---
language: ["en"]
library_name: "pytorch"
pipeline_tag: "text-classification"
base_model: "google/embeddinggemma-300m"
tags: ["multi-label-classification", "hierarchical-classification", "physics", "physh", "transfer-learning"]
metrics: ["f1"]
---



# PhySH Topic Supervised Classifier

A hierarchical multi-label classifier that assigns APS Physics Subject Headings (PhySH) to physics papers using their titles and abstracts.

## Model description

The model uses frozen [`google/embeddinggemma-300m`](https://huggingface.co/google/embeddinggemma-300m) representations with a two-stage conditioned classifier:

1. **Discipline classifier:** Predicts 18 broad APS disciplines.
2. **Concept classifier:** Predicts 186 research-area concepts, conditioned on the discipline probabilities produced by the first stage.

This classifier-chain design incorporates the hierarchy between broad disciplines and more specific research concepts.

## Architecture

The input is formatted as:

```text
{title} [SEP] {abstract}
```

EmbeddingGemma produces a 768-dimensional, L2-normalized representation. The encoder remains frozen during training.

### Frozen encoder

```text
google/embeddinggemma-300m → 768 dimensions
```

### Discipline head

```text
768 → 1024 → 512 → 18
```

### Concept head

```text
[768-dimensional embedding; 18 discipline probabilities]
786 → 1024 → 512 → 186
```

Both classification heads use ReLU activations and dropout with `p = 0.3`. Their outputs are independent sigmoid scores rather than a softmax distribution, allowing multiple labels to be assigned to each paper.

The two MLP heads contain approximately 2.75 million trainable parameters in total.

## Training

* **Objective:** Multi-label binary cross-entropy with logits
* **Optimizer:** Adam
* **Encoder:** Frozen
* **Hardware:** Apple Metal Performance Shaders (MPS)
* **Optional objective:** Focal loss
* **Training run:** `20260130_140842`

## Evaluation

| Prediction level  | Micro-F1 | Macro-F1 |
| ----------------- | -------: | -------: |
| Disciplines       |    0.799 |    0.683 |
| Research concepts |    0.641 |    0.423 |

The model predicts approximately 2.12 labels per paper, compared with approximately 2.15 labels per paper in the evaluation data.

> **Evaluation-data note:** Add the dataset source, number of examples, train/validation/test split sizes, and split methodology before treating these results as independently reproducible.

## Inference

Inference applies a configurable threshold to each sigmoid score. If no score passes the threshold, the highest-scoring label is returned as a top-1 fallback.

Thresholds should be selected according to the intended precision–recall tradeoff:

* **Interactive demo threshold:** `0.35`
* **Batch-labeling threshold:** `0.85`

Try the model in the interactive demo.

## Intended uses

This model is intended for:

* Organizing and exploring physics literature
* Suggesting PhySH labels for paper titles and abstracts
* Supporting search, recommendation, and bibliometric workflows
* Research on hierarchical multi-label classification

Predictions should be treated as label suggestions rather than authoritative APS classifications.

## Limitations

* Performance is lower on rare concepts, as reflected by the gap between micro-F1 and macro-F1.
* Predictions depend on the information available in the title and abstract.
* The model may not generalize to fields, terminology, or document types that differ substantially from its training data.
* Output quality and label frequency depend on the selected inference threshold.
* The frozen encoder limits task-specific representation learning.

## Citation

If you use this model, please cite the model repository:

```bibtex
@misc{physh_topic_supervised_classifier,
  author    = {Luke F},
  title     = {PhySH Topic Supervised Classifier},
  year      = {2026},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/LukeFP/physh_topic_supervised_classifier}
}
```