Result

0.778 MCC

Caduceus (character tokens) · MCC · genomic benchmark categories

Tested configuration: Caduceus (character tokens)
Task: regulatory sequence classification
Dataset: genomic benchmark categories
Procedure: task-category MCC across benchmark datasets
Evaluation: Caduceus (character tokens): regulatory sequence classification
Coverage: scored: unreported; eligible: unreported
Uncertainty: Not reported
Evidence: Independent external evaluation · source checkedThe impact of tokenizer selection in genomic language models · Table 2, Regulatory row, Caduceus (char) MCC column

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: needs review. Source checked does not mean independently reproduced.

Reproduction

Split: paper benchmark summary
Adaptation: Not reported
Scoring implementation: Not reported

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Access requirements and official instructions: regulatory sequence classification

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
attributes.printed_value 0.778 Individual claims	The impact of tokenizer selection in genomic language models Original source ↗ Table 2, Regulatory row, Caduceus (char) MCC column Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558210+00:00	source checked independent ai table review · 2026-09-16T10:38:57.558210+00:00 independent paper Audit details 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. Field: `attributes.printed_value` Claim: claim-b2-genomic-tokenizer-selection-2025 Source artifact SHA-256: `0a01c36fdd63f3f6db509777e61c3f87e8a298c810f8aef7974915aaa0655342` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `0a01c36fdd63f3f6db509777e61c3f87e8a298c810f8aef7974915aaa0655342` Extraction artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: source checked

1 source records and release history

The impact of tokenizer selection in genomic language models · Original source · journal full text in PMC

Download this release

Technical metadata and extraction receipts

Stable ID: b2-genomic-tokenizer-selection-2025

areas: dna-genomes
tasks: regulatory sequence classification
printed value: 0.778
numeric value: 0.778
metric: MCC
metric direction: unknown
unit: unitless
uncertainty: Not reported
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.; evidence: Original PMC XML table headers, row groups and caption inspected; printed value 0.778.; artifact sha256: 0a01c36fdd63f3f6db509777e61c3f87e8a298c810f8aef7974915aaa0655342; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12453675/fullTextXML
legacy id: b2-genomic-tokenizer-selection-2025
legacy row: id: b2-genomic-tokenizer-selection-2025; paper id: genomic-tokenizer-selection-2025; domain id: dna-genomes; task: regulatory sequence classification; model: Caduceus (character tokens); model version: 3.9M parameter variant; dataset: genomic benchmark categories; dataset version: Not reported; split: paper benchmark summary; metric: MCC; value: 0.778; unit: unitless; uncertainty: Not reported; protocol: task-category MCC across benchmark datasets; source locator: Table 2, Regulatory row, Caduceus (char) MCC column; source url: https://pmc.ncbi.nlm.nih.gov/articles/PMC12453675/; evaluation origin: independent_paper; reviewed utc: 2026-09-15T23:33:26Z
missing metadata: dataset version: not_reported_in_legacy_extract; uncertainty: not_reported_in_legacy_extract

Related records

evaluation: Caduceus (character tokens): regulatory sequence classification
subject: Reported MCC for Caduceus (character tokens)

Suggest a correction