Skip to content

docs: Revise CRAYON_Research_Paper.tex for academic rigor#4

Merged
Electroiscoding merged 1 commit intomainfrom
feature/crayon-paper-detailed-revamp-7465752540677140670
Mar 16, 2026
Merged

docs: Revise CRAYON_Research_Paper.tex for academic rigor#4
Electroiscoding merged 1 commit intomainfrom
feature/crayon-paper-detailed-revamp-7465752540677140670

Conversation

@Electroiscoding
Copy link
Copy Markdown
Owner

  • Toned down hype language in Abstract and Introduction.
  • Added 'Related Work' section comparing to SentencePiece, HF Tokenizers, and tiktoken.
  • Re-framed mathematical claims as empirical heuristics (BPE utility).
  • Acknowledged 16-byte SIMD length as an engineering trade-off rather than hardware limit.
  • Formatted CPU benchmark data to M/sec and added explicit GPU benchmarks (Tesla T4).
  • Expanded limitations to address statistical rigor, ablations, and downstream evaluations.
  • Fixed missing \tableofcontents and missing latex bibitem references.

- Toned down hype language in Abstract and Introduction.
- Added 'Related Work' section comparing to SentencePiece, HF Tokenizers, and tiktoken.
- Re-framed mathematical claims as empirical heuristics (BPE utility).
- Acknowledged 16-byte SIMD length as an engineering trade-off rather than hardware limit.
- Formatted CPU benchmark data to M/sec and added explicit GPU benchmarks (Tesla T4).
- Expanded limitations to address statistical rigor, ablations, and downstream evaluations.
- Fixed missing \tableofcontents and missing latex bibitem references.

Co-authored-by: Electroiscoding <103299713+Electroiscoding@users.noreply.github.com>
@Electroiscoding Electroiscoding merged commit abe9dcd into main Mar 16, 2026
5 of 8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant