{"ID":2878328,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17561","arxiv_id":"2508.17561","title":"Consciousness as a Functor","abstract":"We propose a novel theory of consciousness as a functor (CF) that receives and transmits contents from unconscious memory into conscious memory. Our CF framework can be seen as a categorial formulation of the Global Workspace Theory proposed by Baars. CF models the ensemble of unconscious processes as a topos category of coalgebras. The internal language of thought in CF is defined as a Multi-modal Universal Mitchell-Benabou Language Embedding (MUMBLE). We model the transmission of information from conscious short-term working memory to long-term unconscious memory using our recently proposed Universal Reinforcement Learning (URL) framework. To model the transmission of information from unconscious long-term memory into resource-constrained short-term memory, we propose a network economic model.","short_abstract":"We propose a novel theory of consciousness as a functor (CF) that receives and transmits contents from unconscious memory into conscious memory. Our CF framework can be seen as a categorial formulation of the Global Workspace Theory proposed by Baars. CF models the ensemble of unconscious processes as a topos category...","url_abs":"https://arxiv.org/abs/2508.17561","url_pdf":"https://arxiv.org/pdf/2508.17561v1","authors":"[\"Sridhar Mahadevan\"]","published":"2025-08-25T00:06:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}