framework
active
framework:attention-schema-theoryAttention Schema Theory
Theory by Graziano linking consciousness to a predictive model of attention; listed in Butlin et al. 2023.
Neighborhood — ranked by edge-count
Papers (3)
paper
- Taking AI Welfare Seriouslymentions
Thinkers (2)
thinker
- Michael GrazianointroducesstudiesDeveloper of attention schema theory, quoted on the 'cool' motivation for building conscious AI.
- Michael S. A. Grazianostudies
Concepts (9)
concept
- Endogenous Steering Resistanceanalogous_toThe central phenomenon introduced by this paper: inference-time recovery from irrelevant activation steering in LLMs
- Second-Order Perceptionassociated_withCIMC's proposed computational structure of consciousness: perception that perception is occurring, non-inferential and synchronous with its content
- Metacognitive monitoringimplementsHigher-order mechanism that evaluates the reliability of first-order perceptual representations.
- Top-Down Attentional ControlimplementsBiological analogue to ESR where top-down mechanisms detect distracting inputs and redirect processing
- AST-1: A predictive model representing and enabling control over the current state of attentionassociated_withIndicator from AST: having an attention schema that models and controls attention.
- Original Attention Schema Theory paper cited in the related work section
- Phenomenal Model of the Intentionality Relationanalogous_toMetzinger's concept from Being No One noted as possibly anticipating Attention Schema Theory by a decade
- The Attention Schema Theory: A Foundation for Engineering Artificial Consciousness (Graziano, 2017)introducesPaper providing the biological framework analogy for ESR as a form of attentional control
- Attention SchemaimplementsA predictive model representing and controlling attention; central to attention schema theory.
Claims (2)
claim
- Cross-domain analogy linking ESR to Attention Schema Theory
- Historical priority claim noting Metzinger's anticipation of Graziano's AST
Artifacts (2)
artifact
- Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.
- The source essay published in Religions 2025, arguing that AI may fulfill Buddhism's aim of self-overcoming by migrating intelligence to a non-organic substrate.
Hypotheses (1)
hypothesis
- The theoretical hypothesis tested across all four experiments; motivated by convergence of GWT, RPT, HOT, IIT, predictive processing on recurrent/self-referential dynamics
Frameworks (1)
framework
- Conductor Theory of Consciousnessanalogous_toThe paper's model that conscious directed attention functions as a conductor of the mental orchestra, resolving incoherence between partial models
Conceptual bridges
2-hop · via this framework's ideasWhere ideas in this framework connect to the rest of the corpus — the same concept, an analogy, or a restatement elsewhere.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Holland's mathematical account showing schemata must appear in any successful adaptive system, used to ground the necessity of patterns
- Cognitive framework or rule that governs human actions; may or may not preserve wholeness.
- Core operation in transformers, computing weighted combinations of previous elements
- Mathematical equivalence showing the relationship between attention mechanisms and convolutional operations
- Process using Q, K, V to compute a heat map over K and weighted sum of V.
- Identification of algorithms implemented in attention layers, distributed across attention headsfinding0.732VPD successfully recovered interpretable attention algorithms (previous-token behavior, syntax-boundary routing) in weight space without requiring manual decomposition across heads.
- Mechanism that selects information from modules for representation in the global workspace.
- Higher-order generative model variables modulating perceptual precision; subject to policy selection (deliberate shifts of attention).