Metadata-Version: 2.4
Name: nvidia-scicode
Version: 25.8
Summary: SciCode - packaged by NVIDIA
Author: NVIDIA, SciCode
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright [yyyy] [name of copyright owner]
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
        
Project-URL: Original Project, https://github.com/scicode-bench/SciCode
Project-URL: Paper, https://arxiv.org/abs/2407.13168
Project-URL: Homepage, https://scicode-bench.github.io/
Keywords: nlp,code
Classifier: Development Status :: 5 - Production/Stable
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: h5py
Requires-Dist: tqdm
Requires-Dist: openai
Requires-Dist: google-generativeai
Requires-Dist: anthropic
Requires-Dist: config
Requires-Dist: rich
Requires-Dist: pytest
Requires-Dist: pytest-cov
Requires-Dist: litellm
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: matplotlib
Requires-Dist: sympy
Requires-Dist: omegaconf
Requires-Dist: nvidia-eval-commons
Dynamic: license-file

# SciCode 

[**Homepage**](https://scicode-bench.github.io/) | [**Paper**](https://arxiv.org/abs/2407.13168)

# NVIDIA Eval Factory

SciCode provides evaluation clients specifically built to evaluate model endpoints using our Standard API for scientific code generation tasks.

### Launching an evaluation for an LLM

#### Install the package

```bash
pip install nvidia-scicode
```

#### (Optional) Set a token to your API endpoint if it's protected

```bash
export MY_API_KEY="your_api_key_here"
export HF_TOKEN="your_huggingface_token_here"
```

#### List the available evaluations

```bash
eval-factory ls
```

Available tasks:
* scicode
* scicode_background
* aa_scicode

#### Run the evaluation of your choice

```bash
eval-factory run_eval \
    --eval_type aa_scicode \
    --model_id meta/llama-3.1-8b-instruct \
    --model_url https://integrate.api.nvidia.com/v1/chat/completions \
    --model_type chat \
    --api_key_name MY_API_KEY \
    --output_dir /workspace/results
```

#### Gather the results

```bash
cat /workspace/results/results.yml
```

### Command-Line Tool

Each package comes pre-installed with a set of command-line tools, designed to simplify the execution of evaluation tasks. Below are the available commands and their usage for the SciCode evaluations:

#### Commands

##### 1. List Evaluation Types

```bash
eval-factory ls
```

Displays the evaluation types available within the harness.

##### 2. Run an evaluation

The `eval-factory run_eval` command executes the evaluation process. Below are the flags and their descriptions:

**Required flags:**

- `--eval_type <string>`: The type of evaluation to perform (e.g., scicode, scicode_background, aa_scicode)
- `--model_id <string>`: The name or identifier of the model to evaluate.
- `--model_url <url>`: The API endpoint where the model is accessible.
- `--model_type <string>`: The type of the model to evaluate, currently either "chat", "completions", or "vlm".
- `--output_dir <directory>`: The directory to use as the working directory for the evaluation. The results, including the results.yml output file, will be saved here.

**Optional flags:**

- `--api_key_name <string>`: The name of the environment variable that stores the Bearer token for the API, if authentication is required.
- `--run_config <path>`: Specifies the path to a YAML file containing the evaluation definition.
- `--overrides <string>`: Override configuration parameters (e.g., 'config.params.limit_samples=10').

#### Examples

##### Basic SciCode Evaluation

```bash
eval-factory run_eval \
    --eval_type scicode \
    --model_id meta/llama-3.1-8b-instruct \
    --model_type chat \
    --model_url https://integrate.api.nvidia.com/v1/chat/completions \
    --output_dir ./evaluation_results
```

##### SciCode with Background Information

```bash
eval-factory run_eval \
    --eval_type scicode_background \
    --model_id meta/llama-3.1-8b-instruct \
    --model_type chat \
    --model_url https://integrate.api.nvidia.com/v1/chat/completions \
    --output_dir ./evaluation_results
```

