# S Licenses for existing assets

All assets are used in compliance with their respective licenses.

**Table 30.** Language models used as starting checkpoints for maze training or as LLM judges.

| Model | License | Citation | URL |
| --- | --- | --- | --- |
| Qwen3-4B-Instruct-2507 | Apache 2.0 | [30] | [huggingface.co/Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) |
| Qwen3-4B-Base | Apache 2.0 | [30] | [huggingface.co/Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) |
| Qwen3-8B | Apache 2.0 | [30] | [huggingface.co/Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) |
| GPT-OSS-20B | Apache 2.0<sup>$\dagger$</sup> | [22] | [huggingface.co/openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) |
| Gemini 3.1 Flash Lite Preview | Proprietary API | — | [ai.google.dev/gemini-api/terms](https://ai.google.dev/gemini-api/terms) |

**Table 31.** Datasets and benchmarks used for evaluation or for sentiment-vector extraction.

| Dataset | License | Citation | URL |
| --- | --- | --- | --- |
| SimpleQA-Verified | MIT | [10] | [huggingface.co/datasets/google/simpleqa-verified](https://huggingface.co/datasets/google/simpleqa-verified) |
| GSM8K | MIT | [7] | [github.com/openai/grade-school-math](https://github.com/openai/grade-school-math) |
| MMLU | MIT | [11] | [github.com/hendrycks/test](https://github.com/hendrycks/test) |
| OR-Bench | CC BY 4.0 | [8] | [huggingface.co/datasets/bench-llm/or-bench](https://huggingface.co/datasets/bench-llm/or-bench) |
| IMDB-CAD<sup>$\ddagger$</sup> | Apache 2.0 | [15] | [github.com/acmi-lab/counterfactually-augmented-data](https://github.com/acmi-lab/counterfactually-augmented-data) |

**Table 32.** Open-source code libraries and proprietary services used in training, inference, and evaluation.

| Asset | Version | License | Type | URL |
| --- | --- | --- | --- | --- |
| PyTorch | 2.5.1, 2.7 | BSD-style | library | [github.com/pytorch/pytorch](https://github.com/pytorch/pytorch) |
| HuggingFace Transformers | 4.50 | Apache 2.0 | library | [github.com/huggingface/transformers](https://github.com/huggingface/transformers) |
| vLLM | 0.6 | Apache 2.0 | library | [github.com/vllm-project/vllm](https://github.com/vllm-project/vllm) |
| PEFT | 0.13 | Apache 2.0 | library | [github.com/huggingface/peft](https://github.com/huggingface/peft) |
| Flash-Attention | 2 / 3 | BSD-3-Clause | library | [github.com/Dao-AILab/flash-attention](https://github.com/Dao-AILab/flash-attention) |
| Modal | — | Proprietary | service | [modal.com/legal/terms](https://modal.com/legal/terms) |
| Tinker API | — | Proprietary | service | [thinkingmachines.ai/legal/tos/](https://thinkingmachines.ai/legal/tos/) |
| Google Gemini API | — | Proprietary | service | [ai.google.dev/gemini-api/terms](https://ai.google.dev/gemini-api/terms) |