BEELINE 2020 Figure 4 · VSC · {}
Source-specific evaluation. Input conditions: {}. No equivalence to other releases, protocols or model families is inferred.
Published comparisons
Each figure keeps its source, protocol, dataset and metric together. Results from different protocols are shown separately, without a pooled ranking.
BEELINE 2020 Figure 4 · VSC · {}: AUPRC Ratio
AUPRC Ratio (ratio) · Higher values are better for this metric.
Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.
- PIDC · Configuration · Author-reported evaluation2.723414782
- GENIE3 · Configuration · Author-reported evaluation2.756376658
- GRNBOOST2 · Configuration · Author-reported evaluation2.681333463
- PPCOR · Configuration · Author-reported evaluation2.142671976
- SCODE · Configuration · Author-reported evaluation1.340561819
- GRISLI · Configuration · Author-reported evaluation1.22323479
- SINGE · Configuration · Author-reported evaluation1.538039889
- SCNS · Configuration · Author-reported evaluation1.662311252
- LEAP · Configuration · Author-reported evaluation0.985424483
- SINCERITIES · Configuration · Author-reported evaluation1.040102538
- GRNVBEM · Configuration · Author-reported evaluation0.682233423
- SCRIBE · Configuration · Author-reported evaluation0.872725845
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.
BEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 3, column 3 through Figure 4 source CSV row 14, column 3Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| PIDC · Configuration | 2.723414782 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 3, column 3 |
| GENIE3 · Configuration | 2.756376658 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 4, column 3 |
| GRNBOOST2 · Configuration | 2.681333463 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 5, column 3 |
| PPCOR · Configuration | 2.142671976 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 6, column 3 |
| SCODE · Configuration | 1.340561819 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 7, column 3 |
| GRISLI · Configuration | 1.22323479 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 8, column 3 |
| SINGE · Configuration | 1.538039889 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 9, column 3 |
| SCNS · Configuration | 1.662311252 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 10, column 3 |
| LEAP · Configuration | 0.985424483 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 11, column 3 |
| SINCERITIES · Configuration | 1.040102538 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 12, column 3 |
| GRNVBEM · Configuration | 0.682233423 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 13, column 3 |
| SCRIBE · Configuration | 0.872725845 ratio | status: unreported | Author-reported evaluation · source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 14, column 3 |
Scope and limitations
- Source-specific evaluation. Input conditions: {}. No equivalence to other releases, protocols or model families is inferred.
- Across-dataset stability is median pairwise top-k edge-set Jaccard index (paper Online Methods), not Spearman correlation. Not an independent experimental run.
- Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.
Source transcription and grouping reviewed by automated source review on 2026-09-19. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-19-eb6149e5d766 · 12 evaluations · 36 metric rows. Different protocols are not a single leaderboard. Charts retain each source table’s protocol and dataset.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| PPCOR · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 2.142671976 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 6, column 3 Source checking is not independent reproduction. |
| 1.75 EPR Inhibition Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 6, column 15 Source checking is not independent reproduction. |
| 1.75 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 6, column 7 Source checking is not independent reproduction. |
| SCRIBE · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.872725845 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 14, column 3 Source checking is not independent reproduction. |
| 0.995555556 EPR Inhibition Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 14, column 15 Source checking is not independent reproduction. |
| 0.995555556 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 14, column 7 Source checking is not independent reproduction. |
| PIDC · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 2.723414782 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 3, column 3 Source checking is not independent reproduction. |
| 1.866666667 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 3, column 7 Source checking is not independent reproduction. |
| LEAP · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.622222222 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 11, column 7 Source checking is not independent reproduction. |
| 0.622222222 EPR Inhibition Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 11, column 15 Source checking is not independent reproduction. |
| 0.985424483 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 11, column 3 Source checking is not independent reproduction. |
| SINGE · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 1.515294118 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 9, column 7 Source checking is not independent reproduction. |
| 1.538039889 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 9, column 3 Source checking is not independent reproduction. |
| SCODE · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 1.244444444 EPR Inhibition Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 7, column 15 Source checking is not independent reproduction. |
| 1.340561819 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 7, column 3 Source checking is not independent reproduction. |
| 1.244444444 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 7, column 7 Source checking is not independent reproduction. |
| SCNS · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 1.602631579 EPR Inhibition Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 10, column 15 Source checking is not independent reproduction. |
| 1.662311252 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 10, column 3 Source checking is not independent reproduction. |
| 1.602631579 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 10, column 7 Source checking is not independent reproduction. |
| SINCERITIES · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.995555556 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 12, column 7 Source checking is not independent reproduction. |
| GRNBOOST2 · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 2.737777778 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 5, column 7 Source checking is not independent reproduction. |
| 2.681333463 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 5, column 3 Source checking is not independent reproduction. |
| GRNVBEM · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 0.510144928 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 13, column 7 Source checking is not independent reproduction. |
| GRISLI · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 1.132352941 Early Precision Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 8, column 7 Source checking is not independent reproduction. |
| GENIE3 · BEELINE 2020 Figure 4 · VSC BEELINE 2020 Figure 4 Author-reported evaluation · Evaluation metadata: discovered | ||
| 2.756376658 AUPRC Ratio Unit: ratio · Direction: higher Aggregation: Median across source-described simulation datasets | Uncertainty: status: unreported Scored: Not reported · Eligible: Not reported | source checkedBEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Figure 4 source CSV row 4, column 3 Source checking is not independent reproduction. |
Overview
Source-specific evaluation. Input conditions: {}. No equivalence to other releases, protocols or model families is inferred.
