# Hierarchical Text Classification on NYTimes (test)

Source: [Hierarchical Text Classification on NYTimes (test)](<https://www.sota2.com/research/sota/hierarchical-text-classification-on-nytimes-test>)

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

Data updated: 2026-02-26T05:52:47.330Z

Evaluation of Hierarchical Text Classification performance on the test split of the NYTimes dataset, measured using Micro-F1 and Macro-F1 scores.

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 | Hierarchical Text Classification |
| Dataset (including any stated split) | NYTimes (test) |
| Metric | Micro-F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Micro-F1](<https://www.sota2.com/research/sota/hierarchical-text-classification-on-nytimes-test.md?metric=Micro-F1>): Higher is better; unit: PERCENT.

- [Macro-F1](<https://www.sota2.com/research/sota/hierarchical-text-classification-on-nytimes-test.md?metric=Macro-F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Micro-F1 | Result date | Report paper |
| --- | --- | --- | --- |
| HILL | 80.47 | Not recorded | 68fa5b961e209131ce9c9c11 |
| HiTIN | 79.65 | Not recorded | 68fa6fbc1e209131cea471d3 |
| HGCLR | 78.86 | Not recorded | 68fa5b961e209131ce9c9c11 |
| HGCLR | 78.86 | Not recorded | 68fa6fbc1e209131cea471d3 |
| BERT+HTCInfoMax | 78.75 | Not recorded | 68fa5b961e209131ce9c9c11 |
| HTCInfoMax | 78.75 | Not recorded | 68fa6fbc1e209131cea471d3 |
| BERT+HiAGM | 78.64 | Not recorded | 68fa5b961e209131ce9c9c11 |
| HiAGM | 78.64 | Not recorded | 68fa6fbc1e209131cea471d3 |
| BERT | 78.24 | Not recorded | 68fa5b961e209131ce9c9c11 |
| BERT | 78.24 | Not recorded | 68fa6fbc1e209131cea471d3 |
| HIDDEN\_jnt | 77 | Not recorded | 68fa690f1e209131cea1fdb5 |
| HIDDEN\_flt | 76.4 | Not recorded | 68fa690f1e209131cea1fdb5 |
| HiAGM | 74.97 | Not recorded | 68fa5b961e209131ce9c9c11 |
| HIDDEN\_cas | 74.6 | Not recorded | 68fa690f1e209131cea1fdb5 |
| TextRCNN | 70.83 | Not recorded | 68fa5b961e209131ce9c9c11 |
| TextCNN-Flat | 69.5 | Not recorded | 68fa690f1e209131cea1fdb5 |

### HILL

Micro-F1: 80.47. Result ID: 698bb1dc7a967eddb770a9b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

[Implementation](<https://github.com/Rooooyy/HILL>)

Recorded evaluation configuration: {"Text Encoder":"BERT","Learning Paradigm":"Contrastive"}. This record does not assert independent reproduction.

### HiTIN

Micro-F1: 79.65. Result ID: 6990e9183a6c31484904384e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea471d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea471d3.md>)

[Implementation](<https://github.com/Rooooyy/HiTIN>)

Recorded evaluation configuration: {"Text Encoder":"BERT"}. This record does not assert independent reproduction.

### HGCLR

Micro-F1: 78.86. Result ID: 698bb1dc7a967eddb770a9b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c05.md>)

Recorded evaluation configuration: {"Text Encoder":"BERT","Learning Paradigm":"Contrastive"}. This record does not assert independent reproduction.

### HGCLR

Micro-F1: 78.86. Result ID: 6990e9183a6c31484904384d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea471d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c05.md>)

Recorded evaluation configuration: {"Text Encoder":"BERT"}. This record does not assert independent reproduction.

### BERT+HTCInfoMax

Micro-F1: 78.75. Result ID: 698bb1dc7a967eddb770a9b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c05.md>)

Recorded evaluation configuration: {"Text Encoder":"BERT","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### HTCInfoMax

Micro-F1: 78.75. Result ID: 6990e9183a6c31484904384c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea471d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69bb1e209131cea23d6f.md>)

Recorded evaluation configuration: {"Text Encoder":"BERT"}. This record does not assert independent reproduction.

### BERT+HiAGM

Micro-F1: 78.64. Result ID: 698bb1dc7a967eddb770a9b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c05.md>)

Recorded evaluation configuration: {"Text Encoder":"BERT","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### HiAGM

Micro-F1: 78.64. Result ID: 6990e9183a6c31484904384b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea471d3.md>)

Recorded evaluation configuration: {"Text Encoder":"BERT"}. This record does not assert independent reproduction.

### BERT

Micro-F1: 78.24. Result ID: 698bb1dc7a967eddb770a9b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c05.md>)

Recorded evaluation configuration: {"Text Encoder":"BERT","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### BERT

Micro-F1: 78.24. Result ID: 6990e9183a6c31484904384a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea471d3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Text Encoder":"BERT"}. This record does not assert independent reproduction.

### HIDDEN\_jnt

Micro-F1: 77. Result ID: 698d95708b517eb433228001.

[Reporting paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fdb5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fdb5.md>)

[Implementation](<https://github.com/soumyac1999/hyperbolic-label-emb-for-hmc>)

Recorded evaluation configuration: {"base\_model":"TextCNN","architecture":"joint"}. This record does not assert independent reproduction.

### HIDDEN\_flt

Micro-F1: 76.4. Result ID: 698d95708b517eb433227fff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fdb5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fdb5.md>)

[Implementation](<https://github.com/soumyac1999/hyperbolic-label-emb-for-hmc>)

Recorded evaluation configuration: {"base\_model":"TextCNN","architecture":"flat baseline"}. This record does not assert independent reproduction.

### HiAGM

Micro-F1: 74.97. Result ID: 698bb1dc7a967eddb770a9b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

Recorded evaluation configuration: {"Text Encoder":"TextRCNN","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### HIDDEN\_cas

Micro-F1: 74.6. Result ID: 698d95708b517eb433228000.

[Reporting paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fdb5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fdb5.md>)

[Implementation](<https://github.com/soumyac1999/hyperbolic-label-emb-for-hmc>)

Recorded evaluation configuration: {"base\_model":"TextCNN","architecture":"cascaded"}. This record does not assert independent reproduction.

### TextRCNN

Micro-F1: 70.83. Result ID: 698bb1dc7a967eddb770a9b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa5b961e209131ce9c9c11.md>)

Recorded evaluation configuration: {"Text Encoder":"TextRCNN","Learning Paradigm":"Supervised"}. This record does not assert independent reproduction.

### TextCNN-Flat

Micro-F1: 69.5. Result ID: 698d95708b517eb433227ffe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa690f1e209131cea1fdb5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67cb1e209131cea18703.md>)

[Implementation](<https://github.com/morningmoni/HiLAP>)

Recorded evaluation configuration: {"base\_model":"TextCNN","architecture":"flat"}. This record does not assert independent reproduction.

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