framework
active
framework:bayesian-network-model-of-consciousness-attributionBayesian Network Model of Consciousness Attribution
The paper's formal Bayesian machinery translating the supervenience hierarchy into conditional independence and aggregated credence.
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (3)
finding
- Bayesian model outputs aggregate posterior 0.913 for a fly with indicator evidence concentrated at fine-grained (Level 4/5) levelsassociated_withIllustrates that depth of evidence at fine-grained levels matters more than breadth of coarse-grained evidence.
- Bayesian model outputs aggregate posterior 1.000 for a human with all 37 indicators activated, invariant to level-credence weightingassociated_withFace-validity anchor case at the positive extreme.
- Demonstrates that theoretical credence weighting can drastically lower the assessed probability for the same evidence.
Frameworks (3)
framework
- The paper's central original contribution: behavioural, computational, intrinsic causal-structural, organismic, and organism-environment levels.
- Iterative Natural-Kind (INK) Strategyassociated_withBayne et al.'s measurement-theoretic approach validating consciousness tests across populations, complementary to this paper's framework.
- Prior Bayesian multi-stance model (Shiller et al.) that this paper's Bayesian approach complements and structurally explains.
Artifacts (2)
artifact
- Cacophony Interactive ToolimplementsOnline tool implementing the Bayesian model for illustrative consciousness assessments.
- Cacophony Public Code RepositoryimplementsGitHub repository implementing the Bayesian network and indicator mappings.
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.
- Risk of attributing consciousness to non-conscious systems, potentially wasting resources or endangering lives
- Risk of failing to identify consciousness in systems where it is present, potentially causing avoidable harm
- Normative theory proposing biological systems perform approximate Bayesian inference through free energy minimization.
- Cube Flipper's model that consciousness is experienced as fields (visual, somatic) with wave-like soliton dynamics and Gabor wavelets.
- Conceptualization of pain perception as inference over hidden nociceptive causes, from Eckert et al. 2022
- Risk summary.
- We hypothesize that emotional attachments and social-connection roles with AI systems drive consciousness attribution in part.hypothesis0.754Proposed causal mechanism behind lay attribution of AI consciousness.
- Central thesis motivating Section 8's convergence argument.