{"total":24,"rows":[{"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":"2603.06612","title":"Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness","created":"2026-02-20","cited_by_count":9,"area":null},{"id":"2601.22336","title":"Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.24086","title":"The Subjectivity of Monoculture","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2606.07616","title":"Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.07726","title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.16999","title":"Selection Without Signal, Recovery Through Expression: A Measurement Study of Post-Hoc Falsification Operators for Frozen Small Code Models","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2606.25152","title":"Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.19899","title":"Harnessing Disagreement: Detecting Correlated Agreement Blindness in Multi-Agent Triage","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2607.20464","title":"Stochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2512.20638","title":"Uncovering Competency Gaps in Large Language Models and Their Benchmarks","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2604.15529","title":"LACE: Lattice Attention for Cross-thread Exploration","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2607.09765","title":"How Much Does Correctness Cost? Budgeted Placement of Strong Correctors in a Weak Multi-Agent Swarm","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.00285","title":"Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.18795","title":"Decomposing Wrong-Consensus Agreement in LLM Self-Consistency","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.03422","title":"Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.22169","title":"Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiring","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.26145","title":"Unanimity Without Persuasion: A Single Round of Debate Erases the Disagreement That Verification Needs","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.28177","title":"How Sensitive Are LLM Leaderboard Claims to Hidden Model Selection?","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.34864","title":"On the Limits of Metacognitive Monitoring in LLMs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36958","title":"VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39229","title":"RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04084","title":"Dependable AI-Assisted Engineering: A Formal Framework for AI Participation and Assurance in Safety-Critical Workflows","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}