Task

ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer

Specificity SeqSim-outer. Scored with SeqSim-outer on RAbD, 55 antibody-antigen complexes. Antibody design on the 55 antibody-antigen complexes of the RAbD set.

8 evaluations · 8 metric rows

Overview

Specificity SeqSim-outer. Scored with SeqSim-outer on RAbD, 55 antibody-antigen complexes. Antibody design on the 55 antibody-antigen complexes of the RAbD set.

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

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

ProteinBench

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.

Comparison and metric

ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer

seqsim-outer (score) · Lower values are better for this metric.

Every method ProteinBench reports on Specificity SeqSim-outer, scored with SeqSim-outer on RAbD, 55 antibody-antigen complexes.

Evaluation protocol · RAbD, 55 antibody-antigen complexes (ProteinBench split)

RAbD (natural) · Configuration · Author-reported evaluation0.26
HERN · Configuration · Author-reported evaluation0.41
MEAN · Configuration · Author-reported evaluation0.65
dyMEAN · Configuration · Author-reported evaluation0.58
dyMEAN-FixFR · Configuration · Author-reported evaluation0.60
DiffAb · Configuration · Author-reported evaluation0.37
AbDPO · Configuration · Author-reported evaluation0 .38
AbDPO++ · Configuration · Author-reported evaluation0.39

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

proteinbench primary benchmark evidence · Table 6, column(Specificity SeqSim-outer ↓)

Values, uncertainty and evidence

seqsim-outer: original source values
Tested entity	Printed value	Uncertainty	Evidence
RAbD (natural) · Configuration	0.26 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(RAbD (natural)), column(Specificity SeqSim-outer ↓)
HERN · Configuration	0.41 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(HERN), column(Specificity SeqSim-outer ↓)
MEAN · Configuration	0.65 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(MEAN), column(Specificity SeqSim-outer ↓)
dyMEAN · Configuration	0.58 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN), column(Specificity SeqSim-outer ↓)
dyMEAN-FixFR · Configuration	0.60 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Specificity SeqSim-outer ↓)
DiffAb · Configuration	0.37 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(DiffAb), column(Specificity SeqSim-outer ↓)
AbDPO · Configuration	0 .38 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(AbDPO), column(Specificity SeqSim-outer ↓)
AbDPO++ · Configuration	0.39 score	Not reported	Author-reported evaluation · source checkedproteinbench primary benchmark evidence · Table 6, row(AbDPO++), column(Specificity SeqSim-outer ↓)

Scope and limitations

Author-reported numbers, source checked but not independently reproduced.
Many of these metrics are better when lower, including scRMSD, perplexity and binding energy. The direction comes from the arrow in the paper's own header.
Rows such as Native PDBs and RAbD are the natural reference the authors include for scale, not a competing method.

Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-134cd1815de8 · 8 evaluations · 8 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
AbDPO on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: AbDPOTask: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0 .38 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(AbDPO), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.
AbDPO++ on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: AbDPO++Task: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.39 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(AbDPO++), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.
DiffAb on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: DiffAbTask: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.37 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(DiffAb), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.
dyMEAN on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: dyMEANTask: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.58 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.
dyMEAN-FixFR on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: dyMEAN-FixFRTask: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.60 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(dyMEAN-FixFR), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.
HERN on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: HERNTask: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.41 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(HERN), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.
MEAN on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: MEANTask: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.65 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(MEAN), column(Specificity SeqSim-outer ↓) Source checking is not independent reproduction.
RAbD (natural) on ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer Configuration: RAbD (natural)Task: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outerDataset subset: RAbD, 55 antibody-antigen complexes (ProteinBench split) Antibody design on the 55 antibody-antigen complexes of the RAbD set. Author-reported evaluation · Evaluation metadata: source checked
0.26 seqsim-outer Unit: score · Direction: lower	Uncertainty: Not reported Scored: Not reported · Eligible: Not reported	source checkedproteinbench primary benchmark evidence · Table 6, row(RAbD (natural)), column(Specificity SeqSim-outer ↓) Source checking is not 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 2026-09-17-134cd1815de8
Property and statement	Original source and location	Review and provenance
Relationship: part of discovery-benchmark-proteinbench Individual claims	proteinbench primary benchmark evidence Original source ↗ Table 6, column(Specificity SeqSim-outer ↓) Version: 2409.06744v1 Retrieved: 2026-09-16T21:07:13.231727+00:00	source checked automated source review · 2026-09-18 Audit details Primary-source transcription with no human sign-off and no independent reproduction. Field: `links:part_of:discovery-benchmark-proteinbench` Claim: proteinbench-association-ab-specificity-seqsim-outer 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

Release 2026-09-17-134cd1815de8 · 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-task-ab-specificity-seqsim-outer

areas: proteins-complexes
tasks: Specificity SeqSim-outer
metric: SeqSim-outer
metric direction: lower
dataset: RAbD, 55 antibody-antigen complexes
protocol: Antibody design on the 55 antibody-antigen complexes of the RAbD set.
source locator: Table 6, column(Specificity SeqSim-outer ↓)
comparison panels: id: proteinbench-panel-ab-specificity-seqsim-outer; title: ProteinBench AB-SPECIFICITY-SEQSIM-OUTER: Specificity SeqSim-outer; protocol id: proteinbench-task-ab-specificity-seqsim-outer; dataset id: proteinbench-dataset-rabd-55-antibody-antigen-complexes; metric: seqsim-outer; unit: score; direction: lower; result ids: proteinbench-result-rabd-natural-ab-specificity-seqsim-outer-seqsim-outer; proteinbench-result-hern-ab-specificity-seqsim-outer-seqsim-outer; proteinbench-result-mean-ab-specificity-seqsim-outer-seqsim-outer; proteinbench-result-dymean-ab-specificity-seqsim-outer-seqsim-outer; proteinbench-result-dymean-fixfr-ab-specificity-seqsim-outer-seqsim-outer; proteinbench-result-diffab-ab-specificity-seqsim-outer-seqsim-outer; proteinbench-result-abdpo-ab-specificity-seqsim-outer-seqsim-outer; proteinbench-result-abdpo-plus-plus-ab-specificity-seqsim-outer-seqsim-outer; source ids: expansion-p3-proteinbench; source locator: Table 6, column(Specificity SeqSim-outer ↓); context: Every method ProteinBench reports on Specificity SeqSim-outer, scored with SeqSim-outer on RAbD, 55 antibody-antigen complexes.; caveats: Author-reported numbers, source checked but not independently reproduced.; Many of these metrics are better when lower, including scRMSD, perplexity and binding energy. The direction comes from the arrow in the paper's own header.; Rows such as Native PDBs and RAbD are the natural reference the authors include for scale, not a competing method.; review: method: automated_source_review; date: 2026-09-18

Related records

Suggest a correction