paper:doi-10-1098-rsta-2016-0338Coarse-graining as a downward causation mechanism
Original abstract (expand)
Downward causation is the controversial idea that 'higher' levels of organization can causally influence behaviour at 'lower' levels of organization. Here I propose that we can gain traction on downward causation by being operational and examining how adaptive systems identify regularities in evolutionary or learning time and use these regularities to guide behaviour. I suggest that in many adaptive systems components collectively compute their macroscopic worlds through coarse-graining. I further suggest we move from simple feedback to downward causation when components tune behaviour in response to estimates of collectively computed macroscopic properties. I introduce a weak and strong notion of downward causation and discuss the role the strong form plays in the origins of new organizational levels. I illustrate these points with examples from the study of biological and social systems and deep neural networks.This article is part of the themed issue 'Reconceptualizing the origins of life'.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- Fine-Grained Activation Steering: Steering Less, Achieving MoreTianjiao Li, Zixiao Zhu, Hanzhang Zhou, Junlang Qian, Li Zhang, Jia Jim Deryl Chua, Lee Onn Mak, Gee Wah Ng, Kezhi Mao Zijian Feng2026≈ 68%
- The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language ModelsXiachong Feng, Ziyun Song, Xiaocheng Feng, Jing Xiong, Lingpeng Kong Chonghan Qin2026≈ 67%
- Towards Understanding and Improving Refusal in Compressed Models via Mechanistic InterpretabilityMohammad Mahdi Khalili Vishnu Kabir Chhabra2025≈ 67%
- Analysing Moral Bias in Finetuned LLMs through Mechanistic InterpretabilityDaniela Dalbagno, Maurizio Gabbrielli Bianca Raimondi2025≈ 67%
- ≈ 67%
- ≈ 67%
- A macro agent and its actionsFrancesco Massari, Maggie Beheler-Amass and Giulio Tononi Larissa Albantakis2020≈ 67%
- Toward Compositional Generalization in Object-Oriented World ModelingLingzhi Kong, Robin Walters, Lawson L.S. Wong Linfeng Zhao2022≈ 67%
- When Respondents Don't Care Anymore: Identifying the Onset of Careless RespondingMax Welz and Andreas Alfons2026≈ 67%
- Fine-Grained Interpretation of Political Opinions in Large Language ModelsMengyue Yang, Mengnan Du, Weiru Liu Jingyu Hu2025≈ 67%
- Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic InterpretabilityTessa Han, Usha Bhalla, Himabindu Lakkaraju Shichang Zhang2025≈ 66%
- Beyond Input Activations: Identifying Influential Latents by Gradient Sparse AutoencodersXuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu Dong Shu2025≈ 66%
- Causal Probing for Internal Visual Representations in Multimodal Large Language ModelsTianjie Ju, Zheng Wu, Liangbo He, Jun Lan, Huijia Zhu, Weiqiang Wang, Zhuosheng Zhang Zehao Deng2026≈ 66%
- Dissecting and Mitigating Diffusion Bias via Mechanistic InterpretabilityChangming Li, Yifan Wang, Yongxiang Zhao, Anqi Pang, Sibei Yang, Jingyi Yu, Kan Ren Yingdong Shi2025≈ 66%
- ≈ 66%
- Fine-Tuning is Subgraph Search: A New Lens on Learning DynamicsWenhao Gao, Caixia Yuan, Xiaojie Wang Yueyan Li2025≈ 66%
- ≈ 65%
- Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencodersin corpus2026≈ 65%
- ≈ 65%
- ≈ 64%
- Cognitive glues are shared models of relative scarcities: the economics of collective intelligencein corpus2026≈ 64%
- ≈ 63%
- Learning without neurons in physical systemsin corpus2022≈ 63%
- Model Alignment Searchin corpus2025≈ 63%
- From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMsin corpus2025≈ 63%
- What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectorsin corpus2026≈ 63%
- ≈ 63%
- ≈ 63%
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behaviorin corpus2026≈ 63%
- ≈ 62%
Similar preprints — Semantic Scholar
Cited by (4)
- Darwin's agential materials: evolutionary implications of multiscale competency in developmental biology
Cellular collectives operating between the genotype and anatomical phenotype constitute an agential substrate that fundamentally reshapes the evolutionary search process—this is the central claim of L
- Biology, Buddhism, and AI: Care as the Driver of Intelligence
Care—defined as concern for the alleviation of stress (the delta between current and optimal states)—is proposed as the substrate-independent invariant that unifies biology, Buddhist philosophy, and a
- Technological Approach to Mind Everywhere: An Experimentally-Grounded Framework for Understanding Diverse Bodies and Minds
TAME—Technological Approach to Mind Everywhere—formalizes a non-binary, empirically grounded framework for recognizing, comparing, and manipulating cognition across radically diverse substrates, from
- The computational boundary of a 'self': developmental bioelectricity drives multicellularity and scale-free cognition
Scale-Free Cognition, the framework introduced here, proposes that any coherent Self is demarcated by a 'cognitive light cone'—a spatio-temporal boundary of events a system can measure, model, and att