A closed-form sample size correction k^(α, β, t0) for always-valid inference that achieves target power within ~3pp in Gaussian simulations across three boundary families and saves 8-20% versus the last-point rule.
Detecting social me- dia manipulation in low-resource languages
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DysLexLens is a dictionary-filtered, KG-augmented LLM pipeline that turns dyslexia-related forum posts into traceable answers to 30 questions with RAGAS and robustness metrics plus qualitative hallucination checks.
Cross-lingual analysis of 1.76M Singapore comments finds culturally specific hate targets but shared binding moral grammar and threat frames across languages.
citing papers explorer
-
A closed-form sample size correction for always-valid inference with optional stopping
A closed-form sample size correction k^(α, β, t0) for always-valid inference that achieves target power within ~3pp in Gaussian simulations across three boundary families and saves 8-20% versus the last-point rule.
-
DysLexLens: A Low-Resource LLM Framework for Analysing Dyslexic Learners Insights from Online Forums
DysLexLens is a dictionary-filtered, KG-augmented LLM pipeline that turns dyslexia-related forum posts into traceable answers to 30 questions with RAGAS and robustness metrics plus qualitative hallucination checks.
-
Cultural Targets, Structural Frames, Binding Morals: A Cross-Lingual Audit of Online Hate in Multicultural Singapore
Cross-lingual analysis of 1.76M Singapore comments finds culturally specific hate targets but shared binding moral grammar and threat frames across languages.