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
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- GRNBOOST2 · BEELINE 2020 Figure 4 · VSC
- SCODE · BEELINE 2020 Figure 4 · VSC
- SCNS · BEELINE 2020 Figure 4 · VSC
- GENIE3 · BEELINE 2020 Figure 4 · VSC
- SINGE · BEELINE 2020 Figure 4 · VSC
- SCRIBE · BEELINE 2020 Figure 4 · VSC
- PPCOR · BEELINE 2020 Figure 4 · VSC
- LEAP · BEELINE 2020 Figure 4 · VSC
- PIDC · BEELINE 2020 Figure 4 · VSC
- GRNVBEM · BEELINE 2020 Figure 4 · VSC
- SINCERITIES · BEELINE 2020 Figure 4 · VSC
- GRISLI · BEELINE 2020 Figure 4 · VSC
Run instructions
No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-beeline Individual claims | BEELINE: 10.1038/s41592-019-0690-6 source data published 2020 Figure 4 source CSV row 3, column 3 Version: 10.1038/s41592-019-0690-6 source data published 2020 | source checked ai assisted source review · 2026-09-19 Audit detailsField: Claim: acquired-membership-9672535af65f380ccb6d Source artifact SHA-256: Hash scope: Exact downloaded bytes, before optional gzip storage |
Sources and history
View linked audit checks and correction history
Release 2026-09-19-eb6149e5d766 · Record review: discovered
1 source records and release history
- BEELINE: 10.1038/s41592-019-0690-6 source data published 2020 · Original source · 10.1038/s41592-019-0690-6 source data published 2020
Technical metadata and extraction receipts
Stable ID: acquired-protocol-37b5599b7d976211e8c1
- source locator
- Figure 4 source CSV row 3, column 3
- procedure
- BEELINE 2020 Figure 4
- comparison panels
- id: acquired-figure-4c911179177b3f930ca7; title: BEELINE 2020 Figure 4 · VSC · {}: AUPRC Ratio; protocol id: acquired-protocol-37b5599b7d976211e8c1; dataset id: acquired-dataset-caf90389169ff966e573; metric: AUPRC Ratio; unit: ratio; direction: higher; result ids: acquired-result-106d808f878c9a389099; acquired-result-8a2ac5807029b84a841a; acquired-result-a0cdbbe216e099f97e41; acquired-result-003e3111e0ee184b0278; acquired-result-6045b8dbada97fdf8a49; acquired-result-fe34ae3b788355446354; acquired-result-a072d97fd39d92a5c1b6; acquired-result-8f6f4df3a724b3592c15; acquired-result-6e98f9cc01c62f6931dd; acquired-result-b71fb3d8c25f528e8edf; acquired-result-d4b9b92f718dfffc0491; acquired-result-05cbb9e70d2faefb9a0f; source ids: acquired-source-3156602fda847ae943b4; source locator: Figure 4 source CSV row 3, column 3 through Figure 4 source CSV row 14, column 3; context: Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.; caveats: Source-specific evaluation. Input conditions: {}. No equivalence to other releases, protocols or model families is inferred.; Across-dataset stability is median pairwise top-k edge-set Jaccard index (paper Online Methods), not Spearman correlation. Not an independent experimental run.; Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.; review: method: automated_source_review; date: 2026-09-19; id: acquired-figure-5f67927a90b42c4a0655; title: BEELINE 2020 Figure 4 · VSC · {}: Early Precision Ratio; protocol id: acquired-protocol-37b5599b7d976211e8c1; dataset id: acquired-dataset-caf90389169ff966e573; metric: Early Precision Ratio; unit: ratio; direction: higher; result ids: