Because no one theory of consciousness is currently dominant, assessments of AI systems should draw on multiple theories and treat their conditions as indicators rather than definitive criteria.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Indicators used to assess AI systems for consciousness should focus on theories' central explanatory posits, abstracting away from implementation details that may differ across systems.claim0.895
  First of four guidelines for deriving indicators; prevents over-restriction to human-specific features
• Consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness.claim0.890
  Central methodological claim of the paper.
• our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.quote0.851
  Key takeaway from abstract, amended version.
• AI systems which possess more of the indicator properties are more likely to be conscious.claim0.845
  Graded claim about the rubric.
• We take our principal contributions in this report to be: 1. Showing that the assessment of consciousness in AI is scientifically tractable ... 2. Proposing a rubric for assessing consciousness in AI ... 3. Providing initial evidence that many of the indicator properties can be implemented in AI systems using current techniques ...quote0.844
  Summary of contributions.
• Given that it may already be possible to build AI systems that possess many of the indicators, some near-future AI systems will be plausible candidates for consciousness.claim0.843
  Forward-looking assessment of how soon the method's results may have major ethical implications
• Disagreement about AI consciousness is likely to arise and persist in society due to emotional bonds, theoretical considerations, and lack of expert consensus.claim0.840
  Central empirical-sociological claim motivating the paper's inquiry.
• The theory-heavy approach is most suitable for investigating consciousness in AI.claim0.838
  Preferring architectural/functional assessment over behavioural tests.