Evaluation

ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22)

Official ProteinGym leaderboard summary row; transcribed, not reproduced.

Evaluation results

1 evaluation · 18 results. Different protocols are not a single leaderboard.

Protocol: ProteinGym v1.3 zero-shot DMS substitutions · Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)

Sorted by Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Binding assays: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Expression assays: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, High MSA depth proteins: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Human proteins: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Low MSA depth proteins: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays))	Spearman (ProteinGym zero-shot DMS substitutions, Medium MSA depth proteins: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Organismal fitness assays: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Other eukaryote proteins: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Prokaryote proteins: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Stability assays: mean over proteins of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 1 substitution: mean over protein and selection-type groups of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 2 substitutions: mean over protein and selection-type groups of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 3 substitutions: mean over protein and selection-type groups of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 4 substitutions: mean over protein and selection-type groups of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, variants with 5 or more substitutions: mean over protein and selection-type groups of assay-level Spearman)	Spearman (ProteinGym zero-shot DMS substitutions, Virus proteins: mean over proteins of assay-level Spearman)
ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]Evaluation	0.451	0.344	0.42	0.51	0.454	0.398	0.43	0.434	0.376	0.521	0.478	0.557	0.437	0.281	0.266	0.217	0.287	0.338

All 18 result rows with coverage, uncertainty and sources

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: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.43 Spearman (ProteinGym zero-shot DMS substitutions, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)) unitless · higher Uncertainty: SE 0.006. From compute_bootstrap_standard_error_functional_categories in performance_DMS_benchmarks.py at 144fe22 (default 10,000 resamples, lines 95-111 and 310-315); not an absolute standard error of the model's own average. Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Average_Spearman'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.437 Spearman (ProteinGym zero-shot DMS substitutions, variants with 1 substitution: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Depth_1'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.281 Spearman (ProteinGym zero-shot DMS substitutions, variants with 2 substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Depth_2'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.266 Spearman (ProteinGym zero-shot DMS substitutions, variants with 3 substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Depth_3'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.217 Spearman (ProteinGym zero-shot DMS substitutions, variants with 4 substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Depth_4'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.287 Spearman (ProteinGym zero-shot DMS substitutions, variants with 5 or more substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Depth_5+'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.451 Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Function_Activity'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.344 Spearman (ProteinGym zero-shot DMS substitutions, Binding assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Function_Binding'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.42 Spearman (ProteinGym zero-shot DMS substitutions, Expression assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Function_Expression'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.376 Spearman (ProteinGym zero-shot DMS substitutions, Organismal fitness assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Function_OrganismalFitness'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.557 Spearman (ProteinGym zero-shot DMS substitutions, Stability assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Function_Stability'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.51 Spearman (ProteinGym zero-shot DMS substitutions, High MSA depth proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'High_MSA_depth'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.398 Spearman (ProteinGym zero-shot DMS substitutions, Low MSA depth proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Low_MSA_depth'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.434 Spearman (ProteinGym zero-shot DMS substitutions, Medium MSA depth proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Medium_MSA_depth'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.454 Spearman (ProteinGym zero-shot DMS substitutions, Human proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Taxa_Human'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.521 Spearman (ProteinGym zero-shot DMS substitutions, Other eukaryote proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Taxa_Other_Eukaryote'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.478 Spearman (ProteinGym zero-shot DMS substitutions, Prokaryote proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Taxa_Prokaryote'
Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.338 Spearman (ProteinGym zero-shot DMS substitutions, Virus proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ProtSSN (k=10, h=512): ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38, row 'ProtSSN (k=10, h=512)', column 'Taxa_Virus'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

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 2026-10-22-1b7cf027e4f6 · 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

ProteinGym zero-shot DMS substitutions, Spearman summary

Configuration: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]
Protocol: ProteinGym v1.3 zero-shot DMS substitutions
Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)

origin: Evaluation origin not reported
configuration: Not reported
protocol id: rewire-proteingym-v1-3-dms-substitutions
dataset version: 144fe22b07dfaeec2b366f2346203a9838a55b4c
split: Not reported
population: 217 DMS substitution assays (single and multiple substitutions)
inputs: ProteinGym model label 'ProtSSN (k=10, h=512)', model type 'Single sequence & Structure'
adaptation: Zero-shot; no assay labels used
metric implementation: Spearman per assay (performance_DMS_benchmarks.py at 144fe22)
aggregation: Assay-level metrics rounded to 3 decimals; averaged over assays per UniProt ID and selection type, then over proteins within each selection type, then equally over the five selection types (performance_DMS_benchmarks.py lines 304-315); breakdown columns average per protein within the category (lines 336-348) or, for mutational depth, over protein and selection-type groups (lines 321-330)
budget: Not reported

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

Reproduction

Split: Not reported
Adaptation: Zero-shot; no assay labels used
Scoring implementation: Spearman per assay (performance_DMS_benchmarks.py at 144fe22)

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.

