{"total":16,"rows":[{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2408.04820","title":"Natural Language Outlines for Code: Literate Programming in the LLM Era","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2604.25031","title":"Faithful Autoformalization via Roundtrip Verification and Repair","created":"2026-04-27","cited_by_count":8,"area":null},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2604.27924","title":"Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future","created":"2026-04-30","cited_by_count":6,"area":null},{"id":"2407.04831","title":"Code Hallucination","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2601.13398","title":"Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2403.14592","title":"Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2510.01527","title":"Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2604.12911","title":"Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2410.03210","title":"Tadashi: Enabling AI-Based Automated Code Generation With Guaranteed Correctness","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2504.08852","title":"ML For Hardware Design Interpretability: Challenges and Opportunities","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2602.02554","title":"BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.13817","title":"Neurosymbolic Auditing of Natural-Language Software Requirements","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2609.12286","title":"T-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifacts","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.37493","title":"Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}