rewirebio.iobenchmarks
Evidence claim

Model table differences between the BacBench README and the preprint

Model table differences of BacBench

The BacBench README and preprint Table S9 disagree on Nucleotide Transformer (250M against 235M), ProkBERT (27M against 26M), ESM-C (300M against 332M), ProtBert (420M against 412M), Bacformer Large (27M against 332M) and on the ESM-C context length (2,048 against 1,024 tokens)

The two official model tables of the same project disagree on several parameter counts and context lengths, so neither can be taken as the project's single statement of model size.

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.

14 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
model_table_differences
Context-only references
BacBench repository README at commit 64b7d45

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Commit 64b7d45823b2ff2ef88458e3aa235caa461a12aa
Retrieved: 2026-11-15T23:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.field

Source artifact SHA-256: c9d28efef5b4cc30adbcc9de224c350100f5aa2a15a025beaf10dcdeb86cd93e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Claimed field
model_table_differences
Context-only references
Bacformer preprint, bioRxiv 2025.07.20.665723 version 3

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Version 3, posted 17 August 2026 according to the page banner; the bioRxiv API lists version 3 with date 2026-08-19
Retrieved: 2026-11-15T22:55:00Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.field

Source artifact SHA-256: d86de3315063e038ec8d5bed60b7b1a916c137ee60973e55d9d5c82f078d8dfd

Hash scope: The hash is of one download. bioRxiv regenerates this PDF on request, so the container bytes differ between downloads: a second download minutes later gave 08fcc83af256845d942345fc6b63c64911878733acd028edab5e9307d63319db. The pdftotext -layout text layer of both downloads is byte-identical (SHA-256 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2), and that text layer, archived gzipped in artifacts/ with SHA-256 0afdefd78a410d036d1c4f17e33bdf481e8d76241ee02f4c84c7c4be91ee72aa, is what every extracted value was read from.

Rationale
The two official model tables of the same project disagree on several parameter counts and context lengths, so neither can be taken as the project's single statement of model size.
Context-only references
BacBench repository README at commit 64b7d45

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Commit 64b7d45823b2ff2ef88458e3aa235caa461a12aa
Retrieved: 2026-11-15T23:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.rationale

Source artifact SHA-256: c9d28efef5b4cc30adbcc9de224c350100f5aa2a15a025beaf10dcdeb86cd93e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Rationale
The two official model tables of the same project disagree on several parameter counts and context lengths, so neither can be taken as the project's single statement of model size.
Context-only references
Bacformer preprint, bioRxiv 2025.07.20.665723 version 3

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Version 3, posted 17 August 2026 according to the page banner; the bioRxiv API lists version 3 with date 2026-08-19
Retrieved: 2026-11-15T22:55:00Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.rationale

Source artifact SHA-256: d86de3315063e038ec8d5bed60b7b1a916c137ee60973e55d9d5c82f078d8dfd

Hash scope: The hash is of one download. bioRxiv regenerates this PDF on request, so the container bytes differ between downloads: a second download minutes later gave 08fcc83af256845d942345fc6b63c64911878733acd028edab5e9307d63319db. The pdftotext -layout text layer of both downloads is byte-identical (SHA-256 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2), and that text layer, archived gzipped in artifacts/ with SHA-256 0afdefd78a410d036d1c4f17e33bdf481e8d76241ee02f4c84c7c4be91ee72aa, is what every extracted value was read from.

Source location
BacBench README 'Benchmarked models' table against preprint Table S9
Context-only references
BacBench repository README at commit 64b7d45

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Commit 64b7d45823b2ff2ef88458e3aa235caa461a12aa
Retrieved: 2026-11-15T23:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: c9d28efef5b4cc30adbcc9de224c350100f5aa2a15a025beaf10dcdeb86cd93e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Source location
BacBench README 'Benchmarked models' table against preprint Table S9
Context-only references
Bacformer preprint, bioRxiv 2025.07.20.665723 version 3

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Version 3, posted 17 August 2026 according to the page banner; the bioRxiv API lists version 3 with date 2026-08-19
Retrieved: 2026-11-15T22:55:00Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: d86de3315063e038ec8d5bed60b7b1a916c137ee60973e55d9d5c82f078d8dfd

Hash scope: The hash is of one download. bioRxiv regenerates this PDF on request, so the container bytes differ between downloads: a second download minutes later gave 08fcc83af256845d942345fc6b63c64911878733acd028edab5e9307d63319db. The pdftotext -layout text layer of both downloads is byte-identical (SHA-256 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2), and that text layer, archived gzipped in artifacts/ with SHA-256 0afdefd78a410d036d1c4f17e33bdf481e8d76241ee02f4c84c7c4be91ee72aa, is what every extracted value was read from.

