How could the list of indicators in Table 1 be improved?

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

• Positive Indicatorsconcept0.764
  Properties of a system that should increase credence that the system is conscious
• Indicators are merely intended to be credence-shifting; we do not need to be certain that a theory is correct for it to provide useful indicators.claim0.746
  Key epistemic stance of the Bayesian approach to indicators
• Many of the indicator properties can be implemented in AI systems using current techniques.claim0.745
  Feasibility demonstrated in Section 3.1.
• Indicators should avoid ambiguous terms and contested concepts, but without prematurely committing to precise specifications that anticipate all uncertainties.claim0.724
  Fourth guideline for deriving indicators; illustrated by algorithmic vs implementation-level recurrence distinction
• Negative Indicatorsconcept0.720
  Properties of a system that should decrease credence that the system is conscious
• Which of the indicator properties listed in Table 1 are displayed by existing AI systems, including frontier generative language or multimodal models, language agents, and deep reinforcement learning agents?question0.714
  Key outstanding question for empirical follow-up; central to completing the program begun in the 2023 report
• Specificity and Sensitivity of Indicatorsconcept0.714
  Indicator specificity: few non-conscious systems have it; sensitivity: few conscious systems lack it
• Risk Assessmentconcept0.705
  Cognitive behavior of evaluating risk, exhibited by plants according to S&C.