Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,982 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Feb 202219922001200920172026
7 results for “Overcorrection”
Any Axes Are Allowed: A Characteristic-Axis Integral Diagnosis of Factor Modelsq-fin.GN

The paper diagnoses factor models using characteristic axes and zero-curve restrictions.

problem Tackles systematic sign reversals and overcorrections in factor model pricing errors.
method Extends cap-axis integral diagnostic to general characteristic axes, measuring pricing errors as bridge-alpha curves.
result Axis-level pricing errors are nearly orthogonal to maximum-Sharpe gains, showing systematic sign reversals and overcorrections.
factor modelscharacteristic axeszero-curve restrictionspricing errorssign reversals
2026-07-06abs ↗pdf ↗
Any Axes Are Allowed: A Characteristic-Axis Integral Diagnosis of Factor Modelsq-fin.GN

The paper diagnoses factor-model pricing errors using characteristic axes and bridge-alpha curves.

problem Tackles systematic sign reversals and overcorrections in factor-model pricing errors.
method Extends cap-axis integral diagnostic to characteristic axes, measures pricing errors as bridge-alpha curves, and uses a predetermined characteristic order to generate zero-curve restrictions.
result Axis-level pricing errors are nearly orthogonal to maximum-Sharpe gains, showing significant sign reversals and overcorrections.
factor modelspricing errorscharacteristic axesbridge-alpha curvessign reversals
2026-07-06abs ↗pdf ↗
Any Axes Are Allowed: A Characteristic-Axis Integral Diagnosis of Factor Modelsq-fin.GN

This paper diagnoses factor-model pricing errors using a new method.

problem Measuring pricing errors in factor models with general characteristic axes.
method Developed a method to measure factor-model pricing errors as bridge-alpha curves, using a predetermined characteristic order and prefix portfolios.
result Adding a counterpart factor flips the curve's sign on every axis, but only HML and CMA overcorrect enough to be rejected.
factor modelspricing errorscharacteristic axesintegral diagnosisCRSP data
2026-07-06abs ↗pdf ↗
Bridging the Gap between Training and Inference for Neural Machine Translationcs.CL

Improves NMT by sampling context from predicted sequence during training.

problem Error accumulation and overcorrection in NMT due to mismatched training and inference contexts.
method Samples context words from both ground truth and predicted sequences during training.
result Significant improvements on multiple datasets, including Chinese->English and WMT'14 English->German.
Neural Machine TranslationContext SamplingError AccumulationOvercorrectionTraining Inference Discrepancy
2019-06-06abs ↗pdf ↗
Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncs.LG

SCORE resolves the robustness vs accuracy trade-off by redefining robust error.

problem The inherent trade-off between robustness and accuracy in adversarial training.
method SCORE defines local equivariance as the ideal robust behavior, leading to a new robust error metric.
result SCORE reconciles robustness and accuracy, improving model performance on RobustBench.
adversarial trainingrobustnessaccuracy trade-offlocal equivariancerobust error
2022-02-21abs ↗pdf ↗
Causality-Inspired Safe Residual Correction for Multivariate Time Seriescs.LG

CRC improves multivariate forecasting accuracy without risking performance degradation.

problem Systematic errors and lack of guarantees in multivariate forecasters.
method CRC uses a causality-inspired encoder and hybrid corrector with a safety mechanism.
result CRC consistently improves accuracy and ensures high non-degradation rates.
multivariate forecastingresidual correctionsafety gapsystematic errorspost-hoc correction
2025-12-27abs ↗pdf ↗
Bias in the Loop: How Humans Evaluate AI-Generated Suggestionscs.HC

Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.

problem Cognitive biases affect human-AI collaboration, leading to suboptimal outcomes.
method Randomized experiment with 2,784 participants, manipulating AI suggestion quality, task burden, and financial incentives.
result Individual attitudes toward AI are the strongest predictor of performance, influencing accuracy and overcorrection.
human-AI collaborationcognitive biasestask designindividual attitudesAI evaluation
2025-09-10abs ↗pdf ↗