{"total":16,"rows":[{"id":"2508.13180","title":"Search-Time Data Contamination","created":"2025-08-12","cited_by_count":19,"area":null},{"id":"2510.24668","title":"InteractComp: Evaluating Search Agents With Ambiguous Queries","created":"2025-10-28","cited_by_count":12,"area":null},{"id":"2508.11847","title":"Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings","created":"2025-08-16","cited_by_count":8,"area":null},{"id":"2510.11560","title":"Characterizing Web Search in The Age of Generative AI","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2605.15761","title":"A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.19843","title":"Overreliance on AI in Information-seeking from Video Content","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.26891","title":"Strategic Candidacy in Generative AI Arenas","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2608.29696","title":"Ideation Arena: Evaluating LLM Generated Research Ideas with Battle-style Human Expert Assessment","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2608.30023","title":"Demand-Side Measurement for Generative Engine Optimization: Constructing and Validating a Million-Persona, Intent-Annotated Buyer Corpus","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2609.32472","title":"AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2604.14448","title":"MARCA: A Checklist-Based Benchmark for Multilingual Web Search","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.17110","title":"Capturing LLM Capabilities via Evidence-Calibrated Query Clustering","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.28565","title":"Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2609.06811","title":"Measuring GEO Visibility: Prompt Corpora Define the Answer Market","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.22599","title":"MAWILE: Multi-Axis Workbench for Inspecting LLM Evaluators","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}