mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol

Manuscript statistics

Minor revisionpanel verdict · 2026-09-01

Manuscript Statistics — CONCLUSIONS

Measured deterministically at ingest, with no model involved. Every figure describes the converted text the panel read, not the PDF.

How the file converted

  • Format: markdown via rustypaper 0.2.0
  • Section map: read from the document model
  • Conversion health: degraded
  • Fused tokens: 0.0 per 1000 words
  • Hyphenated line breaks: 0.0 per 1000 words
  • Lost sentence spaces: 0.0 per 1000 words
  • Markdown headings emitted by the converter: 3
  • Blank-line-separated blocks: 36
  • Text matching no known section: 84%
  • ⚠ 84% of the text matched no known section — section-keyed statistics are unavailable

Size

  • Words: 2,170
  • Main text (excluding references): 1,987
  • Reference list: 183 words
  • Sentences: 80
  • Display equations: 0
  • Table rows: 0

Prose

  • Sentence length: mean 27.12, median 24.5, 90th percentile 43.0 words
  • Sentences over 40 words: 18%
  • Lexical diversity (MATTR): 0.5996
  • Passive constructions: 0.2 per sentence (regex approximation)

Claims and evidence

  • In-text citations: too few detected to count reliably — this venue most likely sets them as superscript numerals, which convert to bare digits
  • Bibliography: 7 entries typed by the converter
  • Numbers: 41.47 per 1000 words
  • Hedging language: 1.38 per 1000 words
  • Amplifying language: 2.3 per 1000 words
  • p-values: 0 exact, 0 reported only as a threshold

By section

Measured over each section separately. The bibliography is left out: hedging and sentence length over a reference list describe a dozen journals' house styles rather than this manuscript.

SectionWordsSentencesMean sentenceCitations/1kHedges/1kBoosters/1k
_preamble1,8226528.030.01.652.2
conclusion163627.170.00.06.13

← All documents in this review