSWMs.
arXiv Machine Learning
Sep 22
$t_0$: A Time-Series Foundation Model for Forecasting with Context
arXiv:2609.24559v1 Announce Type: new Abstract: We present $t_0$, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: $\texttt{t0-a...
arXiv Machine Learning
Sep 22
One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting?
arXiv:2609.23686v1 Announce Type: new Abstract: Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. W...