Flesch-Kincaid Grade Level

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

• NLA explanations grow more informative over training with FVE increasing from 0.3-0.4 to 0.6-0.8 roughly linearly in log(training steps)finding0.658
  Quantitative evidence that NLA training produces increasingly informative explanations despite optimizing only for reconstruction.
• After controlling for token count, Flesch-Kincaid readability, type-token ratio, and sentence length, typicality coefficient α remains positive and significant (0.260-0.326, p<10^-6)finding0.651
  Shows typicality bias is not fully explained by surface-form confounds