CS357: Foundations of Artificial Intelligence - Literature Review (100 Points)

Purpose, Task, and Criteria

Purpose: To test the plan your team has already committed to against the published evidence rather than against your intuitions, and to make your understanding of the problem multi-disciplinary by reading what the stakeholder's own field says about it, while there is still time for what you find to change the project.

Task: Individually annotate 2-3 credible sources, then as a team write a one-page synthesis that connects them to your problem statement, tests the gap your proposal claimed, and states plainly what the evidence confirms, complicates, or changes about the plan you proposed.

Criteria: I grade this on faithful summaries in your own words, specific credibility assessments, relevance tied to the problem statement, a required span of at least two disciplinary perspectives, a gap that follows from the sources, and an honest account of what the evidence changes about your proposed plan. The rubric below has the details.

Assignment Goals

The goals of this assignment are:

To research the team's stakeholder problem through published sources, assessing each source's credibility and relevance to the problem statement (Goal 11)
To build a multi-disciplinary understanding of the problem by drawing sources from at least two disciplinary perspectives, including the stakeholder's own discipline (Goal 12)
To synthesize individually gathered sources into a team-level account of what is known and the specific gap the project addresses, and to carry that account back into the project plan as a stated confirmation, revision, or risk
To practice information literacy, finding, reading, and critically evaluating scholarly and technical sources

Background Reading and References

Please refer to the following readings and examples offering templates to help get you started:

The Assignment

In this Project Thread milestone, your team finds out what the world already knows about your stakeholder’s problem, and whether that knowledge agrees with the plan you just proposed. The review runs in two phases. In Phase 1, each team member works alone and builds an annotated bibliography of 2-3 sources. In Phase 2, the team writes one page that connects everyone’s sources to the problem statement, names the gap your project will address, and says what the evidence changes about the plan. The assignment goes out the day your Final Project Proposal is due.

A literature review is not a book report, and it is not a pile of links. It is an argument: here is what is known, here is who knows it, here is the hole in it, and here is why that hole matters to our stakeholder. The two-phase structure means every member does real source work (there is no way to ride along on a teammate’s reading), and the synthesis forces the sources to talk to each other.

Timeline

Phase	Who submits	What you submit	Due
Phase 1: Individual Annotated Bibliography	Each member, individually, via the LMS	2-3 annotated sources, search notes, complete citations	See the course schedule
Phase 2: Team Synthesis	One PDF per team	One-page synthesis, plan-impact section, combined bibliography, signatures, AI-use disclosure	See the course schedule

Phase 1 is due first, and it is the longer half. Schedule the Phase 2 team meeting in advance.

Key Concepts

Term	Plain-English Definition	Where It Appears
Annotated bibliography	A list of sources where each entry carries a paragraph of your own: what the source says, whether to trust it, and why it matters here.	Phase 1
Scholarly source	Peer-reviewed work (journal article, conference paper, academic book). Its claims were checked by other experts before publication, which makes it slower and usually more careful than other sources.	Phase 1 requirement
Technical documentation	Official docs, standards, white papers, and engineering reports. Authoritative about how a thing works; not evidence about whether it helps anyone. Allowed, in its lane.	Phase 1
Credibility assessment	Your judgment of what a source can support, based on venue, method, incentives, and recency, not a binary “credible/not.”	Every annotation
Synthesis	Writing that connects sources to each other and to your problem (agreement, conflict, and complement) rather than summarizing them one at a time.	Phase 2
The gap	The specific missing thing your project will address: a question no source answers, a population no study covers, a tool no one has built for this context.	Phase 2
Citation chaining	Finding sources by following a good source’s references (backward) and the papers that cite it (forward). The fastest way to map a literature.	Information literacy guidance

Before You Start

Start from a question. This builds on your Stakeholder Brief, whose problem statement tells you what to go looking for, and on your Final Project Proposal. A literature review without a question is a reading list. Keep both open while you work; every step below refers back to one or both of them.
You are reading against a plan you have already committed to. That is the point. The proposal named a gap and made design decisions. Your job here is to find out whether the published evidence supports them. If you come back and report that a source complicates your plan, the assignment is working; that is not a setback. The synthesis has to say what changed.
The two phases have a hard boundary. Everyone writes an individual annotated bibliography first. Only then does the team synthesize. The individual phase is not a formality: a synthesis assembled from four people who each read one source is visibly thinner than one assembled from four people who each read several.
Search where the evidence lives. Start with the Information Literacy section below rather than with a general web search. The library’s databases and Google Scholar surface different things, and the difference matters for what you are able to claim.

