rewirebio.iobenchmarks
Evidence claim

links:configuration_of:traitgym-20261116-model-gpn-promoter: GPN_final_Embeddings.minus.inner_product (TraitGym)

Subject
GPN_final_Embeddings.minus.inner_product (TraitGym)
Configuration of
GPN-Promoter

The TraitGym scoring configuration GPN_final_Embeddings.minus.inner_product is a configuration of GPN-Promoter, the model this paper introduces, not of GPN. Keeps the previous link.

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.

8 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Claimed field
links:configuration_of:traitgym-20261116-model-gpn-promoter
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.field

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Previous value
regulatory-variant-20261009-model-gpn
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.previous_value

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Source location
Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Target id
traitgym-20261116-model-gpn-promoter
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.target_id

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Claimed value
traitgym-20261116-model-gpn-promoter
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.value

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Description
The TraitGym scoring configuration GPN_final_Embeddings.minus.inner_product is a configuration of GPN-Promoter, the model this paper introduces, not of GPN. Keeps the previous link.
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Relationship: subject
lit-genomics-20261011-traitgym-config-gpn-final-embeddings-minus-inner-product
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: links:subject:lit-genomics-20261011-traitgym-config-gpn-final-embeddings-minus-inner-product

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Name
links:configuration_of:traitgym-20261116-model-gpn-promoter: GPN_final_Embeddings.minus.inner_product (TraitGym)
Context-only references
Benegas, Eraslan and Song 2025, TraitGym benchmark preprint (bioRxiv v2)

Original source ↗

Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)

Version: bioRxiv version 2, posted 2025-03-04 (37 pages, main text and Supplementary Material)
Retrieved: 2026-11-16T01:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa

Hash scope: SHA-256 of the PDF bytes of one download. bioRxiv stamps each download, so this hash pins this retrieval and not the document: a second download in the same session gave 5f424797ed5c92a3852a52e8ecf29f0c3a3416740a47fe9f9fefe9fd9fb0c876. The stable check is the pdftotext -layout text layer, whose SHA-256 is 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097 and was byte-identical across both downloads; every value in this batch was read from that text layer.

Inspected artifact

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: metadata-correction-traitgym-20261116-config-gpn-final-embeddings-minus-inner-product

areas
dna-genomes
contexts
research
field
links:configuration_of:traitgym-20261116-model-gpn-promoter
previous value
regulatory-variant-20261009-model-gpn
review
artifact sha256: 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097; method: source-hash-verification; pdf-text-parse; transcription; scope-review; method note: The pinned artifact was re-downloaded from the v2 full-PDF URL for this pass. Its PDF bytes hash to 961933ed2396ecb0a75737cc27f0655db07ca62be49654f9139ae95815d050f9, not to the 80426c499e0b498e07c07ea598a2f68049adea7569b30fda58cdc0ebafa6c7aa on the source record, and cannot: bioRxiv restamps the container on every request. The reviewer's download differs from the extractor's two in 41 and 44 bytes, every one of them a download-time stamp (the XMP ModifyDate and MetadataDate, the document ModDate and the trailer ID), with the same 37 pages, the same CreationDate of 2025-03-04 and the same pdftotext -layout text layer. That text layer hashes to 23ae4d67751f1092e5cc2da66b52091fa9bbc3ec59310f06bc65be28f93c5097, which is the hash the source record's hash_scope names as the stable check and the hash recorded here; every value in this batch was read from it.; note: The benchmark's GPN_final is the paper's GPN-Promoter, not GPN. Table 2 lists GPN-Promoter among the benchmarked self-supervised models with reference "This work", 152M parameters and a 512 bp window, and lists no GPN row at all; Section 5 introduces it as "a new gLM, called GPN-Promoter, trained using the genomes of 434 animal species, following the training objective of GPN (Benegas et al., 2023) and the ByteNet convolutional architecture"; Appendix B.2 and Table S6 give its training set and hyperparameters, and the availability statement gives its weights as songlab/gpn-animal-promoter. The 10 GPN-Promoter cells of Table S8 equal the GPN_final_* metric files at three decimal places, which ties the file prefix to the model. A configuration is compared as the model it configures, so while this link stood, 14 stored results read as results of GPN, a model this paper never benchmarks. No family or variant_of edge was added from GPN-Promoter to GPN: a configuration resolves through configuration_of, then family, then alias_of, so a family edge would send these configurations back to GPN and undo the relink, and the paper says only that GPN-Promoter follows GPN's training objective and the ByteNet architecture, which is not a shared checkpoint.; retrieval url: https://www.biorxiv.org/content/10.1101/2025.02.11.637758v2.full.pdf; reviewed at: 2026-11-16T02:10:00Z; reviewer: claude; reviewer note: Claude review agent (independent of the extractor); no human review claimed. Every value was read against the pinned artifact; nothing was reproduced and no model was run.
source locator
Section 5 'Models' (page 8); Table 2 (page 8); Appendix B.2 and Table S6 (page 22); Table S8 (page 27); Data, model and code availability (page 15)
target id
traitgym-20261116-model-gpn-promoter
value
traitgym-20261116-model-gpn-promoter
Related records

Suggest a correction