# Artist Verification on 91-artist corpus (25 random artist-disjoint splits)

Source: [Artist Verification on 91-artist corpus (25 random artist-disjoint splits)](<https://www.sota2.com/research/sota/artist-verification-on-91-artist-corpus-25-random-artist-disjoint-splits>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-12T10:31:14.815Z

Evaluation of Artist Verification performance on the 91-artist corpus, utilizing 25 random artist-disjoint splits, measured using AUC and EER metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Artist Verification |
| Dataset (including any stated split) | 91-artist corpus (25 random artist-disjoint splits) |
| Metric | Mean AUC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Mean AUC](<https://www.sota2.com/research/sota/artist-verification-on-91-artist-corpus-25-random-artist-disjoint-splits.md?metric=Mean%20AUC>): Higher is better; unit: PERCENT.

- [Std Dev AUC](<https://www.sota2.com/research/sota/artist-verification-on-91-artist-corpus-25-random-artist-disjoint-splits.md?metric=Std%20Dev%20AUC>): Lower is better; unit: SCALAR.

- [Min AUC (across splits)](<https://www.sota2.com/research/sota/artist-verification-on-91-artist-corpus-25-random-artist-disjoint-splits.md?metric=Min%20AUC%20(across%20splits)>): Higher is better; unit: PERCENT.

- [Mean EER](<https://www.sota2.com/research/sota/artist-verification-on-91-artist-corpus-25-random-artist-disjoint-splits.md?metric=Mean%20EER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Mean AUC | Result date | Report paper |
| --- | --- | --- | --- |
| Pair-logreg | 91.7 | Not recorded | 6a02b410dbc836b87d8246ae |
| Pair-logreg | 91.7 | Not recorded | 6a02b410dbc836b87d8246ae |
| CSLS | 90.5 | Not recorded | 6a02b410dbc836b87d8246ae |
| CSLS | 90 | Not recorded | 6a02b410dbc836b87d8246ae |
| Cosine | 89.5 | Not recorded | 6a02b410dbc836b87d8246ae |
| Cosine | 88.3 | Not recorded | 6a02b410dbc836b87d8246ae |

### Pair-logreg

Mean AUC: 91.7. Result ID: 6a0300ec47f34ce924e674e0.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

Recorded evaluation configuration: {"Input Variant":"vanilla CSD","Resolution":"224","Backbone":"CSD ViT-L/14","Protocol":"Supervised"}. This record does not assert independent reproduction.

### Pair-logreg

Mean AUC: 91.7. Result ID: 6a0300ec47f34ce924e674e1.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

Recorded evaluation configuration: {"Input Variant":"pos-interp 336","Resolution":"336","Backbone":"CSD ViT-L/14","Protocol":"Supervised"}. This record does not assert independent reproduction.

### CSLS

Mean AUC: 90.5. Result ID: 6a0300ec47f34ce924e674df.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

Recorded evaluation configuration: {"Input Variant":"pos-interp 336 (CSD+)","Resolution":"336","Backbone":"CSD ViT-L/14","Protocol":"Unsupervised"}. This record does not assert independent reproduction.

### CSLS

Mean AUC: 90. Result ID: 6a0300ec47f34ce924e674dd.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

Recorded evaluation configuration: {"Input Variant":"vanilla CSD","Resolution":"224","Backbone":"CSD ViT-L/14","Protocol":"Unsupervised"}. This record does not assert independent reproduction.

### Cosine

Mean AUC: 89.5. Result ID: 6a0300ec47f34ce924e674de.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

Recorded evaluation configuration: {"Input Variant":"pos-interp 336 (CSD+)","Resolution":"336","Backbone":"CSD ViT-L/14","Protocol":"Unsupervised"}. This record does not assert independent reproduction.

### Cosine

Mean AUC: 88.3. Result ID: 6a0300ec47f34ce924e674dc.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b410dbc836b87d8246ae.md>)

Recorded evaluation configuration: {"Input Variant":"vanilla CSD","Resolution":"224","Backbone":"CSD ViT-L/14","Protocol":"Unsupervised"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