acquired-result-96ee3a58840801bf3cce; acquired-result-b2bee0a5c3514b0d3a93; acquired-result-4d0caa4e6c6070389642; acquired-result-4267fe4e96025c2a3d49; acquired-result-726a6303bf1c25985f4e; acquired-result-5998eb1494319836be37; acquired-result-128e30179771ad658852; acquired-result-aee122fcb28c463df792; acquired-result-11298d60753d3ec42174; acquired-result-3a13b312668b38debfd0; acquired-result-4e4feb75e1595ff0fd18; acquired-result-77856c03a93e0d20d602; source ids: acquired-source-3156602fda847ae943b4; source locator: Figure 4 source CSV row 3, column 7 through Figure 4 source CSV row 14, column 7; context: Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.; caveats: Source-specific evaluation. Input conditions: {}. No equivalence to other releases, protocols or model families is inferred.; Across-dataset stability is median pairwise top-k edge-set Jaccard index (paper Online Methods), not Spearman correlation. Not an independent experimental run.; Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.; review: method: automated_source_review; date: 2026-09-19; id: acquired-figure-fec9a408a698601daadf; title: BEELINE 2020 Figure 4 · VSC · {}: EPR Inhibition; protocol id: acquired-protocol-37b5599b7d976211e8c1; dataset id: acquired-dataset-caf90389169ff966e573; metric: EPR Inhibition; unit: ratio; direction: higher; result ids: acquired-result-e2aa1b477a35c39c370f; acquired-result-cc41411347bc1d8c0086; acquired-result-f5826c83df631798edc4; acquired-result-1752dfe79b27306ac1b4; acquired-result-38bff4df6e8222f70643; acquired-result-da5673f6370cb42be9bc; acquired-result-cd31b2b20f50bb7e8379; acquired-result-391300a132f1bf32cfbc; acquired-result-3b5947dbac5d391940a0; acquired-result-c6448a0a1dff87cb611f; acquired-result-d592010a91936b13a63a; acquired-result-1d63b0fa40c840610ae8; source ids: acquired-source-3156602fda847ae943b4; source locator: Figure 4 source CSV row 3, column 15 through Figure 4 source CSV row 14, column 15; context: Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.; caveats: Source-specific evaluation. Input conditions: {}. No equivalence to other releases, protocols or model families is inferred.; Across-dataset stability is median pairwise top-k edge-set Jaccard index (paper Online Methods), not Spearman correlation. Not an independent experimental run.; Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.; review: method: automated_source_review; date: 2026-09-19
- scope limitations
- Across-dataset stability is median pairwise top-k edge-set Jaccard index (paper Online Methods), not Spearman correlation. Not an independent experimental run.
Related records
- part of: BEELINE
- benchmark: GRNBOOST2 · BEELINE 2020 Figure 4 · VSC
- benchmark: SCODE · BEELINE 2020 Figure 4 · VSC
- benchmark: SCNS · BEELINE 2020 Figure 4 · VSC
- benchmark: GENIE3 · BEELINE 2020 Figure 4 · VSC
- benchmark: SINGE · BEELINE 2020 Figure 4 · VSC
- benchmark: SCRIBE · BEELINE 2020 Figure 4 · VSC
- benchmark: PPCOR · BEELINE 2020 Figure 4 · VSC
- benchmark: LEAP · BEELINE 2020 Figure 4 · VSC
- benchmark: PIDC · BEELINE 2020 Figure 4 · VSC
- benchmark: GRNVBEM · BEELINE 2020 Figure 4 · VSC
- benchmark: SINCERITIES · BEELINE 2020 Figure 4 · VSC
- benchmark: GRISLI · BEELINE 2020 Figure 4 · VSC
- subject: BEELINE 2020 Figure 4: benchmark membership