Entity · technique

Calibrated Collective Oversight (CCO)

techniqueactivecalibrated-collective-oversight-cco--2a783dde·1 events·first seen May 28, 2026

Aliases: Calibrated Collective Oversight (CCO)

Co-occurring entities

Attainable Utility Preservation Conformal Decision Theory SWE-bench MACHIAVELLI

More like this (12)

scalable oversight Canonical-Context On-Policy Distillation (CCOPD)OpenCoF Creative Quality Alignment (CQA)Collective Alignment CoOp Coalition for Content Provenance and Authenticity Collective Intelligence Project CoT-Control Executable Operational Cognition Community Evals Coordinated Vulnerability Disclosure

Recent events (1)

7arXiv · cs.AI·May 28, 2026·source ↗

Calibrated Collective Oversight (CCO): Scalable Oversight with Finite-Time Statistical Guarantees

This paper introduces Calibrated Collective Oversight (CCO), a framework for maintaining human oversight of agentic AI systems that may exceed human capabilities. CCO aggregates diverse scoring functions into a conservatism penalty inspired by Attainable Utility Preservation, then calibrates this penalty online via Conformal Decision Theory to ensure undesirable outcomes stay below a user-specified threshold with finite-time bounds and no distributional assumptions. Evaluated on a modified SWE-bench (adversarially misaligned agent) and MACHIAVELLI (ethical violations), CCO allows weaker overseers to constrain stronger agents while preserving reward, with empirical violation rates closely matching specified targets.

Evaluation and Benchmarking AI Safety Research Calibrated Collective Oversight (CCO)Attainable Utility Preservation Conformal Decision Theory +4 more