##### AA-SciCode Evaluation (Artificial Analysis Style)

```bash
eval-factory run_eval \
    --eval_type aa_scicode \
    --model_id meta/llama-3.1-8b-instruct \
    --model_type chat \
    --model_url https://integrate.api.nvidia.com/v1/chat/completions \
    --output_dir ./evaluation_results
```

##### SciCode with Authentication

If the model API requires authentication, set the API key in an environment variable and reference it using the `--api_key_name` flag:

```bash
export MY_API_KEY="your_api_key_here"

eval-factory run_eval \
    --eval_type scicode \
    --model_id meta/llama-3.1-8b-instruct \
    --model_type chat \
    --model_url https://integrate.api.nvidia.com/v1/chat/completions \
    --api_key_name MY_API_KEY \
    --output_dir ./evaluation_results
```

##### Limited Sample Evaluation

```bash
eval-factory run_eval \
    --eval_type scicode \
    --model_id meta/llama-3.1-8b-instruct \
    --model_type chat \
    --model_url https://integrate.api.nvidia.com/v1/chat/completions \
    --output_dir ./evaluation_results \
    --overrides 'config.params.limit_samples=10'
```

### Configuring evaluations via YAML

Evaluations in SciCode are configured using YAML files that define the parameters and settings required for the evaluation process. These configuration files follow a standard API which ensures consistency across evaluations.

#### Example of a YAML config:

```yaml
config:
  type: scicode
  params:
    parallelism: 10
    limit_samples: 20
    max_new_tokens: 2048
    temperature: 0.0
    top_p: 0.00001
    request_timeout: 60
    max_retries: 2
    extra:
      n_samples: 1
      with_background: false
      include_dev: false
      eval_threads: null
target:
  api_endpoint:
    model_id: meta/llama-3.1-8b-instruct
    type: chat
    url: https://integrate.api.nvidia.com/v1/chat/completions
    api_key: MY_API_KEY
```

The priority of overrides is as follows:

1. command line arguments
2. user config (as seen above)
3. task defaults (defined per task type)
4. framework defaults

The `--dry_run` option allows you to print the final run configuration and command without executing the evaluation.

#### Example:

```bash
eval-factory run_eval \
    --eval_type scicode \
    --model_id meta/llama-3.1-8b-instruct \
    --model_type chat \
    --model_url https://integrate.api.nvidia.com/v1/chat/completions \
    --output_dir ./evaluation_results \
    --dry_run
```

### Evaluation Types

#### SciCode Tasks

- **scicode**: Standard SciCode evaluation without scientist-annotated background
- **scicode_background**: SciCode evaluation with scientist-annotated background in the prompts
- **aa_scicode**: Artificial Analysis style evaluation with background, dev set inclusion, and 3 samples per problem

### Task Descriptions

#### SciCode
- SciCode is a challenging benchmark designed to evaluate the capabilities of LLMs in generating code for solving realistic scientific research problems.
- This variant does not include scientist-annotated background in the prompts.

#### SciCode-Background
- SciCode is a challenging benchmark designed to evaluate the capabilities of LLMs in generating code for solving realistic scientific research problems.
- This variant includes scientist-annotated background in the prompts.

#### AA-SciCode
- SciCode is a challenging benchmark designed to evaluate the capabilities of LLMs in generating code for solving realistic scientific research problems.
- This variant mimics setup used by Artificial Analysis in their Intelligence Benchmark (v2).
- It includes scientist-annotated background in the prompts and uses all available problems for evaluation (including "dev" set).

