Analysis of robocall data from 65 countries shows the threat is significantly more severe in the US than elsewhere, backed by a new public dataset of 8.7 million records, transcripts, and recordings.
A survey on large language models for code generation,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
In OSS repos that commit AI chat logs, AI use is heavier in smaller, less collaborative projects; chats almost always precede commits, quality signals do not broadly worsen, and developers trust their own AI code more than others'.
AI-generated C++ programs trigger confirmed runtime (sanitizer) violations at roughly twice the odds of human contest solutions, a gap static analysis does not reveal.
CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.
citing papers explorer
-
Robocalls: A Worldwide or US-only Problem? Analyzing Spam and Fraud in International Phone Calls
Analysis of robocall data from 65 countries shows the threat is significantly more severe in the US than elsewhere, backed by a new public dataset of 8.7 million records, transcripts, and recordings.
-
From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software
In OSS repos that commit AI chat logs, AI use is heavier in smaller, less collaborative projects; chats almost always precede commits, quality signals do not broadly worsen, and developers trust their own AI code more than others'.
-
The Illusion of Safety: Multi-Tier Verification of AI vs. Human C++ Code
AI-generated C++ programs trigger confirmed runtime (sanitizer) violations at roughly twice the odds of human contest solutions, a gap static analysis does not reveal.
-
Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs
CURE applies contrastive unlearning to reduce deprecated API usage in code LLMs and improve correct replacements on a benchmark dataset while preserving general performance.