{"total":17,"rows":[{"id":"2609.04094","title":"DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training","created":"2026-09-03","cited_by_count":5,"area":null},{"id":"2608.24419","title":"A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation","created":"2026-08-25","cited_by_count":4,"area":null},{"id":"2609.25447","title":"Conduct Under Pressure: What Sixty Language Models Do When a User Pushes","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2607.08961","title":"NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.26762","title":"Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.04198","title":"Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.25052","title":"Self-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.27787","title":"Ask Which, Not How Good: Sizing Benchmarks Scored by an LLM","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.37236","title":"Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00054","title":"The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.00202","title":"When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.04370","title":"Boundaries Agree, Labels Do Not: Intra-Annotator Dynamics as a Kind of Training Data","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.08501","title":"Language-model ratings of depression reflect the rater more than the patient","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.10232","title":"LLM Persuasion Is in the Eye of the Evaluation","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.15938","title":"The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.17158","title":"The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19992","title":"SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}