36 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Comparison: adaptation Zero-shot; no assay labels used Context-only references	Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-23T18:39:35.572257+00:00	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `0002bc1b031c02dc2d67fde53da092c8fd301415645e8e83b425b4183570eba2` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: adaptation Zero-shot; no assay labels used Context-only references	ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-10-14T13:39:32Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `ee61a7c09efbfbd8d9a6c9355092c798032a578fa58c6f6256b5da8778555fd4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: aggregation Assay-level metrics rounded to 3 decimals; averaged over assays per UniProt ID and selection type, then over proteins within each selection type, then equally over the five selection types (performance_DMS_benchmarks.py lines 304-315); breakdown columns average per protein within the category (lines 336-348) or, for mutational depth, over protein and selection-type groups (lines 321-330) Context-only references	Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-23T18:39:35.572257+00:00	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `0002bc1b031c02dc2d67fde53da092c8fd301415645e8e83b425b4183570eba2` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: aggregation Assay-level metrics rounded to 3 decimals; averaged over assays per UniProt ID and selection type, then over proteins within each selection type, then equally over the five selection types (performance_DMS_benchmarks.py lines 304-315); breakdown columns average per protein within the category (lines 336-348) or, for mutational depth, over protein and selection-type groups (lines 321-330) Context-only references	ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-10-14T13:39:32Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `ee61a7c09efbfbd8d9a6c9355092c798032a578fa58c6f6256b5da8778555fd4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget Not reported Context-only references	Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-23T18:39:35.572257+00:00	missing or unspecified No individual claim review recorded unreported Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `0002bc1b031c02dc2d67fde53da092c8fd301415645e8e83b425b4183570eba2` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget Not reported Context-only references	ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-10-14T13:39:32Z	missing or unspecified No individual claim review recorded unreported Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `ee61a7c09efbfbd8d9a6c9355092c798032a578fa58c6f6256b5da8778555fd4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: dataset version 144fe22b07dfaeec2b366f2346203a9838a55b4c Context-only references	Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-23T18:39:35.572257+00:00	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `0002bc1b031c02dc2d67fde53da092c8fd301415645e8e83b425b4183570eba2` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: dataset version 144fe22b07dfaeec2b366f2346203a9838a55b4c Context-only references	ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-10-14T13:39:32Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `ee61a7c09efbfbd8d9a6c9355092c798032a578fa58c6f6256b5da8778555fd4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: inputs ProteinGym model label 'ProtSSN (k=10, h=512)', model type 'Single sequence & Structure' Context-only references	Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-23T18:39:35.572257+00:00	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `0002bc1b031c02dc2d67fde53da092c8fd301415645e8e83b425b4183570eba2` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: inputs ProteinGym model label 'ProtSSN (k=10, h=512)', model type 'Single sequence & Structure' Context-only references	ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 Original source ↗ benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-10-14T13:39:32Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `ee61a7c09efbfbd8d9a6c9355092c798032a578fa58c6f6256b5da8778555fd4` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

2 source records and release history

ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
Protocol metadata evidence: proteingym-proteingym-performance_DMS_benchmarks.py · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: vep-lit-20261014-eval-pg-dms-protssn-k-10-h-512

areas: proteins-complexes
contexts: research
origin: unreported
protocol: ProteinGym zero-shot DMS substitutions, Spearman summary
input information: ProteinGym 'Model type' label: Single sequence & Structure
comparison: protocol id: rewire-proteingym-v1-3-dms-substitutions; dataset version: 144fe22b07dfaeec2b366f2346203a9838a55b4c; split: Not reported; population: 217 DMS substitution assays (single and multiple substitutions); inputs: ProteinGym model label 'ProtSSN (k=10, h=512)', model type 'Single sequence & Structure'; adaptation: Zero-shot; no assay labels used; metric implementation: Spearman per assay (performance_DMS_benchmarks.py at 144fe22); aggregation: Assay-level metrics rounded to 3 decimals; averaged over assays per UniProt ID and selection type, then over proteins within each selection type, then equally over the five selection types (performance_DMS_benchmarks.py lines 304-315); breakdown columns average per protein within the category (lines 336-348) or, for mutational depth, over protein and selection-type groups (lines 321-330); budget: Not reported
source locator: benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 38 (Model_rank 37)
missing metadata: budget: reason: unreported; per model scored count: reason: unreported; note: The summary file does not print how many assays each model scored; split: reason: inapplicable; note: Zero-shot track
review: reviewer: claude; reviewer note: Claude review agent; no human review claimed. Independent Claude (Opus 5.5) review agent, separate from the extraction agent that built this batch. Automated review only. Transcription, not reproduction.; reviewed at: 2026-10-14T15:30:00Z; artifact sha256: ee61a7c09efbfbd8d9a6c9355092c798032a578fa58c6f6256b5da8778555fd4; retrieval url: https://raw.githubusercontent.com/OATML-Markslab/ProteinGym/144fe22b07dfaeec2b366f2346203a9838a55b4c/benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv; method: source-hash-verification; deterministic-table-parse; scope-review; method note: Links, origin and comparison fields checked against the source and the linked protocol; results checked by review/check_values.py.; note: Origin set to unreported in review: ProteinGym computed the metric with its own scripts, but the summary file does not say who generated each model's scores (the README says new baselines are added with scores supplied by the requester, and others are scored by the maintainers), and most models are not by the ProteinGym authors. author_reported would wrongly mark most rows as developer-reported; paper_compilation would wrongly mark them as copied from earlier papers.

Related records

system: ProtSSN (k=10, h=512) [ProteinGym 144fe22b snapshot]
assessment: ProteinGym v1.3 zero-shot DMS substitutions
data: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)
evaluation: ProtSSN (k=10, h=512) Average_Spearman (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Depth_1 (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Depth_2 (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Depth_3 (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Depth_4 (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Depth_5+ (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Function_Activity (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Function_Binding (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Function_Expression (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Function_OrganismalFitness (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Function_Stability (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) High_MSA_depth (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Low_MSA_depth (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Medium_MSA_depth (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Taxa_Human (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Taxa_Other_Eukaryote (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Taxa_Prokaryote (ProteinGym 144fe22)
evaluation: ProtSSN (k=10, h=512) Taxa_Virus (ProteinGym 144fe22)

Suggest a correction