Unmediated pen input introduced new pen-specific barriers: lack of visual feedback on referential intent and high interaction cost of handwriting complex queries¶

Claim · All claims
Evidence · 2 studies · 2 design r3 · q3
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Study 1 participants lacked visual feedback to confirm whether their intended targets were accurately captured, occasionally producing irrelevant responses. → ref-feedback q3 i? Handwriting lengthy, structured Knowledge-based queries was physically burdensome and cognitively demanding, with recognition anxiety. → express-cost

Evidence¶

ref-feedback¶

Jeongmin Rhee, Changhee Lee, Hyunwoo Kim, Kiroong Choe, Bohyoung Kim, Sungahn Ko, and Jinwook Seo. 2026. Penquiry: A Pen-based Interactive In-situ Q&A System Leveraging LLMs. https://arxiv.org/abs/2609.19870 doi:10.48550/arxiv.2609.19870

q3 · i? · design · r3

Qualitative findings from Study 1 (N=16) interviews; P14 reported an underline producing an irrelevant answer, and P1, P15 and P16 reported misaligned referential intent. The authors conclude explicit visual grounding is essential for verifying captured targets.

"Partici- pants noted a critical lack of visual feedback to confirm whether their intended targets were accurately captured, occasionally re- sulting in irrelevant system responses."

express-cost¶

Jeongmin Rhee, Changhee Lee, Hyunwoo Kim, Kiroong Choe, Bohyoung Kim, Sungahn Ko, and Jinwook Seo. 2026. Penquiry: A Pen-based Interactive In-situ Q&A System Leveraging LLMs. https://arxiv.org/abs/2609.19870

q3 · i? · design · r3

Study 1 qualitative finding on the Expressive Barrier in pen-based inquiry: participants formulating Knowledge-based questions reported physical and cognitive burden of handwriting plus recognition anxiety that the system might fail to digitize their text.

"Those who engaged in complex inquiry reported that hand- writing lengthy, structured queries was both physically burdensome and cognitively demanding."

Discussion¶

Related Claims¶

• In Study 2, Content Snapping's immediate visual confirmation resolved learners' referential uncertainty about system recognition — related
• Pen input supported deictic referencing: 85% of V1 queries contained at least one visible pen mark, and ease of referencing improved significantly over the baseline — related
• Learners using standard keyboard-based LLM workflows during pen-based study face a Referential Barrier and an Expressive Barrier — related
• In Study 1, Penquiry V1 reduced physical demand and better maintained learning flow, and received higher TAM ratings, than a keyboard baseline — related