Resource

AI/Agent

• your-voice: A skill that learns your writing style from your own samples and revises AI drafts across three passes so they read like you, not generic AI.

• AInotator: Annotate computer-mediated discourse with LLMs to capture communicative acts, politeness strategies, and meta-acts. Supports multiple model backends and provides reproducible, theory-grounded annotations for large-scale CMC research.

• RLAM: Make jargon-laden scientific abstracts accessible to those without a college degree.

• NovEval: Assess scientific novelty in alignment with human evaluation.

Corpus

• Blog-1K: A redistributable English authorship identification benchmark with roughly balanced samples per author and fixed data splits (train/val/test), allowing for fair comparison among deep learning–based models.

• RAABT: The Reproducible Authorship Attribution Benchmark Tasks include five tasks for attributing authorship of contemporary non-fiction American English prose. Fixed training/testing splits prevent accuracy inflation from homogeneous corpora.

• Cross-Register Authorship Attribution Corpus: Contains writings from eight authors who wrote in both vernacular and classical Chinese. With 4.2 million Chinese characters, it supports authorship identification research.

Python Package

• functionwords: Provides curated lists of function words in modern English and both modern and classical Chinese.

• writeprints-static: Extracts the Writeprints-static feature set, useful for authorship attribution studies.

Other

• Unofficial IU Poster TeX Template: An unofficial LaTeX poster template for Indiana University.