{"total":53,"rows":[{"id":"2602.07150","title":"On Randomness in Agentic Evals","created":"2026-02-06","cited_by_count":17,"area":"agents"},{"id":"2511.17826","title":"Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch","created":"2025-11-21","cited_by_count":14,"area":null},{"id":"2604.11581","title":"Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking","created":"2026-04-13","cited_by_count":10,"area":null},{"id":"2605.19537","title":"The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2602.10144","title":"When LLMs get significantly worse: A statistical approach to detect model degradations","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2604.15409","title":"The Illusion of Equivalence: Systematic FP16 Divergence in KV-Cached Autoregressive Inference","created":"2026-04-16","cited_by_count":4,"area":"inference"},{"id":"2604.13413","title":"Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models","created":"2026-04-15","cited_by_count":3,"area":"diffusion"},{"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":"2605.30218","title":"MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2601.21902","title":"Hardware-Triggered Backdoors","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.18774","title":"SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for Unpaired RGB+Thermal 3D Reconstruction","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2605.27440","title":"Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2606.19535","title":"FloatDoor: Platform-Triggered Backdoors in LLMs","created":"2026-06-17","cited_by_count":2,"area":"safety"},{"id":"2606.21023","title":"Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL","created":"2026-06-19","cited_by_count":2,"area":"inference"},{"id":"2607.18816","title":"AgentTrails: Towards Trust and Reuse for Agentic Tasks","created":"2026-07-21","cited_by_count":2,"area":"agents"},{"id":"2607.23815","title":"Kalypso: Relational LLM Serving","created":"2026-07-26","cited_by_count":2,"area":"inference"},{"id":"2608.08029","title":"Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families","created":"2026-08-08","cited_by_count":2,"area":"safety"},{"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":"2511.10909","title":"Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2605.29979","title":"Fingerprinting Inference Systems of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.15621","title":"Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2608.03803","title":"M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.06171","title":"Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.20370","title":"Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf","created":"2026-06-19","cited_by_count":1,"area":"agents"},{"id":"2609.00363","title":"Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.25624","title":"Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2609.36931","title":"Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"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":"2601.11334","title":"Information Theoretic Perspective on Representation Learning","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.15756","title":"A Note on Non-Composability of Layerwise Approximate Verification for Neural Inference","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.25422","title":"Navigating the Prompt Space: Improving LLM Classification of Social Science Texts Through Prompt Engineering","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.23955","title":"From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.18431","title":"Beyond Prediction: Tail-Aware Scheduling for LLM Inference","created":"2026-06-16","cited_by_count":0,"area":"inference"},{"id":"2606.29228","title":"Understanding Evaluation Illusion in Diffusion Large Language Models","created":"2026-06-28","cited_by_count":0,"area":"inference"},{"id":"2607.02119","title":"An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2609.03221","title":"Instability Floors: Separating Bias from Noise in Fairness Audits of Clinical LLM Agents with FairMedAgent","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04748","title":"Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving","created":"2026-09-04","cited_by_count":0,"area":"inference"},{"id":"2609.13582","title":"Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.15504","title":"Evaluating Losslessness in Speculative Decoding Under Finite-Precision Inference","created":"2026-09-14","cited_by_count":0,"area":"inference"},{"id":"2609.20614","title":"Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22109","title":"A Shared Learning Rate Is Not a Neutral Control in Selective On-Policy Distillation","created":"2026-08-17","cited_by_count":0,"area":"distill"},{"id":"2609.23033","title":"WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models","created":"2026-09-19","cited_by_count":0,"area":"inference"},{"id":"2609.26621","title":"Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.30749","title":"ORCA: Evaluating LLMs on Data Science Code Translation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31796","title":"Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33220","title":"When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.37617","title":"AS$^2$D: Accelerating On-Demand Audio Understanding on Mobile Devices","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2610.01595","title":"Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.05533","title":"What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.08722","title":"Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09111","title":"Same Text, Different Prediction: Serving-Context Nondeterminism in Text Classifiers","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09193","title":"Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}