Peer answering in the hybrid support system was fast where it occurred: 70.3% of peer-answered queries closed within one hour, against 1.9% of administrator-answered and 14.8% of script-closed queries¶

Claim · All claims
Evidence · 1 study (2 entries) · associational r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Peer-answered queries closed far faster than administrator- or script-handled ones: 70.3% of peer-answered queries closed within one hour of raising, against 1.9% answered directly by an administrator and 14.8% closed by script. → Gupta 2026 q2 i? Peer resolution was broadly shared across the cohort: 285 peer resolutions were authored by 132 participants, of whom 101 also raised queries, at a Gini of 0.414 across authors. → Gupta 2026 (2)

Evidence¶

Gupta 2026¶

Gupta, J., Ayinampudi, P., Aditya B.M.V., Hegade, P., Sharma, R., Sharma, S., Meenakshi, V., Iyengar, S.R.S. (2026). What Students Actually Ask: Demand Structure and Automation Potential in a Hybrid Support System. arXiv:2609.38967. https://arxiv.org/abs/2609.38967 doi:10.48550/arxiv.2609.38967

q2 · i? · associational · r2

Dispatch and timing analysis of the nine-week operational record (N=4,093), reporting medians and upper percentiles by resolution path because timing distributions are heavily right skewed. Peer paths handled the smallest volume shares (5.5% and 1.5%).

"Within one hour of raising, 70.3% of peer answered queries hadclosed,against1.9%ofthoseanswereddirectlybyanadministratorand14.8%ofthoseclosedbyscript."

Gupta 2026 (2)¶

Gupta, J., Ayinampudi, P., Aditya B.M.V., Hegade, P., Sharma, R., Sharma, S., Meenakshi, V., Iyengar, S.R.S. (2026). What Students Actually Ask: Demand Structure and Automation Potential in a Hybrid Support System. arXiv:2609.38967. https://arxiv.org/abs/2609.38967. doi:10.48550/arxiv.2609.38967

q2 · i? · associational · r2

Attribution analysis of resolver identity across the deployment record. Peer answers passed through administrator acceptance and senior approval before release; peer identity was held separately from the approving staff member's email in 61 of 61 and 224 of 225 peer-typed records.

"Peer typed records carry a peer identifier in 61 of 61peer_genuine_approveand 224 of 225 peer_answered_no_formal_approvalrecords, while the resolver email field holds the approving staff member; only three of the administrator's 1,024 records are peer typed. Peer resolutions number 285, authoredby132participantsofwhom101alsoraisedqueries,ataGiniof0.414acrossauthors."

Discussion¶

Related Claims¶

• Operational resolution records require workflow-semantic checks before interpretation: one administrator accounts for 72.7% of attributed human resolutions, most administrative closures occur in synchronous bulk events, and the accepted_derived field encodes resolver identity rather than acceptance — related
• Student chatbot queries were overwhelmingly task-oriented initial inquiries, dominated by definition requests and pasted assignment questions rather than iterative critique — related
• Only 8.0% of queries reaching a person duplicated existing corpus content, suggesting the knowledge base was already well used — related