### Performance Optimizations

SciCode includes several performance optimizations to ensure efficient evaluation:

- **Configurable retries**: Adjustable max_retries parameter for API request resilience
- **Parallel evaluation**: Configurable eval_threads for concurrent test execution
- **Flexible sampling**: Multiple samples per problem for robust evaluation
- **Timeout management**: Configurable request_timeout for API calls
- **Background inclusion**: Optional scientist-annotated background for enhanced context

### Output Format

The evaluation results are saved in the specified output directory with the following structure:

```
output_dir/
├── results.yml          # Main results file
├── generated_code/      # Generated code files
├── prompt/             # Prompt files
└── logs/               # Evaluation logs
```

The `results.yml` file contains the main evaluation metrics including:
- `problems_pass@1`: Problem-level pass@1 score
- `steps_pass@1`: Step-level pass@1 score
- `n_samples`: Number of samples used
- `num_correct`: Detailed correctness information per problem and step

---

This repo contains the evaluation code for the paper "[SciCode: A Research Coding Benchmark Curated by Scientists](https://arxiv.org/abs/2407.13168)"

## 🔔News

**[2025-02-01]: Results for DeepSeek-R1, DeepSeek-V3, and OpenAI o3-mini are added.**

**[2025-01-24]: SciCode has been integrated with [`inspect_ai`](https://inspect.ai-safety-institute.org.uk/) for easier and faster model evaluations.**

**[2024-11-04]: Leaderboard is on! Check [here](https://scicode-bench.github.io/leaderboard/). We have also added Claude Sonnet 3.5 (new) results.**

**[2024-10-01]: We have added OpenAI o1-mini and o1-preview results.**

**[2024-09-26]: SciCode is accepted at NeurIPS D&B Track 2024.**

**[2024-08-22]: The SciCode benchmark has been successfully integrated into [OpenCompass](https://github.com/open-compass/opencompass).**

**[2024-07-24]: We add the scientist-annotated background and support setup for w/ background evaluation.**

## Introduction
SciCode is a challenging benchmark designed to evaluate the capabilities of language models (LMs) in generating code for solving realistic scientific research problems. It has a diverse coverage of **16** subdomains from **6** domains: Physics, Math, Material Science, Biology, and Chemistry. Unlike previous benchmarks that consist of exam-like question-answer pairs, SciCode is converted from real research problems. SciCode problems naturally factorize into multiple subproblems, each involving knowledge recall, reasoning, and code synthesis. In total, SciCode contains **338** subproblems decomposed from **80** challenging main problems, and it offers optional descriptions specifying useful scientific background information and scientist-annotated gold-standard solutions and test cases for evaluation. OpenAI o1-preview, the best-performing model among those tested, can solve only **7.7%** of the problems in the most realistic setting. Broadly, SciCode demonstrates a realistic and scientists' everyday workflow of identifying critical science concepts and facts and then transforming them into computation and simulation code. We believe SciCode not only helps demonstrate contemporary LLMs' progress towards helpful assistant for scientists but also helps shed light on future building and evaluation of scientific AI.



## Dataset Creation
SciCode sources challenging and realistic research-level coding problems across 6 natural science disciplines, covering a total of 16 subfields. Scicode mainly focuses on 1. Numerical methods 2.Simulation of systems 3. Scientific calculation. These are the tasks we believe require intense scientific knowledge and reasoning to optimally test LM’s science capability.

## 🏆 Leaderboard

| Models                   | Main Problem Resolve Rate           | <span style="color:grey">Subproblem</span>            |
|--------------------------|-------------------------------------|-------------------------------------|
| 🥇 OpenAI o3-mini-low    | <div align="center">**10.8**</div>      | <div align="center" style="color:grey">33.3</div>     |
| 🥈 OpenAI o3-mini-high   | <div align="center">**9.2**</div>       | <div align="center" style="color:grey">34.4</div>     |
| 🥉 OpenAI o3-mini-medium | <div align="center">**9.2**</div>       | <div align="center" style="color:grey">33.0</div>     |
| OpenAI o1-preview        | <div align="center">**7.7**</div>       | <div align="center" style="color:grey">28.5</div>     |
| Deepseek-R1              | <div align="center">**4.6**</div>       | <div align="center" style="color:grey">28.5</div>     |
| Claude3.5-Sonnet         | <div align="center">**4.6**</div>       | <div align="center" style="color:grey">26.0</div>     |
| Claude3.5-Sonnet (new)   | <div align="center">**4.6**</div>       | <div align="center" style="color:grey">25.3</div>     |
| Deepseek-v3              | <div align="center">**3.1**</div>       | <div align="center" style="color:grey">23.7</div>     |
| Deepseek-Coder-v2        | <div align="center">**3.1**</div>       | <div align="center" style="color:grey">21.2</div>     |
| GPT-4o                   | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">25.0</div>     |
| GPT-4-Turbo              | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">22.9</div>     |
| OpenAI o1-mini           | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">22.2</div>     |
| Gemini 1.5 Pro           | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">21.9</div>     |
| Claude3-Opus             | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">21.5</div>     |
| Llama-3.1-405B-Chat      | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">19.8</div>     |
| Claude3-Sonnet           | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">17.0</div>     |
| Qwen2-72B-Instruct       | <div align="center">**1.5**</div>       | <div align="center" style="color:grey">17.0</div>     |
| Llama-3.1-70B-Chat       | <div align="center">**0.0**</div>       | <div align="center" style="color:grey">17.0</div>     |
| Mixtral-8x22B-Instruct   | <div align="center">**0.0**</div>       | <div align="center" style="color:grey">16.3</div>     |
| Llama-3-70B-Chat         | <div align="center">**0.0**</div>       | <div align="center" style="color:grey">14.6</div>     |


