# 整个人类的烹饪艺术浓缩在2兆字节中

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：josefchen
- 发布时间：2026-05-27 21:49
- AIHOT 分数：53
- AIHOT 链接：https://aihot.virxact.com/items/cmpo4vz7h02yeslv48qpf2fqo
- 原文链接：https://arxiv.org/abs/2605.22391

## AI 摘要

研究将人类烹饪艺术数据压缩至仅2兆字节。该成果已发布于arxiv.org，论文编号为2605.22391。

## 正文

Computer Science > Artificial Intelligence

Title:Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings

Abstract:We present Epicure, a family of three sibling skip-gram ingredient embeddings retrained from scratch on a multilingual recipe corpus. We aggregate 4.14M recipes from 11 sources spanning seven languages, English, Chinese, Russian, Vietnamese, Spanish, Turkish, Indonesian, German, and Indian-English, and normalise the raw ingredient strings to 1,790 canonical entries via an LLM-augmented pipeline. A 203,508-edge ingredient-ingredient NPMI graph and an 80,019-edge typed FlavorDB ingredient-compound graph, 2,247 typed compound nodes across 15 categories, seed three Metapath2Vec variants that share architecture and hyperparameters and differ only in the random-walk schema: Cooc walks the co-occurrence graph only, Chem walks the typed compound metapaths only, and Core blends both via injected ingredient-ingredient walks at controlled mixing, placing each model at a distinct point on the chemistry-vs-recipe-context spectrum.

Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY) Cite as: arXiv:2605.22391 [cs.AI] (or arXiv:2605.22391v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2605.22391 Focus to learn more arXiv-issued DOI via DataCite

Submission history

Access Paper:

View PDF

HTML (experimental)

TeX Source

Ancillary files (details):

README.md

README.txt

csv/README.md

csv/cross_modal.csv

csv/direction_arithmetic_full.csv

csv/direction_orthogonal.csv

csv/factor_top_alignments_ica_chem_n20.csv

csv/factor_top_alignments_ica_cooc_n20.csv

csv/factor_top_alignments_ica_core_n20.csv

csv/linear_probe.csv

csv/linear_probe_continuous.csv

csv/mode_atlas_chem.csv

csv/mode_atlas_cooc.csv

csv/mode_atlas_core.csv

csv/procrustes_sensory.csv

csv/weat.csv

epicure_chem.csv

epicure_cooc.csv

epicure_core.csv

supplement.pdf

vocab.csv

(16 additional files not shown)

Current browse context:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

Author

Venue

Institution

Topic

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.