Publications

• Known-groups validity is not enough for evaluation-awareness detectors
  Ariel Arévalo-Alvarado, Antonio Badilla-Olivas · Agent Evaluation Science symposium, Fall 2026 (NYC) · 2026
• Multimodal Foundation Models for Zero-Shot User Activity Classification: An Exploratory Analysis of Trace Modalities
  Kenneth Villalobos-Solís, Emilia Víquez-Mora, Antonio Badilla-Olivas, Enrique Vílchez-Lizano, ^†Ariel Arévalo-Alvarado · IEEE JoCICI 2026 · 2026

^†Senior author

All publications →

Projects

• A Shared Corpus for Bribri
  2026-10-16 · University community service proposal: the Bribri materials of DIPALICORI in one open format
• Moral Licensing Comprehension: Measuring Flexibility of Social Prediction in LLMs
  2026-04-16 · Solo submission to the Google DeepMind/Kaggle "Measuring Progress Toward AGI" competition, Social Cognition track
• ClimateFact
  2025-06-14 · A RAG workflow for climate change fact verification

All projects →

Writing

All posts →