2024 MCM
Problem B: Searching for Submersibles
Maritime Cruises Mini-Submarines (MCMS), a company based in Greece, builds submersibles capable of carrying humans to the deepest parts of the ocean. A submersible is moved to the location and deployed untethered from a host ship. MCMS now wishes to use their submersible to take tourists on adventures exploring the bottom of the Ionian Sea for sunken shipwrecks.
Before they can do this, however, they need to win approval from regulators by developing safety procedures in case of a loss of communication to the host ship and possible mechanical defects including a loss of propulsion of the submersible. In particular, they would like you to develop a model to predict the location of the submersible over time. Unlike in a typical search and rescue on land or on the surface of a sea, the defective submersible could potentially find itself positioned on the sea floor or at some point of neutral buoyancy underwater. Its position could further be affected by currents, differing densities in the sea, and/or the geography of the sea floor. Your tasks are to:
- Locate - Develop a model(s) that predicts the location of the submersible over time.
- What are the uncertainties associated with these predictions?
- What information can the submersible periodically send to the host ship to decrease these uncertainties prior to an incident? What kinds of equipment would the submersible need to do so?
- Prepare - What, if any, additional search equipment would you recommend the company carry on the host ship to deploy if necessary? You may consider different types of equipment but must also consider costs associated with availability, maintenance, readiness, and usage of this equipment. What additional equipment might a rescue vessel need to bring in to assist if necessary?
- Search - Develop a model that will use information from your location model(s) to recommend initial points of deployment and search patterns for the equipment so as to minimize the time to location of a lost submersible. Determine the probability of finding the submersible as a function of time and accumulated search results.
- Extrapolate - How might your model be expanded to account for other tourist destinations such as the Caribbean Sea? How will your model change to account for multiple submersibles moving in the same general vicinity?
Prepare a report of no more than 25 pages providing the details of your plan. Include a two-page memo of your report addressed to the Greek government to help win approval.
Your PDF solution of no more than 25 total pages should include:
- One-page Summary Sheet.
- Table of Contents.
- Your complete solution.
- Two-page memo.
- References list.
- AI Use Report (If used does not count toward the 25-page limit.)
Note: There is no specific required minimum page length for a complete MCM submission. You may use up to 25 total pages for all your solution work and any additional information you want to include (for example: drawings, diagrams, calculations, tables). Partial solutions are accepted. We permit the careful use of AI such as ChatGPT, although it is not necessary to create a solution to this problem. If you choose to utilize a generative AI, you must follow the COMAP AI use policy. This will result in an additional AI use report that you must add to the end of your PDF solution file and does not count toward the 25 total page limit for your solution.
Glossary
Submersible: A submersible is an underwater vehicle which needs to be transported and supported by a larger watercraft or platform. This distinguishes submersibles from submarines, which are self-supporting and capable of prolonged independent operation at sea.
Neutral buoyancy occurs when an object's average density is equal to the density of the fluid in which it is immersed, resulting in the buoyant force balancing the force of gravity that would otherwise cause the object to sink (if the body's density is greater than the density of the fluid in which it is immersed) or rise (if it is less). An object that has neutral buoyancy will neither sink nor rise.
Use of Large Language Models and Generative AI Tools in COMAP Contests
This policy is motivated by the rise of large language models (LLMs) and generative AI assisted technologies. The policy aims to provide greater transparency and guidance to teams, advisors, and judges. This policy applies to all aspects of student work, from research and development of models (including code creation) to the written report. Since these emerging technologies are quickly evolving, COMAP will refine this policy as appropriate.
Teams must be open and honest about all their uses of AI tools. The more transparent a team and its submission are, the more likely it is that their work can be fully trusted, appreciated, and correctly used by others. These disclosures aid in understanding the development of intellectual work and in the proper acknowledgement of contributions. Without open and clear citations and references of the role of AI tools, it is more likely that questionable passages and work could be identified as plagiarism and disqualified.
Solving the problems does not require the use of AI tools, although their responsible use is permitted. COMAP recognizes the value of LLMs and generative AI as productivity tools that can help teams in preparing their submission; to generate initial ideas for a structure, for example, or when summarizing, paraphrasing, language polishing etc. There are many tasks in model development where human creativity and teamwork is essential, and where a reliance on AI tools introduces risks. Therefore, we advise caution when using these technologies for tasks such as model selection and building, assisting in the creation of code, interpreting data and results of models, and drawing scientific conclusions.
It is important to note that LLMs and generative AI have limitations and are unable to replace human creativity and critical thinking. COMAP advises teams to be aware of these risks if they choose to use LLMs:
- Objectivity: Previously published content containing racist, sexist, or other biases can arise in LLM-generated text, and some important viewpoints may not be represented.
- Accuracy: LLMs can ‘hallucinate’ i.e. generate false content, especially when used outside of their domain or when dealing with complex or ambiguous topics. They can generate content that is linguistically but not scientifically plausible, they can get facts wrong, and they have been shown to generate citations that don’t exist. Some LLMs are only trained on content published before a particular date and therefore present an incomplete picture.
