rewirebio.iobenchmarks
Evaluation

Evotune on Ty1, edits, 200 references

Developer-reported evaluation transcribed from the reimplemented block of the pinned EditJumps preprint; not reproduced.

Evaluation results

1 evaluation · 1 result. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: Evotuned ESM-2 650M, unforced infillingProtocol: EditJumps section 4.2 frame, 200 references: edits
Dataset subset: Ty1 reference holdout, 200 homologs
4.47 Edit count (mean realised edits per generated sequence, 400 generated sequences per family)
count · unknown

Uncertainty: Not reported by the source: The table prints a single value with no interval.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Evotune on Ty1, edits, 200 references

One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence.

Aggregation: Not reported

When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1) · Table 2, family block "ty1", row "Evotune", column "edits"

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-11-21-c8bea25e5abb · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence.

Configuration
Evotuned ESM-2 650M, unforced infilling
Protocol
EditJumps section 4.2 frame, 200 references: edits
Dataset subset
Ty1 reference holdout, 200 homologs
origin
Author-reported evaluation
configuration
Not reported
adaptation
Per-family retraining of a 650M trunk for 2,000 steps, then iterative infilling
aggregation
Pooled over the 400 generated sequences of the family
budget
b = 5 on Ty1 and b = 4 on HER2-VH, topped up over up to 8 rounds
dataset version
Ty1 homolog family mined from the paired Observed Antibody Space corpus at repository commit d827d47c3bcd29e0f4c15a15f9ac92a6cd859e99
inputs
One template sequence, a per-column entropy profile from the family alignment and an edit budget
metric implementation
mean realised edits per generated sequence, 400 generated sequences per family
population
One held-out antibody family, Ty1
protocol id
editjumps-20261115-protocol-ours-200-edits
split
20 templates and 20 variants per template, 400 generated sequences, scored against 200 held-out Ty1 homologs; agreement ceiling 300 real Ty1 homologs

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split
20 templates and 20 variants per template, 400 generated sequences, scored against 200 held-out Ty1 homologs; agreement ceiling 300 real Ty1 homologs
Adaptation
Per-family retraining of a 650M trunk for 2,000 steps, then iterative infilling
Scoring implementation
mean realised edits per generated sequence, 400 generated sequences per family

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.

21 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
Comparison: adaptation
Per-family retraining of a 650M trunk for 2,000 steps, then iterative infilling
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: aggregation
Pooled over the 400 generated sequences of the family
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: budget
b = 5 on Ty1 and b = 4 on HER2-VH, topped up over up to 8 rounds
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: dataset version
Ty1 homolog family mined from the paired Observed Antibody Space corpus at repository commit d827d47c3bcd29e0f4c15a15f9ac92a6cd859e99
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: inputs
One template sequence, a per-column entropy profile from the family alignment and an edit budget
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: metric implementation
mean realised edits per generated sequence, 400 generated sequences per family
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.metric_implementation

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: population
One held-out antibody family, Ty1
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.population

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: protocol id
editjumps-20261115-protocol-ours-200-edits
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.protocol_id

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Comparison: split
20 templates and 20 variants per template, 400 generated sequences, scored against 200 held-out Ty1 homologs; agreement ceiling 300 real Ty1 homologs
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

Audit details

Field: attributes.comparison.split

Source artifact SHA-256: 4211d8ef46c55efe8d89ba4ee6c0b4e57cca1e78d0856e9cdfbde37046a7f4e1

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

Inspected artifact

Limitations
8 values
  • Computational distribution comparison only. The value measures how similar generated sequences are to a reference set of natural sequences; it is not a measured binding affinity, specificity, stability or retained function.
  • Scores depend on the size of the reference set. Expanding the reference alignment from 200 to 800 homologs alters the normalised spectrum MMD ratio by 50% on Ty1 and 26% on HER2-VH, which the paper states is large enough to invert method rankings, so the ordering of methods is not stable across reference-set sizes.
  • 113 of Ty1's and 103 of HER2-VH's 200 reference sequences were present in the training set. Re-evaluating with strictly disjoint reference sets shifted spectrum MMD by -36.7% on Ty1 and -12.6% on HER2-VH and increased covariance agreement by 12 to 17 points.
  • The two held-out targets are single-chain constructs, the camelid VHH Ty1 and the isolated heavy chain HER2-VH, while the training pairs are concatenated two-chain VH.VL sequences. The paper names this as a domain shift.
  • Aggregate similarity is substantially driven by conserved framework scaffolds. 76% of residues are framework and 24% are complementarity-determining regions, and within those regions the model closes under 25% of the gap between random mutation and natural homologs, so a high aggregate score is not evidence of a better antigen-binding loop.
  • Seed values are not printed. Table 1's caption says it reports individual runs and intervals across three seeds; Table 2 prints one value per cell with no interval.
  • The paper states that its computed values and the published EvoFlows values are not comparable and that it could not recover the original experimental conditions from the EvoFlows paper. Table 1's caption adds that the two blocks are not comparable and that each row compares only against its own block's floor and ceiling.
  • The budget is calibrated in expectation: the realised count varies per sequence and the paper states there is no closed-form mapping from the clock normalisation to it.
Context-only references
When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows (arXiv v1)

