Perplexity (masked nucleotide prediction, over non-repeat regions on the held-out test chromosome) of GPN trained on eight Brassicales genomes, repeat loss weight 0 (PNAS 2023) on Non-repeat regions of Arabidopsis thaliana chromosome 5
2.92 Perplexity (masked nucleotide prediction, over non-repeat regions on the held-out test chromosome)
Methods
- Tested configuration
- GPN trained on eight Brassicales genomes, repeat loss weight 0 (PNAS 2023)
- Protocol
- Test perplexity on Arabidopsis thaliana chromosome 5, non-repeat regions
- Dataset subset
- Non-repeat regions of Arabidopsis thaliana chromosome 5
- Procedure
- Test perplexity on Arabidopsis thaliana chromosome 5, non-repeat regions
- Evaluation
- Test perplexity, non-repeat, GPN with repeat weight 0 (PNAS 2023 Table S2)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source: The source prints no interval or spread for this value.
- Evidence
- Author-reported evaluation · source checkedSI Appendix for PNAS 2023 GPN paper (Tables S1 to S3, Figures S1 to S12); DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) · Table S2 (SI Appendix), row "Repeat weight 0", column "Non-repeat regions"
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.
Reproduction
- Split
- Held-out test chromosome; chromosome 4 was the validation chromosome
- Adaptation
- None; the pretrained model is scored directly
- Scoring implementation
- Exponentiation of the cross-entropy loss, as stated in the SI Appendix Table S2 caption
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.
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.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 2.92 Individual claims | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Table S2 (SI Appendix), row "Repeat weight 0", column "Non-repeat regions" Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 | source checked ["independent-cell-check","pdf-text-parse","source-hash-verification"] · 2026-11-16T01:30:00Z author reported Audit detailsPrinted value, numeric value, metric concept, qualifier, direction, unit and the configuration and protocol it hangs on all match the source. No field is null that the source states. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML Extraction artifact SHA-256: |
| Reported result 2.92 Individual claims | SI Appendix for PNAS 2023 GPN paper (Tables S1 to S3, Figures S1 to S12) Table S2 (SI Appendix), row "Repeat weight 0", column "Non-repeat regions" Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: pnas.2311219120.sapp.pdf as served for PMC10622914, 18 pages, created 2023-09-22 | source checked ["independent-cell-check","pdf-text-parse","source-hash-verification"] · 2026-11-16T01:30:00Z author reported Audit detailsPrinted value, numeric value, metric concept, qualifier, direction, unit and the configuration and protocol it hangs on all match the source. No field is null that the source states. Field: Source artifact SHA-256: Hash scope: pdftotext -layout (poppler 26.08.0) on the pinned PDF; the text layer is kept at extract/si-appendix.layout.txt, sha256 6ee1d0c99cc16aa2f5781755204665f0ee08a8f966a9a52c4e1e804ba3bf335a. Format: PDF Archive member: pnas.2311219120.sapp.pdf Extraction artifact SHA-256: |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
2 source records and release history
- SI Appendix for PNAS 2023 GPN paper (Tables S1 to S3, Figures S1 to S12) · Original source · pnas.2311219120.sapp.pdf as served for PMC10622914, 18 pages, created 2023-09-22
- DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) · Original source · PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914
Technical metadata and extraction receipts
Stable ID: gpn-paper-20261116-result-perplexity-non-repeat-repeat-weight-0
- areas
- dna-genomes
- contexts
- research
- metric
- perplexity
- metric direction
- lower
- metric qualifier
- masked nucleotide prediction, over non-repeat regions on the held-out test chromosome
- missing metadata
- uncertainty: note: The source prints no interval or spread for this value.; reason: unreported
- numeric value
- 2.92
- printed value
- 2.92
- review
- artifact sha256: e9ea2399b54c66f17b6088f205e17242521bd31fcb6b608841cdaf69cf363b16; method: independent-cell-check; pdf-text-parse; source-hash-verification; method note: Independent review pass by a different agent from the extractor, with its own script (review/recheck_values.py), which does not import extract/parse_values.py and does not read extract/values.json. The published article XML and the bioRxiv details API response were re-downloaded and matched their pinned hashes; the SI Appendix PDF was re-downloaded as the member of a freshly built Europe PMC zip (a third distinct zip hash, c7a1b20e8796c4bd384ba6f0308134e32a66e40dc881b0c1e3d0201da26e8498) and the PDF member matched. Every archived gz in artifacts/ decompresses to the hash its source record pins, and the text layer in extract/ regenerates byte for byte from the archived PDF with pdftotext -layout, poppler 26.08.0. npm run batch -- check-values reproduced the extractor's figures: 6 in_cell, 17 locator_not_parsed, no overclaimed_in_row. The six Table S2 cells were re-read by column position: the character span of each column's header label was taken from the printed header line, and a cell is the one number right of the row label whose span overlaps that column's span, so a value from the neighbouring column cannot match. The locator's row and column names were checked against the ones read. A mutation test (review/mutation_test.py) confirmed the check fails on a swapped printed value and on a swapped locator column.; note: Printed value, numeric value, metric concept, qualifier, direction, unit and the configuration and protocol it hangs on all match the source. No field is null that the source states.; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC10622914/supplementaryFiles; reviewed at: 2026-11-16T01:30:00Z; reviewer: claude; reviewer note: Claude review agent, independent of the extractor; no human review claimed. Transcription was checked against the pinned artifacts; nothing was reproduced and no value was recomputed.
- source locator
- Table S2 (SI Appendix), row "Repeat weight 0", column "Non-repeat regions"
- source table
- SI Appendix Table S2
- unit
- unitless