- Contextual understanding: LLMs cannot apply human understanding to the context of a piece of text, especially when dealing with idiomatic expressions, sarcasm, humor, or metaphorical language. This can lead to errors or misinterpretations in the generated content.
- Training data: LLMs require a large amount of high-quality training data to achieve optimal performance. In some domains or languages, however, such data may not be readily available, thus limiting the usefulness of any output.
Guidance for teams
Teams are required to:
- Clearly indicate the use of LLMs or other AI tools in their report, including which model was used and for what purpose. Please use inline citations and the reference section. Also append the Report on Use of AI (described below) after your 25-page solution.
- Verify the accuracy, validity, and appropriateness of the content and any citations generated by language models and correct any errors or inconsistencies.
- Provide citation and references, following guidance provided here. Double-check citations to ensure they are accurate and are properly referenced.
- Be conscious of the potential for plagiarism since LLMs may reproduce substantial text from other sources. Check the original sources to be sure you are not plagiarizing someone else’s work.
COMAP will take appropriate action
when we identify submissions likely prepared with undisclosed use of such tools.
Citation and Referencing Directions
Think carefully about how to document and reference whatever tools the team may choose to use. A variety of style guides are beginning to incorporate policies for the citation and referencing of AI tools. Use inline citations and list all AI tools used in the reference section of your 25-page solution.
Whether or not a team chooses to use AI tools, the main solution report is still limited to 25 pages. If a team chooses to utilize AI, following the end of your report, add a new section titled Report on Use of AI. This new section has no page limit and will not be counted as part of the 25-page solution.
Examples (this is not exhaustive – adapt these examples to your situation):
Report on Use of AI
- OpenAI ChatGPT (Nov 5, 2023 version, ChatGPT-4) Query1: <insert the exact wording you input into the AI tool> Output: <insert the complete output from the AI tool>
- OpenAI Ernie (Nov 5, 2023 version, Ernie 4.0)
Query1: <insert the exact wording of any subsequent input into the AI tool> Output: <insert the complete output from the second query>
- Github CoPilot (Feb 3, 2024 version)
Query1: <insert the exact wording you input into the AI tool> Output: <insert the complete output from the AI tool>
- Google Bard (Feb 2, 2024 version)
Query: <insert the exact wording of your query> Output: <insert the complete output from the AI tool>
译文
2024 MCM
问题 B:寻找潜水器
希腊的一家公司 Maritime Cruises Mini-Submarines(MCMS)制造的潜水器能够载人到海洋的最深处。潜水器被移动到指定地点,并在不与主船相连的情况下部署。MCMS 公司现在希望利用他们的潜水器带领游客在爱奥尼亚海海底探险,寻找沉船残骸。
不过,在此之前,他们需要制定安全程序,以防与主船失去联系以及可能出现的机械故障(包括潜水器失去推进力),从而赢得监管机构的批准。特别是,他们希望你们开发一个模型,以预测潜水器在一段时间内的位置。与在陆地或海面上的典型搜救不同,有缺陷的潜水器有可能被放置在海底或水下中性浮力点。它的位置还可能受到海流、海中不同密度和/或海底地理环境的影响。你们的任务是:
(1)Locate - 建立一个(多个)模型,预测潜水器在一段时间内的位置。
o 这些预测有哪些不确定性?
o 在事故发生前,潜水器可定期向主机发送哪些信息以减少这些不确定性?为此,潜水器需要哪些设备?
(2)Prepare - 如果有的话,你建议公司在主机船上携带哪些额外的搜索设备,以便在必要时部署?您可以考虑不同类型的设备,但也必须考虑与这些设备的可用性、维护、准备和使用相关的成本。如果有必要,救援船可能需要携带哪些额外的设备来提供帮助?
(3)Search - 建立一个模型,利用定位模型中的信息来建议设备的初始部署点和搜索模式,以便最大限度地缩短找到失联潜水器的时间。根据时间和累积搜索结果,确定找到潜水器的概率。
(4)Extrapolate - 如何将你的模型扩展到其他旅游目的地,如加勒比海?如果多艘潜水器在同一附近移动,您的模型将如何变化?
