# Argument validity and novelty prediction on VALNOV (test)

Source: [Argument validity and novelty prediction on VALNOV (test)](<https://www.sota2.com/research/sota/argument-validity-and-novelty-prediction-on-valnov-test>)

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

Data updated: 2026-02-26T05:47:39.979Z

Evaluation of model performance on predicting argument validity and novelty using the VALNOV test set. Metrics include joint F1, Validity F1, and Novelty F1.

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 | Argument validity and novelty prediction |
| Dataset (including any stated split) | VALNOV (test) |
| Metric | Joint F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Joint F1](<https://www.sota2.com/research/sota/argument-validity-and-novelty-prediction-on-valnov-test.md?metric=Joint%20F1>): Higher is better; unit: PERCENT.

- [Validity F1](<https://www.sota2.com/research/sota/argument-validity-and-novelty-prediction-on-valnov-test.md?metric=Validity%20F1>): Higher is better; unit: PERCENT.

- [Novelty F1](<https://www.sota2.com/research/sota/argument-validity-and-novelty-prediction-on-valnov-test.md?metric=Novelty%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Joint F1 | Result date | Report paper |
| --- | --- | --- | --- |
| ST-1st (GPT-3) | 45.16 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | 43.91 | Not recorded | 68fa6f581e209131cea4521e |
| ST-2nd (w/ KG) | 43.27 | Not recorded | 68fa6f581e209131cea4521e |
| contrastive | 37.82 | Not recorded | 68fa6f581e209131cea4521e |
| T5 | 37.71 | Not recorded | 68fa6f581e209131cea4521e |
| max-margin | 36.22 | Not recorded | 68fa6f581e209131cea4521e |
| ST System Avg | 35.94 | Not recorded | 68fa6f581e209131cea4521e |
| ST Baseline | 23.9 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | -2.27 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | -3.25 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | -5.6 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | -6.51 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | -6.71 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | -11.65 | Not recorded | 68fa6f581e209131cea4521e |
| CCKG | -20.65 | Not recorded | 68fa6f581e209131cea4521e |

### ST-1st (GPT-3)

Joint F1: 45.16. Result ID: 6990a9a03a6c314849023eb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d931e209131cea3ac1b.md>)

Recorded evaluation configuration: {"Category":"Shared Task (ST)"}. This record does not assert independent reproduction.

### CCKG

Joint F1: 43.91. Result ID: 6990a9a03a6c314849023eb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Full System":true}. This record does not assert independent reproduction.

### ST-2nd (w/ KG)

Joint F1: 43.27. Result ID: 6990a9a03a6c314849023eb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

Recorded evaluation configuration: {"Category":"Shared Task (ST)"}. This record does not assert independent reproduction.

### contrastive

Joint F1: 37.82. Result ID: 6990a9a03a6c314849023eb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c441e209131cea331d0.md>)

[Implementation](<https://github.com/swarnaHub/ExplagraphGen>)

Recorded evaluation configuration: {"Category":"EG w/ Ours (ExplaGraphs)"}. This record does not assert independent reproduction.

### T5

Joint F1: 37.71. Result ID: 6990a9a03a6c314849023eb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c441e209131cea331d0.md>)

[Implementation](<https://github.com/swarnaHub/ExplagraphGen>)

Recorded evaluation configuration: {"Category":"EG w/ Ours (ExplaGraphs)"}. This record does not assert independent reproduction.

### max-margin

Joint F1: 36.22. Result ID: 6990a9a03a6c314849023eb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c441e209131cea331d0.md>)

[Implementation](<https://github.com/swarnaHub/ExplagraphGen>)

Recorded evaluation configuration: {"Category":"EG w/ Ours (ExplaGraphs)"}. This record does not assert independent reproduction.

### ST System Avg

Joint F1: 35.94. Result ID: 6990a9a03a6c314849023eb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

Recorded evaluation configuration: {"Category":"Shared Task (ST)"}. This record does not assert independent reproduction.

### ST Baseline

Joint F1: 23.9. Result ID: 6990a9a03a6c314849023eb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

Recorded evaluation configuration: {"Category":"Shared Task (ST)"}. This record does not assert independent reproduction.

### CCKG

Joint F1: -2.27. Result ID: 6990a9a03a6c314849023ec0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Ablation":"w/o PC-distance feats.","Type":"Relative to CCKG"}. This record does not assert independent reproduction.

### CCKG

Joint F1: -3.25. Result ID: 6990a9a03a6c314849023ebd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Ablation":"w/o EWA","Type":"Relative to CCKG"}. This record does not assert independent reproduction.

### CCKG

Joint F1: -5.6. Result ID: 6990a9a03a6c314849023ebf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Ablation":"w/o connectivity feats.","Type":"Relative to CCKG"}. This record does not assert independent reproduction.

### CCKG

Joint F1: -6.51. Result ID: 6990a9a03a6c314849023ebc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Ablation":"w/o EWO","Type":"Relative to CCKG"}. This record does not assert independent reproduction.

### CCKG

Joint F1: -6.71. Result ID: 6990a9a03a6c314849023ebe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Ablation":"string matching","Type":"Relative to CCKG"}. This record does not assert independent reproduction.

### CCKG

Joint F1: -11.65. Result ID: 6990a9a03a6c314849023eba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Ablation":"w/o Graph feats.","Type":"Relative to CCKG"}. This record does not assert independent reproduction.

### CCKG

Joint F1: -20.65. Result ID: 6990a9a03a6c314849023ebb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f581e209131cea4521e.md>)

[Implementation](<https://github.com/Heidelberg-NLP/CCKG>)

Recorded evaluation configuration: {"Ablation":"w/o Text feats.","Type":"Relative to CCKG"}. This record does not assert independent reproduction.

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