On using AI here. AI tools are permitted, disclosed, and useful for finding and triaging sources. They are also the single most reliable way to end up citing a paper that does not exist. Every source you cite must be one you opened. Not one a model described to you: one you opened, with a link or DOI (digital object identifier) that resolves. Check every one before you submit, and say in your disclosure how you checked.

Phase 1: Individual Annotated Bibliography

Imagine typing your project’s name into a search box, skimming a few abstracts from thousands of hits, and coming away with three links that all say roughly the same thing. None of them tells you whether your plan holds up. Phase 1 avoids that by starting from the problem statement, dividing the reading before anyone searches, and asking you to judge each source rather than just list it. Each team member, working alone, finds and annotates 2-3 sources relevant to the team’s problem statement. You are the primary author of your own annotations; I grade them individually.

Step 1.1: Divide the territory with your team

Goal: agree on who searches where before anyone starts. In a standup, divide the territory so that, combined, at least one source comes from the stakeholder’s discipline and the set is not three copies of the same paper. Log the division.

You should have. A logged division of the territory, with each member’s name next to the angle they will search.

Predict: if every member searched the same keywords independently, what would the team’s combined bibliography probably look like?

Step 1.2: Search and build a candidate list

Goal: find candidate sources from the right places, and note how you found each one. Follow The search recipe in the Information Literacy section below: library databases and Google Scholar, the stakeholder’s vocabulary and yours, and chaining from any good source. Log your search terms as you go; you need them in Step 1.6.

You should have. A short list of candidates, each with a link or DOI and the database and search terms (or the source you chained from) that found it.

Step 1.3: Choose your 2-3 sources

Goal: pick the 2-3 you will annotate and confirm they meet the source-type rules before you invest reading time. At least one must be a scholarly source (peer-reviewed article, conference paper, or academic book chapter). Technical documentation (official docs, standards, agency or nongovernmental organization (NGO) reports) is allowed where it is the right tool, but it supplements the scholarly requirement rather than replacing it.

You should have. 2-3 sources, each opened, each with a link or DOI that resolves, and at least one of them scholarly.

If it fails. If none of your picks is scholarly, chain from your best technical source into the research literature it cites or that cites it. If a source will not open, drop it.

Step 1.4: Read each source critically

Goal: understand each source well enough to explain its claim and its evidence in your own words. Open every source and read it with The critical-reading protocol in the Information Literacy section below. If you cannot summarize it without the abstract open, read it again.

You should have. For each source, an answer to the protocol’s three questions (or, for technical documentation, its version and currency questions).

Step 1.5: Write one annotation per source

Goal: write one annotation of 150-250 words per source, from the source itself rather than the abstract, with these three labeled parts:

Summary: what the source claims and on what evidence, in your own words.
Credibility assessment: venue and review process, method and sample, who funded or published it and what they might want, how current it is, and (most importantly) what this source can and cannot support. “Peer-reviewed” is the start of an assessment, not the end of one.
Relevance to the problem: which element of your team’s problem statement this source informs, and what it changes. Does it confirm an assumption, kill one, or open a question?

You should have. One 150-250 word annotation per source with all three labeled parts.

Predict: “peer-reviewed, so credible” stops short. For one of your sources, what is one thing it cannot support, even though it passed review?

Step 1.6: Record how you found each source and cite it

Goal: make your search reproducible and your citations complete. Record how you found each source (database and search terms, or what you chained from), and write a complete, consistently formatted citation for it.

You should have. A “how I found it” line and a complete citation for every source, in one format.

Step 1.7: Fill in the skeleton and submit

Goal: assemble your bibliography and submit it individually via the LMS by the Phase 1 date.