Claimed value
The BacBench README and preprint Table S9 disagree on Nucleotide Transformer (250M against 235M), ProkBERT (27M against 26M), ESM-C (300M against 332M), ProtBert (420M against 412M), Bacformer Large (27M against 332M) and on the ESM-C context length (2,048 against 1,024 tokens)
Context-only references
BacBench repository README at commit 64b7d45

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Commit 64b7d45823b2ff2ef88458e3aa235caa461a12aa
Retrieved: 2026-11-15T23:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.value

Source artifact SHA-256: c9d28efef5b4cc30adbcc9de224c350100f5aa2a15a025beaf10dcdeb86cd93e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Claimed value
The BacBench README and preprint Table S9 disagree on Nucleotide Transformer (250M against 235M), ProkBERT (27M against 26M), ESM-C (300M against 332M), ProtBert (420M against 412M), Bacformer Large (27M against 332M) and on the ESM-C context length (2,048 against 1,024 tokens)
Context-only references
Bacformer preprint, bioRxiv 2025.07.20.665723 version 3

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Version 3, posted 17 August 2026 according to the page banner; the bioRxiv API lists version 3 with date 2026-08-19
Retrieved: 2026-11-15T22:55:00Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.value

Source artifact SHA-256: d86de3315063e038ec8d5bed60b7b1a916c137ee60973e55d9d5c82f078d8dfd

Hash scope: The hash is of one download. bioRxiv regenerates this PDF on request, so the container bytes differ between downloads: a second download minutes later gave 08fcc83af256845d942345fc6b63c64911878733acd028edab5e9307d63319db. The pdftotext -layout text layer of both downloads is byte-identical (SHA-256 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2), and that text layer, archived gzipped in artifacts/ with SHA-256 0afdefd78a410d036d1c4f17e33bdf481e8d76241ee02f4c84c7c4be91ee72aa, is what every extracted value was read from.

Description
The two official model tables of the same project disagree on several parameter counts and context lengths, so neither can be taken as the project's single statement of model size.
Context-only references
BacBench repository README at commit 64b7d45

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Commit 64b7d45823b2ff2ef88458e3aa235caa461a12aa
Retrieved: 2026-11-15T23:09:36Z

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: c9d28efef5b4cc30adbcc9de224c350100f5aa2a15a025beaf10dcdeb86cd93e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Description
The two official model tables of the same project disagree on several parameter counts and context lengths, so neither can be taken as the project's single statement of model size.
Context-only references
Bacformer preprint, bioRxiv 2025.07.20.665723 version 3

Original source ↗

BacBench README 'Benchmarked models' table against preprint Table S9

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Version 3, posted 17 August 2026 according to the page banner; the bioRxiv API lists version 3 with date 2026-08-19
Retrieved: 2026-11-15T22:55:00Z

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: d86de3315063e038ec8d5bed60b7b1a916c137ee60973e55d9d5c82f078d8dfd

Hash scope: The hash is of one download. bioRxiv regenerates this PDF on request, so the container bytes differ between downloads: a second download minutes later gave 08fcc83af256845d942345fc6b63c64911878733acd028edab5e9307d63319db. The pdftotext -layout text layer of both downloads is byte-identical (SHA-256 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2), and that text layer, archived gzipped in artifacts/ with SHA-256 0afdefd78a410d036d1c4f17e33bdf481e8d76241ee02f4c84c7c4be91ee72aa, is what every extracted value was read from.

How to read the evidence

Sources and history

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

2 source records and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: bacformer-20261115-claim-model-table-parameter-differences

areas
microbes-communities
contexts
research
field
model_table_differences
rationale
The two official model tables of the same project disagree on several parameter counts and context lengths, so neither can be taken as the project's single statement of model size.
review
artifact sha256: c9d28efef5b4cc30adbcc9de224c350100f5aa2a15a025beaf10dcdeb86cd93e; method: transcription; source-hash-verification; ai-assisted-source-review; method note: Independent review pass. Each source artifact was retrieved again at review time and its SHA-256 compared with the source record; the quoted statement was then read at the recorded locator and compared with the recorded value. Access states were rechecked rather than taken from notes.md.; note: Statement re-read against the pinned artifact by a reviewer who did not extract this batch. Every artifact except the two preprint PDFs was downloaded again at review time and hashed to exactly the value its source record records, and is byte-identical to the copy kept in artifacts/.; retrieval url: https://raw.githubusercontent.com/macwiatrak/BacBench/64b7d45823b2ff2ef88458e3aa235caa461a12aa/README.md; reviewed at: 2026-11-15T23:55:00Z; reviewer: claude; reviewer note: Claude (Opus 5) review agent, independent of the agent that extracted this batch; no human review claimed. Transcription was checked against the pinned sources. Nothing was reproduced and no value was recomputed.
source locator
BacBench README 'Benchmarked models' table against preprint Table S9
value
The BacBench README and preprint Table S9 disagree on Nucleotide Transformer (250M against 235M), ProkBERT (27M against 26M), ESM-C (300M against 332M), ProtBert (420M against 412M), Bacformer Large (27M against 332M) and on the ESM-C context length (2,048 against 1,024 tokens)
Related records

Suggest a correction