Metraipolis › archive › dc_420b4faaa024

TasteBench: Multimodal Benchmark for Sensory Prediction, from Molecules to Sustainable Foods — arXiv:2610.02599

Source: arXiv
Original: https://arxiv.org/abs/2610.02599
License (as archived): CC0-1.0
Archived: 2026-10-05T22:49:05.238Z
SHA-256 of the archived text: 7583d18bcf9d4a5a40332122200d4adc3ee1f7d6614bcd959c81ebe0f2a47167
Stable URL of this page: https://metraipolis.com/documento/dc_420b4faaa024

How to cite

TasteBench: Multimodal Benchmark for Sensory Prediction, from Molecules to Sustainable Foods — arXiv:2610.02599 — arXiv, https://arxiv.org/abs/2610.02599 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_420b4faaa024 (Metraipolis archive dc_420b4faaa024, sha256 7583d18bcf9d4a5a40332122200d4adc3ee1f7d6614bcd959c81ebe0f2a47167)

BibTeX

@misc{dc420b4faaa024,
  title = {TasteBench: Multimodal Benchmark for Sensory Prediction, from Molecules to Sustainable Foods — arXiv:2610.02599},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02599},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_420b4faaa024; sha256 7583d18bcf9d4a5a40332122200d4adc3ee1f7d6614bcd959c81ebe0f2a47167},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02599. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sustainable protein discovery lacks the fast computational proxies, analogous to molecular docking or density functional theory, that accelerate drug and materials discovery. Evaluating whether a novel food tastes like its animal-based target requires expensive human sensory panels, bottlenecking the design-build-test loop. We introduce TasteBench, a multimodal benchmark and privacy-preserving competition for sensory prediction, spanning two tasks: a food-level ranking task built on 21K+ human evaluations across 215 plant-based foods in 24 product categories, yielding 935 within-category ranking pairs, and a supporting molecular-level taste classification task over 15K flavor molecules. To enable rigorous interpretation of model performance, we characterize the ground truth: inter-rater agreement among panelists is low (Krippendorff's $\alpha = .077$), and the split-half reliability ceiling of panel-aggregated rankings is .825, establishing the range within which ML systems on this benchmark should be assessed. We evaluate baselines across four input modalities; on the same pairs panelists rated, the best model achieves .661 pairwise accuracy, competitive with the median individual panelist (.650), and .683 across all within-category pairs. TasteBench provides the evaluation infrastructure and baselines for measuring progress on computational screening for sustainable protein discovery.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02599 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:45:55.605Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).