Configuration

RFdiffusion

RFdiffusion generates protein structures, optionally conditioned on a motif, target or symmetry constraint.

Sources (3)

RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6

20 evaluations · 20 results

How it worksRFdiffusion workflow

Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.

Sources (3)

Overview

Model type

Diffusion-based protein backbone generator

Inputs

Unconditional length specification or structural constraints such as a motif, target and contig map.

Outputs

Generated protein backbone designs for downstream sequence design and assessment.

Access

Official project documentation and implementation: https://github.com/RosettaCommons/RFdiffusion

Sources (3)

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

20 evaluations · 20 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.32 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-100-DIVERSITY-MAX-CLUST: length 100, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 100, Diversity Max Clust.↑)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.41 ± 0.03 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-100-DIVERSITY-PAIRWISE-TM: length 100, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 100, Diversity pairwise TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-100-NOVELTY-MAX-TM: length 100, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.76 ± 0.01 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-100-NOVELTY-MAX-TM: length 100, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 100, Novelty Max TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-100-QUALITY-SCRMSD: length 100, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.48 ± 0.56 scrmsd score · lower Uncertainty: type: standard_deviation; value: 0.56 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-100-QUALITY-SCRMSD: length 100, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 100, Quality scRMSD ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-100-QUALITY-SCTM: length 100, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.98 ± 0.12 sctm score · higher Uncertainty: type: standard_deviation; value: 0.12 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-100-QUALITY-SCTM: length 100, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 100, Quality scTM ↑)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.65 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-300-DIVERSITY-MAX-CLUST: length 300, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 300, Diversity Max Clust. ↑)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.36 ± 0.03 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.03 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-300-DIVERSITY-PAIRWISE-TM: length 300, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 300, Diversity pairwise TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-300-NOVELTY-MAX-TM: length 300, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.64 ± 0.01 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.01 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-300-NOVELTY-MAX-TM: length 300, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 300, Novelty Max TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-300-QUALITY-SCRMSD: length 300, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	1.03 ± 3.14 scrmsd score · lower Uncertainty: type: standard_deviation; value: 3.14 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-300-QUALITY-SCRMSD: length 300, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 300, Quality scRMSD ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-300-QUALITY-SCTM: length 300, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.96 ± 0.15 sctm score · higher Uncertainty: type: standard_deviation; value: 0.15 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-300-QUALITY-SCTM: length 300, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 300, Quality scTM ↑)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-50-DIVERSITY-MAX-CLUST: length 50, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.67 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-50-DIVERSITY-MAX-CLUST: length 50, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 50, Diversity Max Clust. ↑)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-50-DIVERSITY-PAIRWISE-TM: length 50, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.58 ± 0.05 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.05 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-50-DIVERSITY-PAIRWISE-TM: length 50, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 50, Diversity pairwise TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-50-NOVELTY-MAX-TM: length 50, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.65 ± 0.16 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.16 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-50-NOVELTY-MAX-TM: length 50, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 50, Novelty Max TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-50-QUALITY-SCRMSD: length 50, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.45 ± 1.71 scrmsd score · lower Uncertainty: type: standard_deviation; value: 1.71 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-50-QUALITY-SCRMSD: length 50, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 50, Quality scRMSD ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-50-QUALITY-SCTM: length 50, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.95 ± 0.12 sctm score · higher Uncertainty: type: standard_deviation; value: 0.12 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-50-QUALITY-SCTM: length 50, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 50, Quality scTM ↑)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust. Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.89 max-clust score · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-500-DIVERSITY-MAX-CLUST: length 500, Diversity Max Clust. Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 500, Diversity Max Clust.↑)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.33 ± 0.02 pairwise-tm score · lower Uncertainty: type: standard_deviation; value: 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-500-DIVERSITY-PAIRWISE-TM: length 500, Diversity pairwise TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 500, Diversity pairwise TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-500-NOVELTY-MAX-TM: length 500, Novelty Max TM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.62 ± 0.004 max-tm score · lower Uncertainty: type: standard_deviation; value: 0.004 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-500-NOVELTY-MAX-TM: length 500, Novelty Max TM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 500, Novelty Max TM ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-500-QUALITY-SCRMSD: length 500, Quality scRMSD Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	5.60 ± 5.66 scrmsd score · lower Uncertainty: type: standard_deviation; value: 5.66 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-500-QUALITY-SCRMSD: length 500, Quality scRMSD Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 500, Quality scRMSD ↓)
Configuration: RFdiffusion	Task: ProteinBench BB-LENGTH-500-QUALITY-SCTM: length 500, Quality scTM Dataset subset: Designed backbones at fixed lengths (ProteinBench split)	0.79 ± 0.19 sctm score · higher Uncertainty: type: standard_deviation; value: 0.19 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RFdiffusion on ProteinBench BB-LENGTH-500-QUALITY-SCTM: length 500, Quality scTM Unconditional backbone design at a fixed sequence length. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 3, row(RFdiffusion), column(length 500, Quality scTM ↑)

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Use this model

How it works, versions and access

Related profile: RFdiffusion. This page retains the exact record and its evaluation context.