Paste into your submission. Use this skeleton for each of your 2-3 sources, and fill every line.
Citation (complete, consistently formatted):
How I found it (database and search terms, or chained from):
Summary:
Credibility assessment:
Relevance to our problem statement:

You should have. One filled skeleton per source, submitted to the LMS. Run the Individual annotated bibliography items in the Self-Check first.

Phase 2: Team Synthesis

Now picture everyone’s annotations on the table, from at least two fields. If you stack them up (“Source 1 says… Source 2 says…”), you have a longer bibliography, not a synthesis. Phase 2 asks you to read across the stack: where the sources agree, where they disagree, what none of them cover, and what that means for the plan you proposed. The synthesis is one page, with a named primary author who holds drafting responsibility. The whole team reviews and signs.

Step 2.1: Meet and name the primary author

Goal: start with every bibliography in hand. Meet as a team after every Phase 1 bibliography is in. Name the primary author.

You should have. Every member’s annotations in front of the team, and a named primary author.

Step 2.2: Organize by idea, not by source

Goal: connect the team’s combined sources to the problem statement from your Stakeholder Brief, organized by idea, not by source. Write “Three of our sources agree that X; the exception is…” rather than “Source 1 says… Source 2 says…”.

You should have. An outline whose headings are ideas tied to the problem statement, each listing the sources that support or complicate it.

Step 2.3: Show where the disciplines meet

Goal: show where the disciplinary perspectives converge, conflict, or measure success differently, and what that means for the project.

Watch out. The team’s combined review must span at least two disciplinary perspectives (for example, computer science and public health; education and economics), including the stakeholder’s discipline. A review whose every source is a CS paper fails this requirement regardless of quality.

You should have. A passage that names two disciplines, says where they agree, disagree, or define success differently, and says what that means for the project.

Step 2.4: Identify the gap

Goal: identify the gap the project will address, and show that it follows from the sources: what exists, what is missing, why the missing piece matters to your stakeholder.

You should have. A specific gap statement (not “more work is needed”) that follows from your sources.

Predict: is this the same gap your proposal claimed, a narrower one, or a different one?

Step 2.5: Note where your sources are weakest

Goal: note honestly where your source base is weakest. That weakness is the seed of future work, and of your proposal’s risk section.

You should have. A short, specific statement of the weakest part of your source base (for example, a question only one source addresses, or a perspective missing from the set).

Step 2.6: State what this changes about the plan

Goal: name the elements of your proposal the evidence confirms, the ones it complicates, and any it kills, with the source that did it. If the sources leave the plan standing, say so and say why. That is a finding, not a formality.

Paste into your submission. Give the “what this changes about the plan” section its own heading, one entry per proposal element.
Proposal element:
Confirmed, complicated, or changed:
Source(s) responsible:
What we are doing about it (or why the plan stands):

You should have. That section under its own heading, with the source responsible named in every entry.

Step 2.7: Record any scope change

Goal: make sure what you learned reaches the project. Record any resulting scope change in your decision log and raise it at your next intra-team check-in.

You should have. A decision-log entry for each scope change, on the agenda for your next check-in.

Step 2.8: Review, sign, and assemble the team PDF

Goal: have every member review and sign, then assemble the team PDF listed under Deliverables: the one-page synthesis with the primary author named, the what this changes about the plan section, the combined bibliography, all members’ typed signatures, and the team AI-use disclosure.

You should have. One PDF with every item above. Run the Team synthesis items in the Self-Check first.

Information Literacy: Finding and Reading Sources Critically

This section gives you two tools for the same skill: a search recipe (Step 1.2) and a reading protocol (Step 1.4).

The search recipe

Do this.

Start at the library databases (via the Ursinus library site) and Google Scholar, not the open web. Search the stakeholder’s vocabulary and yours: the education literature says “formative feedback” where CS says “evaluation loop.”

When you find one good source, chain it. Mine its references for older foundations (backward), and use Google Scholar’s “Cited by” for what came after (forward).

