1. Title of the Publication Algorithmically-Guided Postharvest Protocols by Experimental Combinatorial Optimization 2. Author Information Ofer Shir, Tel-Hai College, Western Campus, Upper Galilee, ISRAEL; ofersh@telhai.ac.il Boris Yazmir, Migal Institute, Tarshish Street, Kiryat Shemona, ISRAEL; borisy@migal.org.il Assaf Israeli, Migal Institute, Tel-Hai Eastern Campus, Upper Galilee, ISRAEL; assafi@migal.org.il Dan Gamrasni, Tel-Hai College, Western Campus, Upper Galilee, ISRAEL; dang@migal.org.il 3. Corresponding Author: Ofer Shir ofersh@telhai.ac.il 4. Paper Abstract The application of search and learning to experimental domains, where the objective function cannot be accurately simulated, but rather requires a measurement in real industrial settings, lies in the focus of this study. We consider the problem of devising treatment protocols for fresh cucumbers, whose quality rapidly deteriorates once being harvested, by considering the combinatorial space of possible postharvest practices. The overall target is to prescribe a combination of treatments, with specified activation levels, that minimizes the cucumbers' quality loss after 4 weeks in two storage environments: 10°C and 20°C. This study engaged with a postharvest laboratory with industrial settings to research and develop a sequential experimentation procedure, in a closed feedback-loop fashion, and subject to strict budget and timeline constraints. The laboratory measurements comprise the assay of color, stiffness and mass, as well as external blemishes - in both harvest and post-4-weeks points in time. Their deviations constitute the aggregated objective function that undergoes minimization for both temperatures. After formulating the optimization problem, we outline our approach and report on the attained results. The obtained protocols significantly outperform the best-known human reference practice, and their nature is visualized and analyzed. Finally, we mention the impact and outlook for industry. 5. A list containing the competition criteria (in order of importance) {E, F, G, D} 6. Statement why the results satisfy the criteria (E), (F), (G), and (D) - E (The result is equal to or better than the most recent human-created solution to a long-standing problem for which there has been a succession of increasingly better human-created solutions.) Postharvest targets are continuously investigated with the explicit goal of prolonging shelf-lives, whereas the cucumber constitutes a long-standing open challenge because of its high wastage rate and its average storage lifespan of less than two weeks. When compared to the best known human practice, our algorithmically-guided protocols outperformed it dramatically (see also remarks in [9.]). To the best of our knowledge, such an accomplishment for cucumbers has not been reported anywhere in the literature. F (The result is equal to or better than a result that was considered an achievement in its field at the time it was first discovered.) According to Patel and Panigrahi (2019), the longest storage period of cucumbers was 30 days. Our achievement of 9-weeks storage more than doubled that result. G (The result solves a problem of indisputable difficulty in its field.) Postharvest storage of cucumbers encompasses physiological and pathological challenges. The cucumber is a highly-perishable crop and the environmental conditions under which this fruit is grown, transported and displayed significantly affect its quality during shelf-life (and the consequential loss). D (The result is publishable in its own right as a new scientific result independent of the fact that the result was mechanically created.) The result exhibits great merit under the topic of experimental optimization by evolutionary algorithms (a.k.a. Sequential Experimentation) as another real-world corroboration for evolution-in-the-loop (especially since publications in this niche are scarce). Biotechnology-wise, the obtained results in the form of treatment protocols are fascinating by themselves and publishable. 7. Full Citation Ofer M. Shir, Boris Yazmir, Assaf Israeli, and Dan Gamrasni. 2022. Algorithmically-guided postharvest protocols by experimental combinatorial optimization. In Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO '22). Association for Computing Machinery, New York, NY, USA, 2027–2035. https://doi.org/10.1145/3520304.3533976 8. Prize Money Any prize money, if any, is to be divided equally among the co-authors. 9. A statement indicating why this entry would be the "Best" This study constitutes a pioneering work in the domain of Biotechnology / Food Science when an algorithm has guided scientific basic research of fruit in vivo. Already on this first attempt as a Postharvest project, the machine attained outstanding results, which had been unheard of heretofore, by extending the shelf-life of the common cucumber to 9 weeks in storage. The obtained protocols outperformed the best known human practice: the post-storage fruit exhibited a surprising Postharvest quality, while the cucumbers treated by the ‘in-house human protocol’ ended up completely rotten. In terms of computation, it demonstrated the strength of the good old evolution-in-the-loop by going back to basics and relying on the compact yet powerful working principles of evolution strategies. This success story has been of great interest to the Agro and Food industries, due to its potential to revolutionize the current state of Global Food Security by effectively fighting food loss. Finally, this is an exciting validation to the capacity of machines to actively participate in scientific research and significantly contribute to discoveries, thanks to being conception-free and unbiased by flawed intuition. Our algorithmically-guided scientific discovery also caught the attention of the European press - here are a few links to press releases: https://www.finanznachrichten.de/nachrichten-2022-10/57447081-migal-galilee-research-institute-migal-s-advanced-ai-quadruples-cucumber-postharvest-life-008.htm https://www.prnewswire.com/il/news-releases/migals-advanced-ai-quadruples-cucumber-postharvest-life-301663439.html https://latestfinance.news/migals-advanced-ai-quadruples-the-lifespan-of-cucumbers-after-harvest-130422/ 10. Evolutionary Computation Type Mixed-Integer Evolution Strategy (MIES) 11. Publication Date July 2022 (gecco2022's proceedings companion)