# Latent Structural Repair on Objaverse-LVIS Hard (source)

Source: [Latent Structural Repair on Objaverse-LVIS Hard (source)](<https://www.sota2.com/research/sota/latent-structural-repair-on-objaverse-lvis-hard-source>)

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

Data updated: 2026-05-12T15:43:18.981Z

Evaluation of Latent Structural Repair performance on the hard subset of the Objaverse-LVIS dataset, using structural validity and parent relationship 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 | Latent Structural Repair |
| Dataset (including any stated split) | Objaverse-LVIS Hard (source) |
| Metric | Validity@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Validity@1](<https://www.sota2.com/research/sota/latent-structural-repair-on-objaverse-lvis-hard-source.md?metric=Validity%401>): Higher is better; unit: PERCENT.

- [Parent Match@1](<https://www.sota2.com/research/sota/latent-structural-repair-on-objaverse-lvis-hard-source.md?metric=Parent%20Match%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Validity@1 | Result date | Report paper |
| --- | --- | --- | --- |
| C2LT-3D | 66.69 | Not recorded | 6a02b47bdbc836b87d824c2a |
| Dense Support Verifier | 24.56 | Not recorded | 6a02b47bdbc836b87d824c2a |
| C2LT-3D | 23.97 | Not recorded | 6a02b47bdbc836b87d824c2a |
| Geometric NN | 12.21 | Not recorded | 6a02b47bdbc836b87d824c2a |
| C2LT-3D | 7.65 | Not recorded | 6a02b47bdbc836b87d824c2a |

### C2LT-3D

Validity@1: 66.69. Result ID: 6a034a8547f34ce924e88565.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

Recorded evaluation configuration: {"variant":"Learned Seam Prior"}. This record does not assert independent reproduction.

### Dense Support Verifier

Validity@1: 24.56. Result ID: 6a034a8547f34ce924e88562.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

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

### C2LT-3D

Validity@1: 23.97. Result ID: 6a034a8547f34ce924e88563.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

Recorded evaluation configuration: {"variant":"Seam Head Only"}. This record does not assert independent reproduction.

### Geometric NN

Validity@1: 12.21. Result ID: 6a034a8547f34ce924e88561.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

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

### C2LT-3D

Validity@1: 7.65. Result ID: 6a034a8547f34ce924e88564.

[Reporting paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a02b47bdbc836b87d824c2a.md>)

Recorded evaluation configuration: {"variant":"w/o Partition"}. This record does not assert independent reproduction.

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