To reach the stakeholder’s discipline, look up which journals their field actually reads (your interview’s “what should we read?” question was for this), or ask a librarian. Asking a librarian is a professional move, not a fallback.

Log your search terms as you go. Each annotation reports how its source was found.

The critical-reading protocol

For a scholarly paper, read in this order: the abstract, then the introduction’s last paragraph (the claimed contribution), then the figures and tables, then the conclusion’s limitations. Then decide whether the middle is worth your hour. As you read, keep three questions open:

What is the actual evidence (sample, method, effect size)?
Who is not represented in it?
What do the authors themselves say it cannot show?

For technical documentation, the questions shift. What version is this? Is it current? Is it describing designed behavior or measured behavior?

A note on AI assistance. You may use AI tools to find candidate sources or to explain difficult passages. But every annotation must be written by you from the actual source, every quote and claim must be verified against the source itself (models fabricate citations fluently), and all AI assistance goes in the disclosure. An annotated bibliography with a hallucinated source is an integrity violation, not a formatting error.

Deliverables

File or artifact	What it shows	Rubric row
Phase 1: your own annotated bibliography (2-3 annotated sources, search notes, complete citations), submitted individually via the LMS	You read, judged, and connected real sources	Individual Annotations; Disciplinary Breadth; Information Literacy
Phase 2: one team PDF containing the one-page synthesis, primary author named	The sources talk to each other and the gap follows from them	Team Synthesis; Disciplinary Breadth
In the team PDF: the what this changes about the plan section	The evidence was carried back into the proposal	Team Synthesis
In the team PDF: the combined bibliography, all members’ typed signatures, and the team AI-use disclosure	Complete citations and the Project Thread process elements	Information Literacy
Your individual answers to the Reflection Prompts below	What the reading changed for you	Part of a complete submission

Reflection Prompts

Answer individually in your submission, keyed to the Open Questions (Goal 15):

How can we understand the world? Pick the source from another discipline that most changed how you see the problem. What does that discipline accept as evidence that surprised you, and has your idea of what “knowing something” means shifted at all?
What should matter to me? The gap your team named is a claim about what deserves work. Whose needs does that gap center, and whose did your sources let you overlook?

Self-Check Before You Submit

Individual annotated bibliography

Every source is one I actually opened, and every link or DOI resolves.
Each annotation says what the source claims, how it knows, and what it means for our problem, rather than summarizing an abstract.
Each annotation includes a specific credibility assessment (venue, method, funding or incentive, recency, and what the source can and cannot support) and ties the source to a named element of our problem statement.
At least one of my sources is scholarly, and each annotation notes how I found the source (database, search terms, or citation chain) and gives a complete citation.
Across the team’s combined set, the sources span at least two disciplinary perspectives, and at least one comes from the stakeholder’s discipline.

Team synthesis

The synthesis is organized by theme or argument, not source by source.
Where sources disagree, the disagreement is stated and not smoothed over, and at least one observation says where the disciplines converge, conflict, or define success differently, and what that means for the project.
The gap our project addresses is named, and it follows from the sources rather than being asserted before them.
We have said what the evidence confirms, complicates, or changes about our proposal, naming the element affected and the source responsible.
If nothing about the plan changed, we have said why the sources leave it standing rather than leaving the question unanswered.
Every claim traces to a citation, and every citation traces to a source someone on the team read.
We noted honestly where our sources are weakest.
AI disclosure names what was AI-assisted and how citations were verified.
The synthesis names its primary author, the combined bibliography is consistently formatted, and the PDF carries all members’ typed signatures.

Submission

In your submission, please include answers to any questions asked on the assignment page, as well as the questions listed below, in your README file.

If you wrote code as part of this assignment, please describe your design, approach, and implementation in a separate document prepared using a word processor or typesetting program such as LaTeX. This document should include specific instructions on how to build and run your code, and a description of each code module or function that you created suitable for re-use by a colleague.

