# Training Data Provenance Verification on ImageNet-100

Source: [Training Data Provenance Verification on ImageNet-100](<https://www.sota2.com/research/sota/training-data-provenance-verification-on-imagenet-100>)

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

Data updated: 2026-02-26T05:30:23.429Z

Evaluation of model performance for Training Data Provenance Verification on the ImageNet-100 dataset, reporting metrics such as Average Accuracy, F1-score, and AUC.

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 | Training Data Provenance Verification |
| Dataset (including any stated split) | ImageNet-100 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/training-data-provenance-verification-on-imagenet-100.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/training-data-provenance-verification-on-imagenet-100.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/training-data-provenance-verification-on-imagenet-100.md?metric=AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TrainProVe | 78.7 | Not recorded | 68fa77671e209131cea730fb |
| TrainProVe | 78.6 | Not recorded | 68fa77671e209131cea730fb |
| TrainProVe | 78 | Not recorded | 68fa77671e209131cea730fb |
| TrainProVe | 77.1 | Not recorded | 68fa77671e209131cea730fb |
| Han et al.'s Work | 67.1 | Not recorded | 68fa77671e209131cea730fb |
| TrainProVe-Sim | 55.5 | Not recorded | 68fa77671e209131cea730fb |
| Random | 50 | Not recorded | 68fa77671e209131cea730fb |
| Han et al.'s Work | 48 | Not recorded | 68fa77671e209131cea730fb |
| TrainProVe-Ent | 35.6 | Not recorded | 68fa77671e209131cea730fb |

### TrainProVe

Accuracy: 78.7. Result ID: 69949d523a6c3148491e69b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Implementation](<https://github.com/xieyc99/TrainProVe>)

Recorded evaluation configuration: {"Backbone":"Swin-B"}. This record does not assert independent reproduction.

### TrainProVe

Accuracy: 78.6. Result ID: 69949d523a6c3148491e69ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Implementation](<https://github.com/xieyc99/TrainProVe>)

Recorded evaluation configuration: {"Backbone":"ResNet18"}. This record does not assert independent reproduction.

### TrainProVe

Accuracy: 78. Result ID: 69949d523a6c3148491e69b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Implementation](<https://github.com/xieyc99/TrainProVe>)

Recorded evaluation configuration: {"Tt":"33.6h","Tg":"0.1h","Tv":"1.4h","Total":"35.1h"}. This record does not assert independent reproduction.

### TrainProVe

Accuracy: 77.1. Result ID: 69949d523a6c3148491e69af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Implementation](<https://github.com/xieyc99/TrainProVe>)

Recorded evaluation configuration: {"Backbone":"ConvNeXt-B"}. This record does not assert independent reproduction.

### Han et al.'s Work

Accuracy: 67.1. Result ID: 69949d523a6c3148491e69ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TrainProVe-Sim

Accuracy: 55.5. Result ID: 69949d523a6c3148491e69ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Implementation](<https://github.com/xieyc99/TrainProVe>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Random

Accuracy: 50. Result ID: 69949d523a6c3148491e69aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Han et al.'s Work

Accuracy: 48. Result ID: 69949d523a6c3148491e69b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

Recorded evaluation configuration: {"Tt":"137.7h","Tg":"8.0h","Tv":"1.2h","Total":"146.9h"}. This record does not assert independent reproduction.

### TrainProVe-Ent

Accuracy: 35.6. Result ID: 69949d523a6c3148491e69ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77671e209131cea730fb.md>)

[Implementation](<https://github.com/xieyc99/TrainProVe>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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