AI Paper Atlas

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

Neural Attribution for Semantic Bug-Localization in Student Programs

Rahul Gupta, Aditya Kanade, Shirish Shevade

NeurIPS 2019 · Large language models › Agents, code and math · approach: Neural program synthesis and transpilation · 21 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 NBL instead of Tarantula-1 (one passing test)bug localization · Student C programs, top-10programs localized: 964 -> 1164Improved
use NBL instead of Ochiai-1 (one passing test)bug localization · Student C programs, top-1programs localized: 227 -> 294Improved
use NBL instead of Tarantula-*/Ochiai-* (all passing tests)bug localization · Student C programs, top-1 and top-5programs localized: top-1: 294 vs 311/385; top-10: 1164 vs 1141/1151Mixed
use NBL instead of syntactic diff-based approachbug localization · Student C programs, top-10programs localized: 623 -> 1164Improved
restrict k-means clustering (5 clusters) for baseline program search (ablation)NBL · Student C programslocalization accuracy: <0.5% change in every metricNo clear effect
evaluate on both success and failure pairs instead of failure-only pairsTCNN · Evaluation pairsclassification accuracy: 54.48% -> about 72%Improved

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