xPST

Product or Programme · All products and programmes
Evidence · 6 claims (4 for, 1 mixed, 1 against) · 1 study (1 design), q2 · 1 of 1 report an effect size · 6 claims rest on one study

Description

xPST is an authoring system and tutor engine developed by Stephen B. Gilbert and colleagues that lets instructional designers create embedded, model-tracing-like tutors for third-party software through TutorLink plug-ins and instruction files.

Components

• The xPST architecture: a model-tracing-like tutor engine overlaid on third-party software via TutorLink plug-ins and a plain-text instruction file: xPST is an authoring system that produces tutors behaving like model-tracing tutors without a formal cognitive model: authors write an xPST Instruction File with Mappings, Sequence, and Feedback sections, and the xPST Tutor Engine checks each learner action and returns hints, just-in-time messages, or error marking. TutorLink plug-ins mediate between the engine and third-party applications, with a Listener Module that "eavesdrops on user 's actions" and a Presentation Module that displays feedback in the host interface. The article presents this as a way to let instructional designers build embedded tutors on existing software. (Stephen B. Gilbert et al. (2015))

Claims

• Students tutored by an xPST-created web statistics tutor (xSTAT) scored higher on exam transfer problems than untutored students [+M]
• In the Paint.NET embedded-tutor comparison, task performance differed among book, movie, and ITS groups, with the book group scoring significantly higher than the movie group and the ITS group in between [~M]
• Ten non-programmer graduate students quickly learned early Web xPST and produced mostly high-quality tutors, with authoring time dropping across successive tasks [+W]
• Five non-programmers authoring with final Web xPST produced 74 effective statistics tutors in a month, with coding a small share of total authoring time [+W]
• In a head-to-head comparison, xPST and CTAT both let non-programmers create high-caliber tutors, with no significant time differences by the third problem [+M]
• Paint.NET ITS users rated the system's usability significantly lower than book and movie condition students [-W]

Related Products and Programmes

• Web xPST

Key Sources

• Stephen B. Gilbert, Stephen B. Blessing, Enruo Guo. (2015). Authoring Effective Embedded Tutors: An Overview of the Extensible Problem Specific Tutor (xPST) System. Int J Artif Intell Educ 25:428–454. https://doi.org/10.1007/s40593-015-0045-0

Page metadata

Field	Value
type	product
id	xpst
title	xPST
description	xPST is an authoring system and tutor engine developed by Stephen B.
status	review
product_kind	software
generated	by process:settle-candidates on 2026-10-27
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.