Original source ↗

Table 2, family block "ty1", row "Evotune", column "edits"

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

not individually reviewed

No individual claim review recorded

author reported

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

How to read the evidence

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-eval-ours-200-edits-evotuning-ty1

areas
protein-function; proteins-complexes
contexts
research
comparison
adaptation: Per-family retraining of a 650M trunk for 2,000 steps, then iterative infilling; aggregation: Pooled over the 400 generated sequences of the family; budget: b = 5 on Ty1 and b = 4 on HER2-VH, topped up over up to 8 rounds; dataset version: Ty1 homolog family mined from the paired Observed Antibody Space corpus at repository commit d827d47c3bcd29e0f4c15a15f9ac92a6cd859e99; inputs: One template sequence, a per-column entropy profile from the family alignment and an edit budget; metric implementation: mean realised edits per generated sequence, 400 generated sequences per family; population: One held-out antibody family, Ty1; protocol id: editjumps-20261115-protocol-ours-200-edits; split: 20 templates and 20 variants per template, 400 generated sequences, scored against 200 held-out Ty1 homologs; agreement ceiling 300 real Ty1 homologs
limitations
Computational distribution comparison only. The value measures how similar generated sequences are to a reference set of natural sequences; it is not a measured binding affinity, specificity, stability or retained function.; Scores depend on the size of the reference set. Expanding the reference alignment from 200 to 800 homologs alters the normalised spectrum MMD ratio by 50% on Ty1 and 26% on HER2-VH, which the paper states is large enough to invert method rankings, so the ordering of methods is not stable across reference-set sizes.; 113 of Ty1's and 103 of HER2-VH's 200 reference sequences were present in the training set. Re-evaluating with strictly disjoint reference sets shifted spectrum MMD by -36.7% on Ty1 and -12.6% on HER2-VH and increased covariance agreement by 12 to 17 points.; The two held-out targets are single-chain constructs, the camelid VHH Ty1 and the isolated heavy chain HER2-VH, while the training pairs are concatenated two-chain VH.VL sequences. The paper names this as a domain shift.; Aggregate similarity is substantially driven by conserved framework scaffolds. 76% of residues are framework and 24% are complementarity-determining regions, and within those regions the model closes under 25% of the gap between random mutation and natural homologs, so a high aggregate score is not evidence of a better antigen-binding loop.; Seed values are not printed. Table 1's caption says it reports individual runs and intervals across three seeds; Table 2 prints one value per cell with no interval.; The paper states that its computed values and the published EvoFlows values are not comparable and that it could not recover the original experimental conditions from the EvoFlows paper. Table 1's caption adds that the two blocks are not comparable and that each row compares only against its own block's floor and ceiling.; The budget is calibrated in expectation: the realised count varies per sequence and the paper states there is no closed-form mapping from the clock normalisation to it.
origin
author_reported
protocol
One frame for every arm and both families: 20 templates per family and 20 variants per template, so 400 generated sequences, scored against a 200-sequence held-out natural homolog set, with the agreement ceiling computed on 300 real homologs. Sampling runs Euler tau-leaping over 50 steps. Every arm is held to a matched realised edit budget of about 4 to 5 edits per sequence.
retrospective
true
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: Checked against the re-retrieved sources at the locators this record and its linked records name.; 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.
scoring population
400 generated sequences against 200 held-out Ty1 homologs
seeds
Table 1's caption states individual runs and intervals across three seeds; Table 2 prints one value per cell
source locator
Table 2, family block "ty1", row "Evotune", column "edits"
Related records

Suggest a correction