Papers
arxiv:2608.29669

Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations

Published on Aug 30
· Submitted by
Marcus Gawronsky
on Sep 3
Authors:

Abstract

A language-model embedding field reconstructed via Wasserstein barycenters predicts peer-misalignment penalties more accurately than conventional weighting schemes.

Spatial return models take the interaction matrix as given and leave feedback uninterpreted. We construct a bandwidth-free field from firms' language-model article embedding distributions using target-anchored Wasserstein barycentric reconstruction. A quadratic exposure-adjustment problem maps feedback into a peer-misalignment penalty ratio. For 52 firms, the field, frozen from 2018-2022 news, yields a 2023-2026 penalty ratio of 3.46 (95% interval [2.89, 4.17]) and higher conditional quasi-likelihood than equal-weighted peer support or RBF weighting of the same distances. Joint penalty ratios for the barycentric and news co-mention fields are 2.33 and 0.86 with boundary calibrated tests which reject both exclusions.

Community

Paper author Paper submitter

While this work explores applications in Financial Ecometrics, it's bandwith-free barycentric operator offers a more general between modern language modelling and interprettable econometric and statistical techniques, by treating an entities' documents as empirical distributions and using methods from spatial regression to measure spatial interaction between semantic clouds. For machine learning and data science researchers and practitioners, this new insights into sentiment analysis, and other forecasting applications.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.29669
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2608.29669 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2608.29669 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2608.29669 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.