rewirebio.iobenchmarks
Evidence claim

Training did not converge

Training convergence of EditJumps editor, clock normalisation 40

Validation loss fell from 798.0 at initialisation to 149.6 at step 8,500, 138.7 at step 16,000 and 135.2 at step 19,999. The paper states the model remained non-converged at the 20,000-step budget, with the final four evaluations improving by 2.3 units over preceding checkpoints.

A descriptive statement the source makes, with the location it is printed at.

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.

7 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
training_convergence
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Appendix D 'Training Protocol and Compute Resources'

Version: arXiv:2609.18745v1, 16 September 2026
Retrieved: 2026-11-16T00:03:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.field

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Limitations
1 values
  • Every reported score therefore comes from a model the authors state is not converged.
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Appendix D 'Training Protocol and Compute Resources'

Version: arXiv:2609.18745v1, 16 September 2026
Retrieved: 2026-11-16T00:03:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.limitations

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Source location
Appendix D 'Training Protocol and Compute Resources'
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Appendix D 'Training Protocol and Compute Resources'

Version: arXiv:2609.18745v1, 16 September 2026
Retrieved: 2026-11-16T00:03:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Claimed value
Validation loss fell from 798.0 at initialisation to 149.6 at step 8,500, 138.7 at step 16,000 and 135.2 at step 19,999. The paper states the model remained non-converged at the 20,000-step budget, with the final four evaluations improving by 2.3 units over preceding checkpoints.
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Appendix D 'Training Protocol and Compute Resources'

Version: arXiv:2609.18745v1, 16 September 2026
Retrieved: 2026-11-16T00:03:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.value

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Description
A descriptive statement the source makes, with the location it is printed at.
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Appendix D 'Training Protocol and Compute Resources'

Version: arXiv:2609.18745v1, 16 September 2026
Retrieved: 2026-11-16T00:03:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: description

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Relationship: subject
editjumps-20261115-config-editjumps-clock-40
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Appendix D 'Training Protocol and Compute Resources'

Version: arXiv:2609.18745v1, 16 September 2026
Retrieved: 2026-11-16T00:03:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: links:subject:editjumps-20261115-config-editjumps-clock-40

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Name
Training did not converge
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Appendix D 'Training Protocol and Compute Resources'

Version: arXiv:2609.18745v1, 16 September 2026
Retrieved: 2026-11-16T00:03:00Z

not individually reviewed

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: name

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

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: editjumps-20261115-claim-non-convergence

areas
protein-function; proteins-complexes
contexts
research
field
training_convergence
limitations
Every reported score therefore comes from a model the authors state is not converged.
review
artifact sha256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1; method: ai-assisted-source-review; source-hash-verification; method note: Independent review pass. Every pinned artifact was re-downloaded from the URL in its source record and its SHA-256 recomputed: all nine match. The arXiv PDF's text layer was regenerated with pdftotext -layout from poppler 26.08.0 and matches the hash notes.md records. npm run batch -- check-values over the whole batch reproduced the extractor's figures exactly (8 in_cell, 164 in_row, 3 locator_not_parsed, no wrong_column and no overclaimed_in_row). Because 164 results sit at in_row only, column assignment was then checked separately by review/column_check.py, written for this pass and using neither extract/tables.py nor extract/check_tables.py. It builds two independent column models: the PDF text layer, where Tables 2 and 4 are assigned by clustering printed field right edges and Table 1 by ordinal position within the row, and the arXiv HTML rendering parsed as a cell grid from the table markup. The two models agree on every cell, and all 172 table-located results match their locator's column and block in both. Four negative controls, two columns exchanged within a row, a row shifted one column left, a Ty1 and HER2 sub-column exchanged, and the Table 1 upper and lower blocks exchanged for one row label, are rejected by both models.; note: Re-read at the locator this claim names in each source it cites, against the re-retrieved artifacts. Every figure quoted in the claim was checked against the source text.; retrieval url: https://arxiv.org/pdf/2609.18745v1; reviewed at: 2026-11-16T01:30:00Z; reviewer: claude; reviewer note: Claude (Opus 5) review agent for issue #244, independent of the extraction agent; no human review claimed. All nine pinned artifacts were re-retrieved and their SHA-256 re-computed; no value was reproduced and no model was run.
source locator
Appendix D 'Training Protocol and Compute Resources'
value
Validation loss fell from 798.0 at initialisation to 149.6 at step 8,500, 138.7 at step 16,000 and 135.2 at step 19,999. The paper states the model remained non-converged at the 20,000-step budget, with the final four evaluations improving by 2.3 units over preceding checkpoints.
Related records

Suggest a correction