Bayesian plan recognition worked poorly in a goal-free interface because students often had no recognizable plan¶
Claim · All claims
Evidence · 1 study · associationalr1·q2
Currency · newest study 2015 · not yet checked against its sources · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Andes1's Bayesian plan recognition agreed with instructors on only 3 of 21 snapshots where instructors agreed, because most students appeared to have no recognizable plan. → VanLehn 2015
Evidence¶
VanLehn 2015¶
VanLehn, K. (2015). Reflections on Andes' Goal-free User Interface. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-015-0067-7
q2 · i? · associational · r1
Evaluation of Andes1's Bayesian plan recognition: 40 snapshots of students' work at help requests were shown to physics instructors, who indicated the goal they thought students needed help on. Andes "agreed with the instructors on only 3" of the 21 agreement snapshots; instructors judged most students had no plan.
"Instructors disagree on 19 snapshots, but in 21 snapshots where they did agree, Andes agreed with the instructors on only 3 (V anLehn et al. 2005)."
Discussion¶
Related Claims¶
- LLMs and instructors agree broadly on where feedback belongs but diverge on exact sentence spans, with span overlap strongly goal-dependent and LLMs highlighting more of each essay — related
- Survey data indicate the ability signal had informational value, leading students to revise self-assessed ability and AP plans consistent with Bayesian learning — related
- Feedback givers agree on exact urgency tiers only about a fifth of the time, with most disagreements off by a single tier — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
plan-recognition-fails-goal-free-interface |
title |
Bayesian plan recognition worked poorly in a goal-free interface because students often had no recognizable plan |
description |
Bayesian plan recognition worked poorly in a goal-free interface because students often had no recognizable plan |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2015 |
generated |
by process:wiki-ingest on 2026-10-27 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — vanlehn-2015 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.