{"total":24,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"area":null},{"id":"2205.13026","title":"Preference Dynamics Under Personalized Recommendations","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2401.09804","title":"Clickbait vs. Quality: How Engagement-Based Optimization Shapes the Content Landscape in Online Platforms","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2210.10039","title":"How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios","created":"2022-10-18","cited_by_count":9,"area":null},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2209.13019","title":"Fast online ranking with fairness of exposure","created":"2022-09-13","cited_by_count":5,"area":null},{"id":"2401.05304","title":"Can Probabilistic Feedback Drive User Impacts in Online Platforms?","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2403.00188","title":"Impact of Decentralized Learning on Player Utilities in Stackelberg Games","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2412.03620","title":"Recommender Systems for Sustainability: Overview and Research Issues","created":"2024-12-04","cited_by_count":5,"area":null},{"id":"2209.06317","title":"Quantitative AI Risk Assessments: Opportunities and Challenges","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2202.13985","title":"The dangers in algorithms learning humans' values and irrationalities","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2509.04445","title":"Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment","created":"2025-09-04","cited_by_count":3,"area":null},{"id":"2210.09957","title":"Contextual bandits with concave rewards, and an application to fair ranking","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2406.01611","title":"System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2507.02819","title":"Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2507.16430","title":"Beyond Algorethics: Addressing the Ethical and Anthropological Challenges of AI Recommender Systems","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2208.12299","title":"Modelling the Recommender Alignment Problem","created":"2022-08-25","cited_by_count":0,"area":null},{"id":"2310.05871","title":"Dynamic value alignment through preference aggregation of multiple objectives","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2607.10915","title":"Normative Alignment of Recommender Systems via Internal Label Shift","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.17128","title":"Toward Personal Intelligence Through Cooperative Observation","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}