准备一份不超过 25 页的报告,提供计划的详细信息。包括一份给希腊政府的两页备忘录,以帮助赢得批准。
您的 PDF 解决方案总页数不超过 25 页,其中应包括
1.一页摘要表。
2.目录。
3. 您的完整解决方案。
4. 两页备忘录。
5.参考文献列表。
6.人工智能使用报告(如果使用,则不计入 25 页限制。)
注意:对于提交的完整材料,没有具体的最低页数要求。你可以用最多 25 页的篇幅来完成所有的解答工作,以及你想包含的任何附加信息(例如:图纸、图表、计算、表格)。我们接受部分解决方案。我们允许谨慎使用人工智能,如 ChatGPT,但没有必要为这一问题创建解决方案。如果您选择使用生成式人工智能,则必须遵守 COMAP 人工智能使用政策。这将导致一份额外的人工智能使用报告,您必须将其添加到 PDF 解决方案文件的末尾,并且不计入解决方案的 25 页总页数限制中。
术语表
潜水器 潜水器是一种需要由较大的水上船只或平台运输和支持的水下航行器。这使潜水器有别于潜水艇,后者可以自给自足,并能在海上长时间独立作业。
当物体的平均密度等于浸入液体的密度时,就会产生中性浮力,从而使浮力与重力平衡,否则重力会导致物体下沉(如果物体的密度大于浸入液体的密度)或上浮(如果物体的密度小于重力)。具有中性浮力的物体既不会下沉,也不会上升。
在 COMAP 竞赛中使用大型语言模型和生成式人工智能工具
本政策的出台是由于大型语言模型(LLM)和生成式人工智能辅助技术的兴起。该政策旨在为参赛队、顾问和评委提供更高的透明度和指导。该政策适用于学生作品的各个方面,从模型的研究和开发(包括代码创建)到书面报告。由于这些新兴技术发展迅速,COMAP 将根据实际情况完善本政策。
团队必须公开、诚实地说明他们对人工智能工具的所有使用情况。团队及其提交的报告越透明,其工作就越有可能得到他人的充分信任、赞赏和正确使用。这些信息的披露有助于了解智力工作的发展,也有助于对贡献给予适当的肯定。如果不对人工智能工具的作用进行公开、明确的引用和参考,有问题的段落和作品更有可能被认定为剽窃并取消资格。
解决这些问题并不需要使用人工智能工具,但允许负责任地使用这些工具。COMAP 认识到 LLM 和生成式人工智能作为生产力工具的价值,它们可以帮助团队准备提交材料;例如,为结构生成初步想法,或者在总结、转述、语言润色等方面。在模型开发的许多任务中,人类的创造力和团队合作是必不可少的,而依赖人工智能工具则会带来风险。因此,我们建议在使用这些技术进行模型选择和构建、协助创建代码、解释数据和模型结果以及得出科学结论等任务时要谨慎。
必须注意的是,LLM 和生成式人工智能有其局限性,无法取代人类的创造力和批判性思维。COMAP 建议各团队在选择使用 LLMs 时要注意这些风险:
1.Objectivity: 以前发表的含有种族主义、性别歧视或其他偏见的内容可能会出现在 LLM 生成的文本中,一些重要的观点可能无法体现。
2.准确性: LLM 可能会产生 "幻觉",即生成错误的内容,尤其是在其领域之外使用或处理复杂或模糊的主题时。它们可能会生成语言上可信但科学上不可信的内容,可能会弄错事实,还可能生成不存在的引文。有些 LLM 只针对特定日期前发布的内容进行培训,因此呈现的内容并不完整。
3.语境理解: LLM 无法将人类的理解力应用到文本的上下文中,尤其是在处理成语表达、讽刺、幽默或隐喻性语言时。这会导致生成的内容出现错误或曲解。
4. 训练数据: LLM 需要大量高质量的训练数据才能达到最佳性能。但是,在某些领域或语言中,此类数据可能并不容易获得,从而限制了任何输出结果的实用性。
参赛队指南
要求参赛队
1.在报告中明确指出使用了 LLM 或其他人工智能工具,包括使用了哪种模型以及用 于何种目的。请使用内联引文和参考文献部分。同时在 25 页的解决方案后附上人工智能使用报告(如下所述)。
2.核实语言模型生成的内容和任何引文的准确性、有效性和适当性,并纠正任何错误或不一致之处。
3.按照此处提供的指导提供引文和参考文献。仔细检查引文,确保其准确无误,并正确引用。
4.意识到剽窃的可能性,因为法律硕士可能会从其他来源复制大量文字。检查原始资料来源,确保您没有剽窃他人的作品。
COMAP 将采取适当行动
当我们发现提交的材料可能是在未披露使用此类工具的情况下编写的。
引用和参考指南
无论团队选择使用什么工具,都要仔细考虑如何记录和引用。各种风格指南都开始纳入人工智能工具的引用和参考政策。请使用内联引文,并在 25 页解决方案的参考文献部分列出所有使用过的人工智能工具。
无论团队是否选择使用人工智能工具,主要解决方案报告仍以 25 页为限。如果团队选择使用人工智能,请在报告末尾添加一个新章节,标题为 "人工智能使用报告"。这一新部分没有页数限制,也不会算作 25 页解决方案的一部分。
示例(并非详尽无遗--请根据您的情况调整这些示例):
人工智能使用报告
1.OpenAI ChatGPT(2023 年 11 月 5 日版本,ChatGPT-4) Query1: <插入您输入人工智能工具的准确措辞> 输出: <输入人工智能工具的完整输出>。
2.OpenAI Ernie(2023 年 11 月 5 日版本,Ernie 4.0)
查询1: <插入随后输入人工智能工具的准确措辞> 输出:<插入人工智能工具的完整输出> 2.OpenAI Ernie(2023 年 11 月 5 日版本,Ernie 4.0 <插入第二个查询的完整输出>。