# Generative Modeling on Crosshatch 20% missing-entry rate

Source: [Generative Modeling on Crosshatch 20% missing-entry rate](<https://www.sota2.com/research/sota/generative-modeling-on-crosshatch-20-percent-missing-entry-rate>)

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

Data updated: 2026-04-29T07:18:28.446Z

Evaluation of generative models on the Crosshatch dataset subset characterized by a 20% missing entry rate, assessed using Absolute Entry Mean Difference and Standard Deviation Difference 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 | Generative Modeling |
| Dataset (including any stated split) | Crosshatch 20% missing-entry rate |
| Metric | Mean Entry Difference (x10^-2) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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 Entry Difference (x10^-2)](<https://www.sota2.com/research/sota/generative-modeling-on-crosshatch-20-percent-missing-entry-rate.md?metric=Mean%20Entry%20Difference%20(x10%5E-2)>): Lower is better; unit: SCALAR.

- [Std Dev Entry Difference (x10^-2)](<https://www.sota2.com/research/sota/generative-modeling-on-crosshatch-20-percent-missing-entry-rate.md?metric=Std%20Dev%20Entry%20Difference%20(x10%5E-2)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Mean Entry Difference (x10^-2) | Result date | Report paper |
| --- | --- | --- | --- |
| CoreFlow | 0.0107 | Not recorded | 69f1907455a3c32af89fb990 |
| SMG-Core | 0.0728 | Not recorded | 69f1907455a3c32af89fb990 |
| CSDM | 0.1946 | Not recorded | 69f1907455a3c32af89fb990 |
| CSDM | 0.309 | Not recorded | 69f1907455a3c32af89fb990 |
| CSDM | 0.638 | Not recorded | 69f1907455a3c32af89fb990 |
| CoreFlow | 0.85 | Not recorded | 69f1907455a3c32af89fb990 |
| SMG-Core | 14.3 | Not recorded | 69f1907455a3c32af89fb990 |
| CSDM | 15.7 | Not recorded | 69f1907455a3c32af89fb990 |
| CSDM | 20.9 | Not recorded | 69f1907455a3c32af89fb990 |
| CSDM | 32.7 | Not recorded | 69f1907455a3c32af89fb990 |

### CoreFlow

Mean Entry Difference (x10^-2): 0.0107. Result ID: 69f1b0b247f34ce924d7bb0b.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"1.44%"}. This record does not assert independent reproduction.

### SMG-Core

Mean Entry Difference (x10^-2): 0.0728. Result ID: 69f1b0b247f34ce924d7bb0a.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7e541e209131cea96068.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"1.44%"}. This record does not assert independent reproduction.

### CSDM

Mean Entry Difference (x10^-2): 0.1946. Result ID: 69f1b0b247f34ce924d7bb09.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"64%"}. This record does not assert independent reproduction.

### CSDM

Mean Entry Difference (x10^-2): 0.309. Result ID: 69f1b0b247f34ce924d7bb08.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"36%"}. This record does not assert independent reproduction.

### CSDM

Mean Entry Difference (x10^-2): 0.638. Result ID: 69f1b0b247f34ce924d7bb07.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"1.44%"}. This record does not assert independent reproduction.

### CoreFlow

Mean Entry Difference (x10^-2): 0.85. Result ID: 69f1b0b147f34ce924d7ba15.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"1.44%"}. This record does not assert independent reproduction.

### SMG-Core

Mean Entry Difference (x10^-2): 14.3. Result ID: 69f1b0b147f34ce924d7ba14.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7e541e209131cea96068.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"1.44%"}. This record does not assert independent reproduction.

### CSDM

Mean Entry Difference (x10^-2): 15.7. Result ID: 69f1b0b147f34ce924d7ba13.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"64%"}. This record does not assert independent reproduction.

### CSDM

Mean Entry Difference (x10^-2): 20.9. Result ID: 69f1b0b147f34ce924d7ba12.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"36%"}. This record does not assert independent reproduction.

### CSDM

Mean Entry Difference (x10^-2): 32.7. Result ID: 69f1b0b147f34ce924d7ba11.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907455a3c32af89fb990.md>)

Recorded evaluation configuration: {"learned-dimension ratio (ρ)":"1.44%"}. This record does not assert independent reproduction.

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