POLAR: A Per-User Association Test in Embedding Space

Wagner Meira, Gisele Pappa, Virgilio Almeida, Arthur Chagas, Pedro Bento, Yan Aquino, Arthur Buzelin, Victoria Estanislau, Samira Malaquias, Pedro Robles Dutenhefner

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• pedroaugtb/POLAR-A-Per-User-Association-Test-in-Embedding-Space

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Most intrinsic association probes operate at the word, sentence, or corpus level, obscuring author-level variation. We present POLAR (Per-user On-axis Lexical Association Report), a per-user lexical association test that runs in the embedding space of a lightly adapted masked language model. Authors are represented by private deterministic tokens; POLAR projects these vectors onto curated lexical axes and reports standardized effects with permutation pvalues and Benjamini-Hochberg control. On a balanced bothuman Twitter benchmark, POLAR cleanly separates LLMdriven bots from organic accounts; on an extremist forum, it quantifies strong alignment with slur lexicons and reveals rightward drift over time. The method is modular to new attribute sets and provides concise, per-author diagnostics for computational social science. All code is publicly available at https://github.com/pedroaugtb/POLAR-A-Per-User-Association-Test-in-Embedding-Space.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.15950")
get_code_for_paper("2603.15950")
have("2603.15950")

Connect an agent — have() is free.