claim · source checked
Reported MCC for Caduceus (character tokens)
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: source checked
- The impact of tokenizer selection in genomic language models · Original source · journal full text in PMC
Technical metadata and extraction receipts
Stable ID: claim-b2-genomic-tokenizer-selection-2025
- areas
- dna-genomes
- tasks
- regulatory sequence classification
- field
- attributes.printed_value
- value
- 0.778
- source locator
- Table 2, Regulatory row, Caduceus (char) MCC column
- review
- method: independent_ai_table_review; reviewer: Codex secondary table review; reviewed at: 2026-09-16T10:38:57.558210+00:00; notes: Matched Regulatory row with Caduceus (char) column, 0.778. Caption establishes these as MCC summaries by category; model-size row identifies 3.9M parameters. This is an aggregated category result, not a single unspecified split.