This configuration

Protein model evaluated by the ProteinBench authors under their harness.

record: RFdiffusion
configuration: Not reported
entity type: Configuration

How it works

RFdiffusion generates protein structures, optionally conditioned on a motif, target or symmetry constraint. Diffusion-based protein structure generation with checkpoint-specific conditioning and denoising configuration. The documented inputs are unconditional length specification or structural constraints such as a motif, target and contig map. The output consists of generated protein backbone designs for downstream sequence design and assessment.

Sources (3)

Versions and reproducibility

Base, active-site, sequence-inpainting and other conditioning-specific checkpoints; preserve the selected weight identity. The RFdiffusion training crop is 384 residues (supplementary Table 6). This crop size is not an inference maximum; contig lengths and conditional task settings remain explicit.

Sources (3)

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Supports motif scaffolding, symmetry, binder design and partial diffusion through explicit conditioning options.
Sources (3)
RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6

Limitations and conditions

Different conditioning modes use different trained weights. Backbone generation alone does not establish a functional experimentally validated protein.
Sources (3)
RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6

Profile review details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Stable record: discovery-model-rfdiffusion

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Inputs, outputs and configuration
Property	Description and evidence
Model type	Diffusion-based protein backbone generator Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Architecture	Diffusion-based protein structure generation with checkpoint-specific conditioning and denoising configuration. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Inputs	Unconditional length specification or structural constraints such as a motif, target and contig map. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Outputs	Generated protein backbone designs for downstream sequence design and assessment. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Parameters	The complete supplementary architecture and training sections specify RoseTTAFold-derived modules and training settings but do not state a total for each released conditional checkpoint. · Not reported in inspected sources Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Known versions	Base, active-site, sequence-inpainting and other conditioning-specific checkpoints; preserve the selected weight identity. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Training data	Fine-tunes pretrained RoseTTAFold to denoise protein backbone structures from the PDB; unconditional and task-conditioned variants are distinct configurations. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Training cutoff	The supplementary RoseTTAFold pretraining description specifies a 2 August 2021 PDB cutoff and additional AlphaFold2 models. This is pretraining provenance, not a date for every conditional design fine-tune. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Context limits	The RFdiffusion training crop is 384 residues (supplementary Table 6). This crop size is not an inference maximum; contig lengths and conditional task settings remain explicit. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Weights licence	BSD licence in the inspected LICENSE explicitly covers both source code and linked downloadable model weights. Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Access	Official project documentation and implementation: https://github.com/RosettaCommons/RFdiffusion Sources (3) RosettaCommons/RFdiffusion: README.md; rfdiffusion: Journal full-text XML; rfdiffusion-supp: Publisher supplementary archive · RFdiffusion paper Main text and Extended Data Figure 1 (pretrained representations); README.md: model variants, contigs and licence; Supplementary Methods Sections 1.4 and 4.1, Table 6
Code licence	BSD-3-Clause Sources RosettaCommons/RFdiffusion: LICENSE · LICENSE: licence text

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Relationship: family discovery-model-rfdiffusion Individual claims	proteinbench primary benchmark evidence Original source ↗ Tables 3; task methods and corresponding named row Version: 2409.06744v1 Retrieved: 2026-09-16T21:07:13.231727+00:00	source checked automated source review · 2026-09-23 Audit details Source review establishes this relationship only. Exact evaluated configurations and original numerical review status remain unchanged. Paper evaluates this named model under its ProteinBench harness. Association is to the family, not an assertion of checkpoint equivalence or cross-task comparability. Field: `links:family:discovery-model-rfdiffusion` Claim: model-evaluation-identity-7ab2fb1d706347ec24d1 Source artifact SHA-256: `4334d636223ad42bfb9ae68aae03f5a255c29ba1cebe7b8f9588fb3b9b5453b2` Hash scope: Exact retrieved primary paper artifact bytes. Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: source checked

1 source records and release history

proteinbench primary benchmark evidence · Original source · 2409.06744v1

Download this release

Technical metadata and extraction receipts

Stable ID: proteinbench-method-rfdiffusion

areas: proteins-complexes
source locator: Table 3, row(RFdiffusion)
missing metadata: checkpoint revision: unreported; parameters: unextracted

Related records

Suggest a correction