rewirebio.iobenchmarks
Evaluation

Measured binding of a selected TorchCraft VHH to PDGFRb

The biolayer interferometry measurement of the displayed TorchCraft VHH design against PDGFRb.

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: TorchCraft framework-conditioned VHH design, raw outputProtocol: Apparent dissociation constant of a selected VHH design by biolayer interferometry
Dataset subset: PDGFRb measurements of the VHH validation campaign
268 Dissociation constant (apparent KD of a framework-conditioned VHH, measured by biolayer interferometry with the VHH immobilised and fitted with a 1:1 binding model, for one displayed representative design from a filtered and ranked pool, not a campaign hit rate)
nanomolar · lower

Uncertainty: Not reported by the source: No error, interval or replicate spread is printed for the KD values.

Coverage: 1 displayed designs scored (One representative design; the tested denominator is not stated.)

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

Measured binding of a selected TorchCraft VHH to PDGFRb

Not reported

Aggregation: Not reported

TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Figure 3a caption (page 5), sentence "Apparent dissociation constants of the displayed binders were 24.3, 122, 268, and 354 nM, respectively."; value for PDGFRb. The same number is printed in Section 2.3 and in the Figure 3a panel label "KD: 268nM".

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

Configuration
TorchCraft framework-conditioned VHH design, raw output
Protocol
Apparent dissociation constant of a selected VHH design by biolayer interferometry
Dataset subset
PDGFRb measurements of the VHH validation campaign
origin
Author-reported evaluation
configuration
As published in arXiv:2609.19770v1
adaptation
Raw TorchCraft output; no post hoc MPNN sequence redesign
aggregation
Not reported
budget
12500 candidates generated for this target before filtering and ranking
dataset version
Target PDGFRb as prepared in Supplementary Table S8
inputs
Target structure with crop and hotspots from Supplementary Table S3, and a fixed framework with CDR length ranges
metric implementation
Apparent KD from a 1:1 binding model in the instrument's curve-fitting module, after buffer-only background subtraction
population
One displayed representative design against PDGFRb; the number of designs expressed and tested is not stated
protocol id
torchcraft-20261115-protocol-bli-apparent-kd-vhh
split
Not reported

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

Reproduction

Split
Not reported
Adaptation
Raw TorchCraft output; no post hoc MPNN sequence redesign
Scoring implementation
Apparent KD from a 1:1 binding model in the instrument's curve-fitting module, after buffer-only background subtraction

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.

25 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
Candidate budget
12500
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.candidate_budget

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Candidate denominator
Unreported: the preprint states the generated pool and the filters, but not how many designs were expressed and tested.
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.candidate_denominator

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Candidate selection
Filtered by CDR interface rate above 0.6, CDR3 hotspot coverage rate above 0 and TorchCraft ipTM above 0.7, then ranked by the composite score 100 x TorchCraft ipTM minus the Rosetta interface score; the top-ranked designs were selected for validation.
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.candidate_selection

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Comparison: adaptation
Raw TorchCraft output; no post hoc MPNN sequence redesign
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Comparison: aggregation
Not reported
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Comparison: budget
12500 candidates generated for this target before filtering and ranking
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Comparison: dataset version
Target PDGFRb as prepared in Supplementary Table S8
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Comparison: inputs
Target structure with crop and hotspots from Supplementary Table S3, and a fixed framework with CDR length ranges
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Comparison: metric implementation
Apparent KD from a 1:1 binding model in the instrument's curve-fitting module, after buffer-only background subtraction
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.metric_implementation

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

Inspected artifact

Comparison: population
One displayed representative design against PDGFRb; the number of designs expressed and tested is not stated
Context-only references
TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1)

Original source ↗

No field-specific location recorded

Version: arXiv:2609.19770v1, submitted 17 September 2026
Retrieved: 2026-11-15T23:36:17Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.population

Source artifact SHA-256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21

Hash scope: SHA-256 of the PDF as downloaded. The pdftotext -layout text layer every value was read from hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b; it is regenerated from the PDF and is not archived here.

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: torchcraft-20261115-evaluation-bli-kd-vhh-pdgfrb

areas
protein-structure; molecular-interactions
contexts
research
candidate budget
12500
candidate denominator
Unreported: the preprint states the generated pool and the filters, but not how many designs were expressed and tested.
candidate selection
Filtered by CDR interface rate above 0.6, CDR3 hotspot coverage rate above 0 and TorchCraft ipTM above 0.7, then ranked by the composite score 100 x TorchCraft ipTM minus the Rosetta interface score; the top-ranked designs were selected for validation.
comparison
adaptation: Raw TorchCraft output; no post hoc MPNN sequence redesign; aggregation: Not reported; budget: 12500 candidates generated for this target before filtering and ranking; dataset version: Target PDGFRb as prepared in Supplementary Table S8; inputs: Target structure with crop and hotspots from Supplementary Table S3, and a fixed framework with CDR length ranges; metric implementation: Apparent KD from a 1:1 binding model in the instrument's curve-fitting module, after buffer-only background subtraction; population: One displayed representative design against PDGFRb; the number of designs expressed and tested is not stated; protocol id: torchcraft-20261115-protocol-bli-apparent-kd-vhh; split: Not reported
coverage
note: One representative design is displayed for this target; the tested denominator is not stated.; scored: 1; unit: displayed designs
endpoint
Apparent dissociation constant of a selected design
interpretation
Experimentally measured by the authors and not reproduced here. One selected design bound its target; this is not a campaign hit rate.
limitations
A single displayed design, not a campaign hit rate.; Developer-measured and selected after confidence filtering and Rosetta ranking.; Binding does not establish that the predicted interface is correct.
missing metadata
denominator: note: The number of designs expressed and tested against this target is not stated.; reason: unreported; replicate count: note: No replicate count is given for the reported KD.; reason: unreported
origin
author_reported
review
artifact sha256: f8145b5b95552dd30996eda2940507c0f32d09adfc60f44f28458e7872788f21; method: transcription; automated-source-review; source-hash-verification; method note: Every quotation and locator on this record was re-read in the refetched artifact named by retrieval_url. All seven pinned artifacts were re-retrieved by the reviewer on 2026-11-16T00:08Z. Six came back byte-identical to the hash on their source record. The Hugging Face page did not, and cannot: three consecutive fetches gave three different hashes. Normalising its per-request hf-sanitized CSS class hashes leaves one further per-request difference, window.requestId, and the page also prints a download counter; with those normalised the markup is identical. Its licence tag, gate text and dataset card matched the recorded quotations word for word, so the page is a per-retrieval stamp, not a changed page. The pdftotext -layout text layer of the refetched PDF hashes to 90f1da5f8a936766087beba0ade3f038f5b69504b9f581b42f2391f5640c5e6b, the value the extractor recorded.; retrieval url: https://arxiv.org/pdf/2609.19770v1; reviewed at: 2026-11-16T01:05:00Z; reviewer: claude; reviewer note: Claude (Opus 5) review agent, independent of the extractor; no human review claimed. Every pinned artifact was re-retrieved and hashed, and every stored value re-read against it. Nothing was reproduced: no design run, score, docking calculation or binding measurement was repeated, and no value was recomputed from source data.
version
As published in arXiv:2609.19770v1
Related records

Suggest a correction