Grading

Grades will be broken down as follows:

• Discussion posts and participation: 10%
• Problem set: 10%
• Paper presentation: 20%
• Course project: 60%

See below for policies on attendance and participation, and see the Paper presentations and Project pages for more detailed grading breakdowns for those assignments.

Course policies

Attendance

Because this is a small topics course that is meant to be interactive, regular attendance and participation are expected throughout the semester, though occasional absences for illness, conferences, research travel, or other reasonable circumstances are okay.

For both the mid-semester project update presentations and the student-led paper presentations during the last few weeks of the course, attendance is required. If you are a presenter and expect to miss the class you’re supposed to present in, please email the instructor as soon as possible. If you miss your presentation, you will need to send the instructor a video recording of your presentation within one week to receive credit.

Final project presentations will occur during the course’s designated final exam period (9am-12pm on Tuesday, December 15th) and attendance is required.

Collaboration policy

• Reading responses should be done independently by each student.
• Students are encouraged to collaborate on the problem set, so long as they list the other students they worked with.
• Paper presentations will be done in groups of 2-3, and projects will be done in groups of 1-3.

Late work policy

Extensions may be granted at the instructor’s discretion for discussion posts, problem set, and the project proposal. No extensions will be granted for the final project writeup.

Academic integrity

The strength of the university depends on academic and personal integrity. In this course, you must be honest and truthful, abiding by the Computer Science Academic Integrity Policy.

Generative AI use. Generative AI models (including but not limited to ChatGPT, Claude, Gemini, Qwen, etc.) can help support learning, debugging, proofreading, and understanding technical course material. However, these tools should not replace your own intellectual work and understanding. As such, use of AI for the following purposes is prohibited:

• Writing weekly reading responses.
• Generating complete solutions or substantive portions of solutions to problem set questions.
• Generating an entire algorithm implementation or substantive parts of the codebase for the final project.
• Generating a complete mathematical proof or substantive portions of a proof for the final project.
• Generating substantive prose for the project proposal or final project writeup (e.g., more than a paragraph).
• Generating citations without independently locating and verifying the source.
• Generating substantive parts of the slide deck for the paper presentation or final project presentation.

The following uses of AI are permitted:

• Brainstorming final project ideas and technical approaches.
• Asking AI to explain results in existing papers.
• Using AI as a starting point for literature review, followed by an independent literature search (using, e.g., Google Scholar). Note that AI tools (even advanced ones like ChatGPT Deep Research) may not find all related papers, so it is important to do your own search.
• Debugging code and writing generic supporting code (for, e.g., plotting results). Note that students remain responsible for the correctness of the generated code.
• Checking student-written mathematical proofs for correctness.
• Rephrasing and editing student-written text to help with exposition, clarity, grammar, and spelling.
• Providing feedback on slide organization, layout, and presentation.

For the final project and presentations, you should include a section at the end of the paper or presentation disclosing any substantive use of generative AI, including the tool used and what you used it for. Basic use for spelling and grammar does not need to be disclosed. Permitted and disclosed AI use will not be penalized.

The spirit of this policy is that students must remain solely responsible for their own work, even if they use AI to assist. An inability to demonstrate ownership and understanding of one’s submitted work—for example, by failing to answer basic questions about the results in one’s final project—may affect the relevant rubric scores. If you are uncertain about whether a particular use of AI is allowed, please ask the instructor.

Accessibility and accommodations

Johns Hopkins University is committed to providing welcoming, equitable, and accessible educational experiences for all students. If disability accommodations are needed for this course, students should request accommodations through Student Disability Services (SDS) as early as possible to provide time for effective communication and arrangements.

For further information about this process, please refer to the SDS Website.