{"total":21,"rows":[{"id":"2506.09501","title":"Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference","created":"2025-06-11","cited_by_count":53,"area":null},{"id":"2507.10846","title":"Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2506.01054","title":"No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2601.06118","title":"Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism","created":"2026-01-03","cited_by_count":4,"area":null},{"id":"2601.21824","title":"DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2606.00279","title":"Bit-Exact AI Inference Verification Without Performance Tradeoffs","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2604.22032","title":"Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2505.18332","title":"An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2510.20075","title":"LLMs can hide text in other text of the same length","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2510.23389","title":"Floating-Point Neural Network Verification at the Software Level","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2603.20421","title":"Hawkeye: Reproducing GPU-Level Non-Determinism","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2604.22411","title":"Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2608.13756","title":"The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2503.17173","title":"Robustness of deep learning classification to adversarial input on GPUs: asynchronous parallel accumulation is a source of vulnerability","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2510.15060","title":"A solution to generalized learning from small training sets found in infants repeated visual experiences of individual objects","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2601.17684","title":"A Model-Driven Lossless Compression Algorithm Resistant to Mismatch","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2602.00182","title":"EigenAI: Deterministic Inference, Verifiable Results","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.17223","title":"Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2607.19490","title":"Integrity of peer-to-peer distributed LLM inference under malicious nodes","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.16085","title":"Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.22220","title":"Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}