{"total":64,"rows":[{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2510.27527","title":"TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control","created":"2025-10-31","cited_by_count":14,"area":null},{"id":"2511.02687","title":"The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2602.01576","title":"Generative Visual Code Mobile World Models","created":"2026-02-02","cited_by_count":13,"area":"wm"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2602.06718","title":"GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2505.16723","title":"LLM Fingerprinting via Semantically Conditioned Watermarks","created":"2025-05-22","cited_by_count":9,"area":"safety"},{"id":"2509.25302","title":"Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2511.02781","title":"Measuring AI Diffusion: A Population-Normalized Metric for Tracking Global AI Usage","created":"2025-11-04","cited_by_count":5,"area":null},{"id":"2512.12777","title":"State over Tokens: Characterizing the Role of Reasoning Tokens","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2603.16900","title":"Social physics in the age of artificial intelligence","created":"2026-03-04","cited_by_count":5,"area":null},{"id":"2509.25179","title":"NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2511.05613","title":"Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2602.12018","title":"Artificial intelligence is creating a new global linguistic hierarchy","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.15699","title":"This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2603.21606","title":"mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2603.25268","title":"CRAFT: Grounded Multi-Agent Coordination Under Partial Information","created":"2026-03-26","cited_by_count":3,"area":"agents"},{"id":"2604.20995","title":"Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2508.00081","title":"Rethinking Evidence Hierarchies in Medical Language Benchmarks: A Critical Evaluation of HealthBench","created":"2025-07-31","cited_by_count":2,"area":"lr"},{"id":"2508.20236","title":"The Mathematician's Assistant: Integrating AI into Research Practice","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2511.09829","title":"Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2601.08768","title":"AI as Entertainment","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2602.09902","title":"Routing, Cascades, and User Choice for LLMs","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2604.06233","title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2604.07190","title":"The ATOM Report: Measuring the Open Language Model Ecosystem","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2606.05609","title":"SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks","created":"2026-06-04","cited_by_count":2,"area":"safety"},{"id":"2508.06411","title":"Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2510.01494","title":"Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2601.08061","title":"Universal computation is intrinsic to language model decoding","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2602.04836","title":"Are AI Capabilities Increasing Exponentially? A Competing Hypothesis","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.07092","title":"Lemon Agent Technical Report","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2603.01630","title":"SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.15186","title":"Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines","created":"2026-04-16","cited_by_count":1,"area":"agents"},{"id":"2604.21083","title":"Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2506.04513","title":"Pruning Everything, Everywhere, All at Once","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2509.21654","title":"Limitations on Accurate, Trusted, Human-level Reasoning","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2512.04287","title":"Artificial Intelligence Applications in Horizon Scanning for Infectious Diseases","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2601.13286","title":"AI Skills Improve Job Prospects: Causal Evidence from a Hiring Experiment","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.19886","title":"AI Cap-and-Trade: Efficiency Incentives for Accessibility and Sustainability","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.07226","title":"Fault-Tolerant Evaluation for Sample-Efficient Model Performance Estimators","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.19502","title":"Human-Guided Agentic AI for Multimodal Clinical Prediction: Lessons from the AgentDS Healthcare Benchmark","created":"2026-02-23","cited_by_count":0,"area":"agents"},{"id":"2603.11001","title":"RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.13294","title":"Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2603.18633","title":"An Onto-Relational-Sophic Framework for Governing Synthetic Minds","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.22777","title":"AgriPestDatabase-v1.0: A Structured Insect Dataset for Training Agricultural Large Language Model","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.29075","title":"The Future of AI is Many, Not One","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.17626","title":"Toward Reusability of AI Models Using Dynamic Updates of AI Documentation","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2606.12428","title":"A Tool to Map AI Programs in the U.S.: A Snapshot from April 2026 and an Analysis of Requirements for AI Majors and Minors","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.12713","title":"Definitional alignment before capability alignment: a Design-Science framework for adjudicating claims about AGI","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.19270","title":"Beyond Algorithms: Conceptual Innovation in Medical Imaging AI","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.21045","title":"OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.23871","title":"Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.29121","title":"Does Anthropomorphic Language Impact Public Perceptions of AI?","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.14371","title":"Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.14565","title":"Position: AI Lock-In Is in Progress, and We Must Be Prepared","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.15417","title":"An Evaluation Framework for National AI Regulation","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.25623","title":"Using profiles of cognitive capability to assess AI suitability for workplace tasks","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.13334","title":"The Agentic Company OS: Substrate Inversion for Sustained Enterprise Agent Deployment","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.16051","title":"\"Looking for Something Weird to Happen\": How Humans Sustain AI Agent Novelty Amid Semantic Collapse","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.31607","title":"Statistical attribute alignment for black-box generative AI via output post-processing","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.09296","title":"The AI Evaluation Ecosystem","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}