{"total":15,"rows":[{"id":"2404.16958","title":"A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice","created":"2024-04-25","cited_by_count":26,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2505.05459","title":"UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections","created":"2025-05-08","cited_by_count":5,"area":null},{"id":"2408.08217","title":"RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Classifiers for Computational Social Science","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2511.14117","title":"Distributions In, Distributions Out: The Case for Soft-Label Training","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2604.07591","title":"From Ground Truth to Measurement: A Statistical Framework for Human Labeling","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2410.14515","title":"Efficient Annotator Reliability Assessment and Sample Weighting for Knowledge-Based Misinformation Detection on Social Media","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2503.04439","title":"A Dataset for Analysing News Framing in Chinese Media","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2504.00589","title":"Efficient Annotator Reliability Assessment with EffiARA","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2603.15150","title":"SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2505.18916","title":"SCRum-9: Multilingual Stance Classification over Rumours on Social Media","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2507.18098","title":"Learning from Hard Labels with Additional Supervision on Non-Hard-Labeled Classes","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.29797","title":"Metric-Dependent Annotation Saturation for Learning from Label Distributions","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.15608","title":"Through the Eyes of the Beholder: Biometric and Demographic Conditioning for Multimodal Sexism Detection","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}