Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict? Paper • 2608.01704 • Published 2 days ago • 1
Language Models Agree With Each Other, Not With Readers Paper • 2607.29274 • Published 5 days ago • 1
Measuring Alignment With Reader Highlights Net of Position and Length Paper • 2607.27739 • Published 6 days ago • 1
The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience Paper • 2606.11654 • Published Jun 11 • 1
Trait, Not State: The Durability of Reading Identity in Social Highlighting Paper • 2606.12904 • Published Jun 11 • 1
Factions Within, Uncertain Across: Within-Document Reader Sub-Groups in Social Highlighting Paper • 2606.11613 • Published Jun 10 • 1
Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting Paper • 2606.10398 • Published Jun 9 • 1
Disentangling Answer Engine Optimization from Platform Growth: A Log-Based Natural Experiment on ChatGPT Referral Traffic Paper • 2606.04362 • Published Jun 3 • 1
Personal Salience: Highlighting Is Social, but Individuality Lives in Selection Paper • 2606.09024 • Published Jun 8 • 1