13 papers
More Reader Data or a Better Teacher? Updating a Model of Crowd Highlights in Late 2026
Kazuki Nakayashiki, Keisuke Watanabe
A model trained on readers' highlights can show a newcomer where earlier readers converged on a page, even on pages with few readers. A year of stronger language models suggests tw…
Random projection with linear equalities and inequalities
Santanu S. Dey, Jingye Xu
Random projection is a preprocessing technique for optimization that reduces the number of linear equality constraints by replacing them with random linear combinations while appro…
Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory
Kazuki Nakayashiki
A model that inherits one-line memories may pull one archived source record before acting; a directive in the store can steer that pull: a pointer, a criterion or both. Across sixt…
When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory
Kazuki Nakayashiki
Provenance links keep the evidence behind an inherited belief reachable; an agent with a verification budget must still choose which links to inspect. We study a consolidated memor…
Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?
Kazuki Nakayashiki, Keisuke Watanabe
A benchmark score means nothing without knowing what a trivial method achieves and what the best possible method could achieve. We construct both bounds for a task with a rare kind…
Language Models Agree With Each Other, Not With Readers
Kazuki Nakayashiki, Keisuke Watanabe
Claims that language models homogenise are usually measured against human judgements collected for the study, which makes the human side an artifact of the design: a crowdworker gi…
Measuring Alignment With Reader Highlights Net of Position and Length
Kazuki Nakayashiki, Keisuke Watanabe
Context compression discards most of a document before a language model reads it, and is normally evaluated by downstream task accuracy - which makes another model the judge of wha…
Trait, Not State: The Durability of Reading Identity in Social Highlighting
Kazuki Nakayashiki, Keisuke Watanabe
Prior work on a social web highlighter located individuality in selection -- which documents a person chooses to highlight -- but measured it cross-sectionally. We ask the temporal…
The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience
Kazuki Nakayashiki, Keisuke Watanabe
A social highlighter's most useful signal -- which passages a crowd of readers marks -- exists only for documents people have already read. Can the aggregate crowd salience of a do…
Factions Within, Uncertain Across: Within-Document Reader Sub-Groups in Social Highlighting
Kazuki Nakayashiki, Keisuke Watanabe
When many people highlight the same document, is the crowd a single consensus, or is it internally structured into reader sub-groups that mark different things -- and is that struc…
Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting
Kazuki Nakayashiki, Keisuke Watanabe
Does personalizing what a reader sees pay off, and where does it stop? Using a social web highlighter and a co-readership identity control (the same document highlighted by many us…
Personal Salience: Highlighting Is Social, but Individuality Lives in Selection
Kazuki Nakayashiki, Keisuke Watanabe
Social highlighters let people mark passages that matter to them. We ask how much of an individual is recoverable from these naturalistic traces, using a co-readership identity con…
Disentangling Answer Engine Optimization from Platform Growth: A Log-Based Natural Experiment on ChatGPT Referral Traffic
Keisuke Watanabe, Kazuki Nakayashiki
Large language model (LLM) "answer engines" such as ChatGPT now send measurable referral traffic to the open web, and a practice analogous to search engine optimization, here calle…