{"total":26,"rows":[{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"area":null},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2306.01424","title":"Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2107.11927","title":"On Blame Attribution for Accountable Multi-Agent Sequential Decision Making","created":"2021-07-26","cited_by_count":13,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2106.04235","title":"Definitions of intent suitable for algorithms","created":"2021-06-08","cited_by_count":8,"area":null},{"id":"2204.00302","title":"Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes","created":"2022-04-01","cited_by_count":8,"area":null},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2307.16685","title":"Anticipating Responsibility in Multiagent Planning","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2302.12676","title":"Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2106.03684","title":"Extending counterfactual accounts of intent to include oblique intent","created":"2021-06-07","cited_by_count":2,"area":null},{"id":"2307.01532","title":"Analyzing Intentional Behavior in Autonomous Agents under Uncertainty","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2411.03275","title":"Causal Responsibility Attribution for Human-AI Collaboration","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2506.00175","title":"Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2605.13077","title":"Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2205.08192","title":"Moral reinforcement learning using actual causation","created":"2022-05-17","cited_by_count":1,"area":null},{"id":"2306.13659","title":"Toward A Logical Theory Of Fairness and Bias","created":"2023-06-08","cited_by_count":1,"area":null},{"id":"2310.11334","title":"Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2204.04071","title":"Utility Functions for Human/Robot Interaction","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2306.14816","title":"Experiments with Detecting and Mitigating AI Deception","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2307.05631","title":"Causal Kripke Models","created":"2023-07-11","cited_by_count":0,"area":null},{"id":"2603.18968","title":"Teleological Inference in Structural Causal Models via Intentional Interventions","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2605.00248","title":"Causal Foundations of Collective Agency","created":"2026-04-30","cited_by_count":0,"area":null}],"next_cursor":null}