# MINERVA Checkpoints — MetaQA

These files contain the pretrained **MINERVA** checkpoints used for the corresponding experiments in [*Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation*](https://arxiv.org/abs/2609.14528).

Three independently trained runs are released, using seeds **0**, **42**, and **100**. Each seed is distributed as a self-contained ZIP archive containing the trained TensorFlow checkpoint together with the configuration and evaluation artifacts retained from that run.

- **THESEUS:** https://github.com/HalcyonSolutions/THESEUS
- **MINERVA implementation:** https://github.com/HalcyonSolutions/MINERVA


## Release summary

| Field | Value |
| --- | --- |
| Model | MINERVA |
| Dataset | MetaQA |
| QA setting | Multi-answer |
| Question hops | 1–3 |
| Reasoning horizon | 3 hops |
| Seeds | 0, 42, 100 |
| Dataset page | https://storage.googleapis.com/halcyon_data/multihop_ds/datasets/MetaQA/index.html |

## Downloads

| Seed | Archive |
| ---: | --- |
| 0 | [seed0.zip](https://storage.googleapis.com/halcyon_data/multihop_ds/conferences/all/minerva/metaqa/seed0.zip) |
| 42 | [seed42.zip](https://storage.googleapis.com/halcyon_data/multihop_ds/conferences/all/minerva/metaqa/seed42.zip) |
| 100 | [seed100.zip](https://storage.googleapis.com/halcyon_data/multihop_ds/conferences/all/minerva/metaqa/seed100.zip) |

## Archive layout

```text
qa_nhop_reason_3hop_seed<seed>/
├── model/
│   ├── checkpoint
│   ├── model.ckpt.data-00000-of-00001
│   ├── model.ckpt.index
│   └── model.ckpt.meta
├── config.json
├── scores.txt
├── test_beam/
│   └── test_paths.txt
└── LICENSE
```

## Archive contents

Each `seed<seed>.zip` contains one experiment directory. The `model/` directory is the loadable TensorFlow checkpoint; the remaining files document the original run and its evaluations.

| Artifact | Description |
| --- | --- |
| `model/checkpoint` | TensorFlow checkpoint-state file. |
| `model/model.ckpt.data-00000-of-00001` | TensorFlow checkpoint parameter data. |
| `model/model.ckpt.index` | TensorFlow checkpoint index. |
| `model/model.ckpt.meta` | TensorFlow graph metadata. |
| `config.json` | Effective configuration saved during the original run for reproducibility. It records the resolved run settings and original paths, but is **not** intended to be used directly as an evaluation configuration. |
| `scores.txt` | Score history/evaluation output retained from the original run. |
| `test_beam/test_paths.txt` | Human-readable per-question evaluation output for the top-ranked beam-search trajectory. |

The four files under `model/` belong to the same TensorFlow checkpoint and should be kept together.


### Evaluation notes

- No `scores_rephrasing.txt` is provided for MetaQA.
- No separate `scores_updated.txt` is required for this release.
- The navigation-ready MetaQA release does **not** provide annotated reference reasoning paths. Consequently, evaluation fields that require reference entity-level paths are not available in the same way as for Kinship or MQuAKE-ST.

## Loading a checkpoint

Extract one seed archive, then point a compatible MINERVA evaluation configuration to the checkpoint prefix:

```yaml
load_model: true
model_load_dir: /path/to/extracted/experiment/model/model.ckpt
```

Use the matching [MINERVA implementation](https://github.com/HalcyonSolutions/MINERVA) and the corresponding THESEUS-formatted dataset. `config.json` is provided as a record of the original run; paths stored in it may refer to the training environment in which the checkpoint was produced.

## Integrity

SHA-256 hashes for the three seed archives are provided in `SHA256SUMS.txt`. After downloading the files, they can be checked with:

```bash
sha256sum -c SHA256SUMS.txt
```


## Dataset attribution

These checkpoints were trained and evaluated on the navigation-ready encoding of **MetaQA** distributed through THESEUS. MetaQA itself was introduced by Yuyu Zhang, Hanjun Dai, Zornitsa Kozareva, Alexander J. Smola, and Le Song; the THESEUS version only repackages/encodes the original benchmark for the common navigation interface.

See the [MetaQA dataset page](https://storage.googleapis.com/halcyon_data/multihop_ds/datasets/MetaQA/index.html) and the [original MetaQA repository](https://github.com/yuyuz/MetaQA) for dataset details and licensing.

## Citation

If you use these checkpoints, please cite MINERVA and THESEUS. When using MetaQA, also cite the original MetaQA paper.

### MINERVA

```bibtex
@inproceedings{minerva,
  title     = {Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning},
  author    = {Das, Rajarshi and Dhuliawala, Shehzaad and Zaheer, Manzil and Vilnis, Luke and Durugkar, Ishan and Krishnamurthy, Akshay and Smola, Alex and McCallum, Andrew},
  booktitle = {International Conference on Learning Representations},
  year      = {2018}
}
```

### THESEUS

```bibtex
@article{hernandez2026theseus,
  author  = {Hernandez, Eduin E. and Garcia, Luis F. and Askar, Nurassyl and Diaz, Sergio A. and Rini, Stefano},
  title   = {Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation},
  journal = {arXiv preprint arXiv:2609.14528},
  year    = {2026}
}
```


### MetaQA

```bibtex
@inproceedings{zhang2017variational,
  title     = {Variational Reasoning for Question Answering with Knowledge Graph},
  author    = {Zhang, Yuyu and Dai, Hanjun and Kozareva, Zornitsa and Smola, Alexander J. and Song, Le},
  booktitle = {AAAI},
  year      = {2018}
}
```

## License

The pretrained MINERVA checkpoints and associated experiment artifacts in this release are distributed under the **Apache License 2.0**, consistent with the MINERVA implementation used to produce them.

A copy of the Apache 2.0 license is provided alongside the downloads and is also included inside each seed archive. See [`LICENSE`](./LICENSE) for the complete terms.

The datasets used to train and evaluate these checkpoints are distributed separately and remain subject to their respective licenses and attribution requirements.