In your README, please include answers to the following questions:

Describe what you did, how you did it, what challenges you encountered, and how you solved them.
Please answer any questions found throughout the narrative of this assignment.
If collaboration with a buddy was permitted, did you work with a buddy on this assignment? If so, who? If not, do you certify that this submission represents your own original work?
Please identify any and all portions of your submission that were not originally written by you (for example, code originally written by your buddy, or anything taken or adapted from a non-classroom resource). It is always OK to use your textbook and instructor notes; however, you are certifying that any portions not designated as coming from an outside person or source are your own original work.
Approximately how many hours it took you to finish this assignment (I will not judge you for this at all...I am simply using it to gauge if the assignments are too easy or hard)?
Your overall impression of the assignment. Did you love it, hate it, or were you neutral? One word answers are fine, but if you have any suggestions for the future let me know.
Using the grading specifications on this page, discuss briefly the grade you would give yourself and why. Discuss each item in the grading specification.
Any other concerns that you have. For instance, if you have a bug that you were unable to solve but you made progress, write that here. The more you articulate the problem the more partial credit you will receive (it is fine to leave this blank).
Please describe any use of outside resources you may have engaged in the completion of this assignment, including the use of generative Artificial Intelligence.

Assignment Rubric

Description	Pre-Emerging (< 50%)	Beginning (50%)	Progressing (85%)	Proficient (100%)
Individual Annotations, Summary, Credibility, and Relevance (Goal 11) (40%)	Annotations are missing, or are copied abstracts rather than the student's own account	Two to three sources are listed but annotations summarize only, with no credibility assessment or no connection to the team's problem statement, or the required source types (at least one scholarly; at least one from the stakeholder's discipline across the set) are not met	Each annotation contains a summary, a credibility assessment, and a relevance statement, but at least one element is thin, a credibility assessment that says "peer-reviewed, so credible" or a relevance claim that does not mention the stakeholder's problem	Each of the student's 2-3 annotations contains a faithful summary in the student's own words, a specific credibility assessment (venue, method, funding or incentive, recency, and what the source can and cannot support), and a relevance statement that ties the source to a named element of the team's problem statement; at least one source is scholarly and technical documentation is used appropriately where included (Goal 11)
Disciplinary Breadth (Goal 12) (20%)	All sources are from a single perspective, or the stakeholder's discipline is absent from the team's combined review	A second discipline appears in the source list but the annotations do not engage with how that discipline frames the problem	The combined review spans two disciplinary perspectives including the stakeholder's discipline, and annotations engage each field's framing, but the perspectives never meet, no annotation or synthesis paragraph notes where the fields agree, disagree, or measure differently	The team's combined review spans at least two disciplinary perspectives, at least one source comes from the stakeholder's discipline, and the writing shows the perspectives interacting, at least one explicit observation of where the disciplines converge, conflict, or define success differently, and what that means for the project (Goal 12)
Team Synthesis and Gap Identification (Goals 11, 12) (25%)	No synthesis is submitted, or it is a list of the annotations restated	The synthesis connects some sources to each other but not to the problem statement, or names no gap	The one-page synthesis connects the sources to the problem statement and proposes a gap, but the gap is generic ("more work is needed") or is not actually supported by the reviewed sources, or the account of what the evidence changes about the proposed plan is present but perfunctory	The one-page synthesis, with a named primary author, weaves the team's sources into a coherent account of what is known about the stakeholder's problem, states the specific gap the project addresses, shows that the gap follows from the reviewed sources (what exists, what is missing, why it matters to the stakeholder), states explicitly what the evidence confirms, complicates, or changes about the plan the team proposed (naming the affected element of the proposal, and where nothing changed, saying why the sources leave the plan standing), and honestly notes where the team's sources are weakest (Goals 11, 12)
Information Literacy, Process, and Submission (15%)	An incomplete submission is provided	Citations are incomplete or unformatted, search strategies are undocumented, or the Project Thread signatures are missing	Citations are complete and consistent and the submission includes all process elements, with a minor gap such as an undocumented search strategy for one source	Every source has a complete, consistently formatted citation; each annotation notes how the source was found (database, search terms, or citation chain); the submission carries all members' signatures and names the synthesis's primary author; every citation was verified against the actual source

Please refer to the Style Guide for code quality examples and guidelines.