Model

ProSST

Transformer protein language model that combines the residue sequence with quantized structure tokens through disentangled attention, pretrained by masked language modelling, scored in ProteinGym as a zero-shot substitution baseline from sequence and structure.

12 evaluations · 114 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

12 evaluations · 114 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: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort	0.535 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 ProSST (K=1024) AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=ProSST (K=1024)
Configuration: ProSST (K=128) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort	0.418 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 ProSST (K=128) AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=ProSST (K=128)
Configuration: ProSST (K=20) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort	0.363 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 ProSST (K=20) AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=ProSST (K=20)
Configuration: ProSST (K=2048) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort	0.481 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 ProSST (K=2048) AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=ProSST (K=2048)
Configuration: ProSST (K=4096) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort	0.587 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 ProSST (K=4096) AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=ProSST (K=4096)
Configuration: ProSST (K=512) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort	0.479 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 ProSST (K=512) AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=ProSST (K=512)
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.485 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 0.009. 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Average_Spearman'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.492 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Depth_1'
Configuration: ProSST (K=1024) [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, 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Depth_2'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.373 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Depth_3'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.341 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Depth_4'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.403 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Depth_5+'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.433 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Function_Activity'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.436 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Function_Binding'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.499 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Function_Expression'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.414 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Function_OrganismalFitness'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.642 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Function_Stability'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.585 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'High_MSA_depth'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.457 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Low_MSA_depth'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.466 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Medium_MSA_depth'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.483 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Taxa_Human'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.568 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Taxa_Other_Eukaryote'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.539 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Taxa_Prokaryote'
Configuration: ProSST (K=1024) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.436 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 ProSST (K=1024): 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 8, row 'ProSST (K=1024)', column 'Taxa_Virus'
Configuration: ProSST (K=128) [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.469 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 0.009. 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 ProSST (K=128): 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 14, row 'ProSST (K=128)', column 'Average_Spearman'

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

Use this model

How it works, versions and access

Versions and evaluated configurations

ProSST (K=1024) [ProteinGym 144fe22b snapshot] · configuration of
ProSST (K=128) [ProteinGym 144fe22b snapshot] · configuration of
ProSST (K=20) [ProteinGym 144fe22b snapshot] · configuration of
ProSST (K=2048) [ProteinGym 144fe22b snapshot] · configuration of
ProSST (K=4096) [ProteinGym 144fe22b snapshot] · configuration of
ProSST (K=512) [ProteinGym 144fe22b snapshot] · configuration of

Strengths, limitations and unresolved questions

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.

3 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
Description Transformer protein language model that combines the residue sequence with quantized structure tokens through disentangled attention, pretrained by masked language modelling, scored in ProteinGym as a zero-shot substitution baseline from sequence and structure. Individual claims	Abstract: ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention Original source ↗ uc20260930-source-proteingym-amfr-spearman: Benchmark CSV header (model scored in the zero-shot DMS substitution benchmark); run-doc-proteingym-readme-md-144fe22b: README 'Leaderboard' baseline table (model name, input modalities, reference); qa-descriptions-20261010-source-prosst: abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Europe PMC core record PPR/PPR839004 (title and abstract), bioRxiv 2024 Retrieved: 2026-10-10T06:44:11Z	source checked ["automated-source-review","ai-assisted-source-review"] · 2026-10-10 Audit details Description written from the cited source text; provenance text was generic and is kept here as previous_value. Independent review 2026-10-10: every stated fact is supported by the cited text. Field: `description` Claim: metadata-correction-60b514e1f652a5203a27 Source artifact SHA-256: `efcc6e8cd6905ee2d3de5ae096bfeb2388dad798a4dc9a75c19746f5a77f1bbd` Hash scope: SHA-256 of one retrieval of a Europe PMC REST search response. The response is not byte-stable: on 2026-10-10 a second retrieval of 10 of these 31 records differed only in JSON key order and parsed to identical content. The title and abstractText fields are the evidence. Inspected artifact
Description Transformer protein language model that combines the residue sequence with quantized structure tokens through disentangled attention, pretrained by masked language modelling, scored in ProteinGym as a zero-shot substitution baseline from sequence and structure. Individual claims	OATML-Markslab/ProteinGym / README.md Original source ↗ uc20260930-source-proteingym-amfr-spearman: Benchmark CSV header (model scored in the zero-shot DMS substitution benchmark); run-doc-proteingym-readme-md-144fe22b: README 'Leaderboard' baseline table (model name, input modalities, reference); qa-descriptions-20261010-source-prosst: abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-17T09:32:03.517591+00:00	source checked ["automated-source-review","ai-assisted-source-review"] · 2026-10-10 Audit details Description written from the cited source text; provenance text was generic and is kept here as previous_value. Independent review 2026-10-10: every stated fact is supported by the cited text. Field: `description` Claim: metadata-correction-60b514e1f652a5203a27 Source artifact SHA-256: `321487a8de52c6cfa647a658f61150dd72e0acb0125470524fb94d1f8b23321a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Description Transformer protein language model that combines the residue sequence with quantized structure tokens through disentangled attention, pretrained by masked language modelling, scored in ProteinGym as a zero-shot substitution baseline from sequence and structure. Individual claims	ProteinGym AMFR assay-level Spearman comparison Original source ↗ uc20260930-source-proteingym-amfr-spearman: Benchmark CSV header (model scored in the zero-shot DMS substitution benchmark); run-doc-proteingym-readme-md-144fe22b: README 'Leaderboard' baseline table (model name, input modalities, reference); qa-descriptions-20261010-source-prosst: abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c Retrieved: 2026-09-30	source checked ["automated-source-review","ai-assisted-source-review"] · 2026-10-10 Audit details Description written from the cited source text; provenance text was generic and is kept here as previous_value. Independent review 2026-10-10: every stated fact is supported by the cited text. Field: `description` Claim: metadata-correction-60b514e1f652a5203a27 Source artifact SHA-256: `f432423b87f79ac9778dfac86e3d95be041d246bc618dc0a406b35b0b7466437` 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

3 source records and release history

ProteinGym AMFR assay-level Spearman comparison · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
OATML-Markslab/ProteinGym / README.md · Original source · Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c
Abstract: ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention · Original source · Europe PMC core record PPR/PPR839004 (title and abstract), bioRxiv 2024

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: uc20260930-model-prosst

areas: proteins-complexes
source locator: Pinned ProteinGym Spearman CSV header: ProSST (K=20)
review: method: automated-source-review; reviewer: codex; reviewed at: 2026-09-30T21:40:59.576893+00:00; scope: Primary-source transcription and catalogue applicability audit; not human scientific review or independent experimental reproduction.; reviewer note: role: experimental use-case curation
entity level: family
identity scope: Family/method identity only; no undocumented checkpoint equivalence.

Related records

subject: ProSST: description
configuration of: ProSST (K=1024) [ProteinGym 144fe22b snapshot]
configuration of: ProSST (K=128) [ProteinGym 144fe22b snapshot]
configuration of: ProSST (K=20) [ProteinGym 144fe22b snapshot]
configuration of: ProSST (K=2048) [ProteinGym 144fe22b snapshot]
configuration of: ProSST (K=4096) [ProteinGym 144fe22b snapshot]
configuration of: ProSST (K=512) [ProteinGym 144fe22b snapshot]

Suggest a correction