{"total":119,"rows":[{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2606.05806","title":"When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents","created":"2026-06-04","cited_by_count":17,"area":"lr"},{"id":"2512.04062","title":"Eval Factsheets: A Structured Framework for Documenting AI Evaluations","created":"2025-12-03","cited_by_count":9,"area":null},{"id":"2601.18572","title":"One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization","created":"2026-01-26","cited_by_count":9,"area":null},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2605.30315","title":"Resolution Diagnostics for Paired LLM Evaluation","created":"2026-05-28","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2603.15121","title":"Establishing Construct Validity in LLM Capability Benchmarks Requires Nomological Networks","created":"2026-03-16","cited_by_count":6,"area":null},{"id":"2605.20251","title":"ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2604.27405","title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2605.23262","title":"Designing Benchmarks for Knowledge Work","created":"2026-05-22","cited_by_count":5,"area":null},{"id":"2605.25240","title":"JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2607.26587","title":"The Implementation Lottery: Auditing Idea Reliability in Automated Research","created":"2026-07-29","cited_by_count":5,"area":null},{"id":"2601.18486","title":"Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias","created":"2026-01-26","cited_by_count":4,"area":null},{"id":"2603.20172","title":"Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation","created":"2026-03-20","cited_by_count":4,"area":"lr"},{"id":"2606.09809","title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2601.20617","title":"Agent Benchmarks Fail Public Sector Requirements","created":"2026-01-28","cited_by_count":3,"area":"agents"},{"id":"2602.16085","title":"Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs","created":"2026-02-17","cited_by_count":3,"area":"lr"},{"id":"2603.00063","title":"Measuring What AI Systems Might Do: Towards A Measurement Science in AI","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2604.03244","title":"AI Evaluation Should Require Standardized Item-Level Data Releases","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2601.02285","title":"pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2602.24055","title":"CIRCLE: A Framework for Evaluating AI from a Real-World Lens","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2604.20622","title":"pAI/MSc: ML Theory Research with Humans on the Loop","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2605.23715","title":"NLG Evaluation: Past, Present, Future","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2606.08044","title":"When Behavioral Safety Evaluation Fails: A Representation-Level Perspective","created":"2026-06-06","cited_by_count":2,"area":"safety"},{"id":"2606.28574","title":"Correct codes for the wrong reasons? validating LLMs as measurement instruments for theoretical constructs","created":"2026-06-26","cited_by_count":2,"area":"lr"},{"id":"2607.28685","title":"Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks","created":"2026-07-30","cited_by_count":2,"area":"safety"},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2609.01519","title":"When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation","created":"2026-09-01","cited_by_count":2,"area":"agents"},{"id":"2609.37315","title":"Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2601.09896","title":"The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2602.14307","title":"Benchmarking at the Edge of Comprehension","created":"2026-02-15","cited_by_count":1,"area":null},{"id":"2603.06811","title":"Making AI Evaluation Deployment Relevant Through Context Specification","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.18019","title":"BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2604.14856","title":"ClimateCause: Complex and Implicit Causal Structures in Climate Reports","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.15203","title":"MADE: A Living Benchmark for Multi-Label Text Classification with Uncertainty Quantification of Medical Device Adverse Events","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.06652","title":"When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2605.16301","title":"Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2605.26001","title":"AI-Assisted Systematization for Evaluating GenAI Systems","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.26937","title":"Beyond Questions: Evaluating the Stated Knowledge of LLMs","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.02467","title":"Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.05552","title":"The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.28274","title":"MORFES: A Benchmark for Productive Inflectional Competence in Modern Greek","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.14065","title":"Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.20204","title":"ContractScrub: A benchmark for final review of legal contracts","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2609.00482","title":"Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.19866","title":"Reproducibility is not construct validity: LLM measurement of institutionally situated communication","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2610.12841","title":"Fear Is Not Always Fear: Variation in Emotion Label Equivalence Across Datasets","created":"2026-10-09","cited_by_count":1,"area":null},{"id":"2601.01878","title":"Theory Trace Card: Theory-Driven Socio-Cognitive Evaluation of LLMs","created":"2026-01-05","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":"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":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2603.18294","title":"The Validity Gap in Health AI Evaluation: A Cross-Sectional Analysis of Benchmark Composition","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.21636","title":"Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.13371","title":"Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2604.25923","title":"On Challenges in Evaluation Methodology: A Review","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.08522","title":"Coordinates of Capability: A Unified MTMM-Geometric Framework for LLM Evaluation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.11398","title":"AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.13318","title":"VERA-MH: Validation of Ethical and Responsible AI in Mental Health","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18824","title":"Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.05029","title":"Validity Threats for Foundation Model Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.07897","title":"Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.11208","title":"BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.04576","title":"Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.05123","title":"ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.14336","title":"Copy-on-Write Scoring: Application-Specific Agent Evaluations","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2607.24243","title":"Epistemic Norms for AI Safety and Alignment Research","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.24999","title":"CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.26159","title":"When benchmark inferences do not compose: Projectibility in AI evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.28677","title":"Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.03340","title":"Benchmarking the Benchmarks: Testing the Predictive Validity of Commonsense Benchmarks","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05656","title":"Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.10030","title":"Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.10089","title":"Status Association Does Not Reliably Predict Decision Leakage","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.10268","title":"Toward Human Rights Benchmarking for LLMs: A Pilot Methodology","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.12880","title":"Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13840","title":"ASSERT: A Measurement Pipeline for GenAI Audits","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.19269","title":"What Does an Evaluation License? A Commit-Bound Census of Claim Replay in Inspect Evals","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.20729","title":"Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.27009","title":"The Guard That Cried Wolf: How Scary Words Make Agent Guardrails Refuse Legitimate Actions","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2608.27716","title":"PCFBench: A Diagnostic Benchmark for Product Carbon Footprint Estimation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.29420","title":"One Capability or Many? Structural and Predictive Tests of Benchmark Validity Disagree About Economic Benchmarks for Frontier AI","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2608.29463","title":"Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2608.29560","title":"Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.03047","title":"SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.05036","title":"Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.05296","title":"LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.06190","title":"One Perturbation Is Not Enough: Identifiability and Blind Baselines for Behavioral AI Evaluation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.11291","title":"Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13642","title":"When Compliance Data Masquerades as Evaluation: Measurement Validity for Deployed AI Systems","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.16267","title":"The record is part of the task: matched-record evaluation of text classifiers across maintenance, safety and recall reporting","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.16793","title":"Available but Unclaimed: An Empirical Study of Human-AI Synergy","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":"100"}