## Instructions to evaluate a new model

1. Clone this repository `git clone git@github.com:scicode-bench/SciCode.git`
2. Install the `scicode` package with `pip install -e .`
3. Download the [numeric test results](https://drive.google.com/drive/folders/1W5GZW6_bdiDAiipuFMqdUhvUaHIj6-pR?usp=drive_link) and save them as `./eval/data/test_data.h5`
4. Run `eval/scripts/gencode_json.py` to generate new model outputs (see the [`eval/scripts` readme](eval/scripts/)) for more information
5. Run `eval/scripts/test_generated_code.py` to evaluate the unittests


## Instructions to evaluate a new model using `inspect_ai` (recommended)

Scicode has been integrated with `inspect_ai` for easier and faster model evaluation, compared with the methods above. You need to run the first three steps in the [above section](#instructions-to-evaluate-a-new-model), and then go to the `eval/inspect_ai` directory, setup correspoinding API key, and run the following command:

```bash
cd eval/inspect_ai
export OPENAI_API_KEY=your-openai-api-key
inspect eval scicode.py --model openai/gpt-4o --temperature 0
```

For more detailed information of using `inspect_ai`, see [`eval/inspect_ai` readme](eval/inspect_ai/)

## More information and FAQ

More information, including a [FAQ section](https://scicode-bench.github.io/faq/), is provided on our [website](https://scicode-bench.github.io/).
If you have trouble reaching the website, please find the markdown source in its [github repository](https://github.com/scicode-bench/scicode-bench.github.io/tree/main/docs).

## Attribution

This repository is a fork of the original SciCode project available at [https://github.com/scicode-bench/SciCode](https://github.com/scicode-bench/SciCode). See [ATTRIBUTION.md](ATTRIBUTION.md) for complete attribution information.

## Contact
- Minyang Tian: mtian8@illinois.edu
- Eliu Huerta: elihu@anl.gov
- Hao Peng: haopeng@illinois.edu

## Citation
```bibtex
@misc{tian2024scicode,
    title={SciCode: A Research Coding Benchmark Curated by Scientists},
    author={Minyang Tian and Luyu Gao and Shizhuo Dylan Zhang and Xinan Chen and Cunwei Fan and Xuefei Guo and Roland Haas and Pan Ji and Kittithat Krongchon and Yao Li and Shengyan Liu and Di Luo and Yutao Ma and Hao Tong and Kha Trinh and Chenyu Tian and Zihan Wang and Bohao Wu and Yanyu Xiong and Shengzhu Yin and Minhui Zhu and Kilian Lieret and Yanxin Lu and Genglin Liu and Yufeng Du and Tianhua Tao and Ofir Press and Jamie Callan and Eliu Huerta and Hao Peng},
    year={2024},
    eprint={2407.13168},
    archivePrefix={arXiv},
    primaryClass={cs.AI}
}
```
