rewire.itbenchmarks
Evaluation

foldbench protein ligand helixfold3

Author-reported evaluation; no new execution.

Research readiness

These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.

Release 2026-09-30-e37e3ab1284d · 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.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • metric replay: verification is missing

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.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • metric replay: verification is missing
  • annotations: verification is missing
  • dependence: verification is missing

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.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • recipe pinned: verification is missing
  • resource estimate: verification is missing

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.
  • artifact hashes: verification is missing
  • join integrity: verification is missing
  • score semantics: verification is missing
  • independent validation: verification is missing
  • overlap checked: verification is missing

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.

Read reviewed discrepancy investigations

Evaluation results

1 evaluation · 3 results. 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: HelixFold 3 — FoldBench published inferenceProtocol: FoldBench protein-ligand published full-set assessment
Dataset: FoldBench protein-ligand published targets
0.89 lddt-lp
fraction · higher

Uncertainty: Not reported

Coverage: Not reported scored / Not reported eligible

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

foldbench protein ligand helixfold3

Not reported

Aggregation: source table mean

FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-ligand block, LDDT-LP row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inferenceProtocol: FoldBench protein-ligand published full-set assessment
Dataset: FoldBench protein-ligand published targets
0.69 lddt-pli
fraction · higher

Uncertainty: Not reported

Coverage: Not reported scored / Not reported eligible

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

foldbench protein ligand helixfold3

Not reported

Aggregation: source table mean

FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-ligand block, LDDT-PLI row, HelixFold 3 column; Table 1 assessable count
Configuration: HelixFold 3 — FoldBench published inferenceProtocol: FoldBench protein-ligand published full-set assessment
Dataset: FoldBench protein-ligand published targets
51.8% success-rate
percent · higher

Uncertainty: Not reported

Coverage: Not reported scored / Not reported eligible

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

foldbench protein ligand helixfold3

Not reported

Aggregation: source table mean

FoldBench supplementary target coverage and performance · Supplementary Table 3, protein-ligand block, Success rate row, HelixFold 3 column; Table 1 assessable count

Source checking is not independent reproduction. Release 2026-09-30-e37e3ab1284d.

Evaluation procedure

Not reported

Configuration
HelixFold 3 — FoldBench published inference
Protocol
FoldBench protein-ligand published full-set assessment
Dataset
FoldBench protein-ligand published targets
origin
Author-reported evaluation
configuration
Not reported
protocol id
ucc-research-protocol-foldbench-protein-ligand
dataset version
published Supplementary Tables 1–3
split
source-specific; see protocol and limitations
population
Full-set task population; distinct model failures mean assessable subsets differ. Source Table 1 is authoritative for this snapshot.
inputs
5 seeds × 5 samples, 10 recycles; highest model ranking score. Paper-specific input/code adjustments; H800 80GB inference.
adaptation
source-specific configuration; see model configuration
aggregation
metric-specific; inspect result

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

Reproduction

Split
source-specific; see protocol and limitations
Adaptation
source-specific configuration; see model configuration
Scoring implementation
Not reported

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.

34 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-30-e37e3ab1284d
Property and statementOriginal source and locationReview and provenance
attributes.aggregation
mean over assessable targets; top-ranked prediction
Context-only references
Benchmarking all-atom biomolecular structure prediction with FoldBench

Original source ↗

No field-specific location recorded

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

Version: 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:23:29Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.aggregation

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.aggregation
mean over assessable targets; top-ranked prediction
Context-only references
FoldBench supplementary target coverage and performance

Original source ↗

No field-specific location recorded

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

Version: Supplementary Information to 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:26:52Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.aggregation

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.assessable_targets
466
Context-only references
Benchmarking all-atom biomolecular structure prediction with FoldBench

Original source ↗

No field-specific location recorded

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

Version: 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:23:29Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.assessable_targets

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.assessable_targets
466
Context-only references
FoldBench supplementary target coverage and performance

Original source ↗

No field-specific location recorded

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

Version: Supplementary Information to 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:26:52Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.assessable_targets

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.comparison.adaptation
source-specific configuration; see model configuration
Context-only references
Benchmarking all-atom biomolecular structure prediction with FoldBench

Original source ↗

No field-specific location recorded

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

Version: 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:23:29Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.comparison.adaptation
source-specific configuration; see model configuration
Context-only references
FoldBench supplementary target coverage and performance

Original source ↗

No field-specific location recorded

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

Version: Supplementary Information to 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:26:52Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.comparison.aggregation
metric-specific; inspect result
Context-only references
Benchmarking all-atom biomolecular structure prediction with FoldBench

Original source ↗

No field-specific location recorded

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

Version: 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:23:29Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.comparison.aggregation
metric-specific; inspect result
Context-only references
FoldBench supplementary target coverage and performance

Original source ↗

No field-specific location recorded

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

Version: Supplementary Information to 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:26:52Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.comparison.dataset_version
published Supplementary Tables 1–3
Context-only references
Benchmarking all-atom biomolecular structure prediction with FoldBench

Original source ↗

No field-specific location recorded

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

Version: 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:23:29Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: Not recorded

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

Inspected artifact

attributes.comparison.dataset_version
published Supplementary Tables 1–3
Context-only references
FoldBench supplementary target coverage and performance

Original source ↗

No field-specific location recorded

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

Version: Supplementary Information to 10.1038/s41467-025-67127-3
Retrieved: 2026-09-30T21:26:52Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: Not recorded

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

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-30-e37e3ab1284d · Record review: source checked

2 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: ucc-research-eval-foldbench-protein-ligand-helixfold3

origin
author_reported
review
method: automated_source_review; actor: Codex research coverage worker; reviewed at: 2026-09-30T21:43:56Z; note: Primary-source table transcription and scope review; no independent reproduction or human scientific review.
comparison
protocol id: ucc-research-protocol-foldbench-protein-ligand; dataset version: published Supplementary Tables 1–3; split: source-specific; see protocol and limitations; population: Full-set task population; distinct model failures mean assessable subsets differ. Source Table 1 is authoritative for this snapshot.; inputs: 5 seeds × 5 samples, 10 recycles; highest model ranking score. Paper-specific input/code adjustments; H800 80GB inference.; adaptation: source-specific configuration; see model configuration; aggregation: metric-specific; inspect result
total targets
558
assessable targets
466
scoring population
model-specific assessable counts from Table 1; exact Table 3 metric denominators not independently reconciled
aggregation
mean over assessable targets; top-ranked prediction
Related records

Suggest a correction