AI Paper Atlas

Research map / Large language models / Agents, code and math

STAND: Self-Aware Precondition Induction for Interactive Task Learning

Daniel Weitekamp, Glen R Smith, Ken Koedinger, Christopher J. MacLellan

ICML 2026 · Large language models › Agents, code and math · approach: Reasoning benchmarks and platforms · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hierarchical shrinkage to STAND (ablation)STAND · Synthetic precondition datafinal holdout accuracy %: 90.0 -> 92.8Improved
add hierarchical shrinkage to decision tree (ablation)Decision Tree · Synthetic precondition datafinal holdout accuracy %: 88.6 -> 87.81No clear effect
add hierarchical shrinkage to STAND (ablation)STAND · Synthetic precondition datafalse positive reoccurrence rate %: 2.6 -> 2.2Improved
add hierarchical shrinkage to STAND (ablation)STAND · Synthetic precondition dataBrier Score: 0.0046 -> 0.0029Improved
add hierarchical shrinkage to STAND (ablation)STAND · Synthetic precondition dataExpected Calibration Error: 0.147 -> 0.123Improved
add hierarchical shrinkage to decision tree (ablation)Decision Tree · Synthetic precondition datafalse positive reoccurrence rate %: 7.3 -> 8.9Hurt
use STAND space-of-classifiers instead of decision treedecision tree learner · Synthetic precondition datafalse positive reoccurrence rate %: 7.3 -> 2.6Improved
use STAND instead of ensembles for certainty scoresSTAND · Synthetic precondition dataproductive monotonicity: 60-70% vs not much higher than 50%Improved
use STAND with hierarchical shrinkage for mislabel detection with few examplesSTAND (h.s.) · Mislabeled sample detection, 20 examplestop-1 detection rate %: 18.0 -> 37.8 (vs XGBoost)Improved
use STAND on large noisy UCI dataSTAND · 6 UCI datasets (mean)test accuracy %: 89.18 vs 89.12 (tree), 89.67 (RF)No clear effect
use STAND with hierarchical shrinkage on real ITL tasksSTAND (h.s.) · Multi-column Addition (AI2T)final holdout accuracy %: 95.4 -> 99.43Improved

Later papers that compared with this method

1 later accepted paper reports STAND as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy