AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions

David Bieber, Rishab Goel, Dan Zheng, Hugo Larochelle, Daniel Tarlow

ICLR 2023 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 2 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
Use an interpreter-inspired IPA-GNN instead of a generic TransformerRuntime error prediction · Python Runtime Errors balanced testaccuracy: 63.6 -> 68.3Improved
Add external resource descriptions as docstrings (ablation)GGNN, Transformer, and LSTM · Python Runtime Errors balanced testaccuracy: 62.8 -> 68.3; 63.6 -> 67.3; 66.1 -> 68.1Improved
Add a resource description as a docstring (ablation)IPA-GNN · Python Runtime Errors balanced testweighted error F1: 53.8 -> 62.2Improved
Add a resource description as a docstring (ablation)Exception IPA-GNN · Python Runtime Errors balanced testweighted error F1: 53.3 -> 63.5Improved
Incorporate the resource description directly with cross-attention rather than as a docstring (ablation)Exception IPA-GNN · Python Runtime Errors balanced testaccuracy: 71.6 -> 73.8Improved
Incorporate the resource description directly with cross-attention rather than as a docstring (ablation)IPA-GNN · Python Runtime Errors balanced testaccuracy: 71.4 -> 72.0No clear effect
Use FiLM instead of docstring resource input (ablation)Exception IPA-GNN · Python Runtime Errors balanced testweighted error F1: 63.5 -> 59.8Hurt
Add exception-handling transitions to the IPA-GNN (ablation)IPA-GNN · Python Runtime Errors balanced testaccuracy: 68.3 -> 68.7No clear effect
Add a resource description (ablation)Local MIL Transformer · Python Runtime Errors balanced testlocalization accuracy: 33.0 -> 48.9Improved
Add a resource description (ablation)Global MIL Transformer · Python Runtime Errors balanced testlocalization accuracy: 48.2 -> 48.8No clear effect
Model exception handling and use execution-derived exception provenance to localize errors without location labelsException IPA-GNN · Python Runtime Errors balanced testlocalization accuracy: 48.2 -> 50.8Improved
Add cross-attention resource descriptions (ablation)Exception IPA-GNN · Python Runtime Errors balanced testlocalization accuracy: 50.8 -> 68.8Improved

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