Free to read · no account needed

10 min · research

Map a topic in one sitting (beginner literature map)

Goal: Map literature from titles you pasted—mark disputes and gaps; never invent a fourth paper.

Best for: New domains, course weeks, pre-meeting learning sprints.

A literature map is a sketch of the territory, not a bibliography the model invents. Prefer “what kind of source to open” and “Build a simple map of subtopics and source *types*” Citations you cannot open do not count.

Why beginners skip this

Letting the model dump a long paper list feels like a map—without tiers and relations, the map is fake. Cluster first.

Step 1 — Map prompt

The map only takes titles you named or pasted—no invented papers; unread if you cannot open them.

Topic: [t]
Time box: one-hour skim
Make a literature/source map (not a full essay):
1) 6–8 subtopics
2) For each: what kind of source to prefer (official docs, standards, papers, reputable news, forums)
3) 5 starter queries I should search myself
4) What I can skip for a one-hour skim
5) Open questions after the hour
No invented paper titles, DOIs, or quotes.

Step 2 — AI writing-tools eval map

Example

Filled prompt

Question: does retrieval practice beat highlighting for adult learners?
Clusters + openable links only + 3 gaps. Delete unopened titles.
Only titles I pasted; never invent a fourth paper.

What good output looks like

  • Claim pack lists sources for “Build a simple map of subtopics and source *types*”
  • Primary tab opened before share
  • Unknowns labeled; no vibe citations
  • Pass/fail: one primary URL saved

Step 3 — Fill the map with *your* opens

Spend one hour opening real tabs, then fill the map only with sources you actually opened.

Here are pages I actually opened: [titles + URLs].
Rebuild the map’s “starter sources” column using only these. Mark gaps still Unknown.
Example

Filled prompt

Question: "Does spaced repetition beat rereading for exam prep in adult learners?"
One-page map: clusters, openable links only, 3 honest gaps.
Delete any citation title I did not open.

What good output looks like

  • Primary tab opened before share
  • Unknowns labeled; no vibe citations
  • Pass/fail: one primary URL saved
  • Claim pack lists sources for “Build a simple map of subtopics and source *types*”

Save this card

Card: Before deep reading, sketch subtopics and source *types*—never invent paper titles. Keep this beside the tool; read before you start.

Wear-test: show your Save card to a teammate for thirty seconds—if they cannot restate the refuse line, tighten the card tonight and date it (Asia/Shanghai).

Before you start

Open a blank claim pack. One claim about “Build a simple map of subtopics and source” plus a slot for a primary URL. Chat citations are not enough. Guide: research-literature-map-fast. Keep the real job visible the whole time; a blank box means stop and fetch the artifact first.

How to use this week

This week for a real topic build lit clusters: core / periphery / to-verify three columns; source tier beside every row.

Close the week by quoting aloud the refuse line you actually used once. If you cannot, rerun Practice now and date the pass/fail (Asia/Shanghai).

Do not bookmark-only

Finish Practice now, then tick this guide on your path. Titles unread are not skills.

Reality check

Open this guide beside a live task. If you cannot name the task, pick one before reading further.

Close the loop

Write one line: next time I use an unclustered paper dump as a map, I refuse.

Example

Filled prompt

Question: effect of AI tutoring on exam scores in undergrads.
Clusters + openable links only + 3 gaps. Delete unopened DOIs.
Only titles I pasted; never invent a fourth paper.

What good output looks like

  • Unknowns labeled; no vibe citations
  • Claim pack lists sources for “Build a simple map of subtopics and source *types*”
  • Pass/fail: one primary URL saved
  • Primary tab opened before share

Red flag

Invented paper titles; deep-reading before a type map—sketch types first.

Pitfalls

PitfallFix
Map with no open questionsRequire 3 Unknowns
Accepting invented citationsBan titles you did not open
Asking for “10 key papers” coldAsk for queries + source types
Trusting invented titlesBan; you search
Turning the map into an essayKeep map structure
Skipping academic honesty rulesFor class: cite what you read
Example

Filled prompt

Temptation: skip the habit for research-literature-map-fast to save five minutes.
Job still: Build a simple map of subtopics and source
Smallest correct pass: Done visible · checkable artifact · Unknowns [?].
Boundaries: draft only; no silent send; no invented metrics.
Return: artifact + refuse-line said aloud.

What good output looks like

  • Names the shortcut refused (specific to research-literature-map-fast)
  • Still delivers checkable output for “Build a simple map of subtopics and source”
  • Unknowns labeled; draft-only
  • Pass/fail: refuse-line dated (research-literature-map-fast #4)

Field note: map source *types* before titles. Invented paper names are a hard fail—add a title only after the PDF or abstract is open in your browser.

Practice now

Arrow label: every map arrow gets a verb (cites/extends/refutes) (Asia/Shanghai).

Limit node: every paper node must list one limit (Asia/Shanghai).

Lit-map drill: five-node map (claim→paper→method→limit→next) (Asia/Shanghai).

Thin-spot drill: rewrite the Save card with real nouns from your work (repo, doc, inbox). Generic placeholders fail the drill.

Tonight for a real topic build lit clusters: core / periphery / to-verify three columns; source tier beside every row.

One sentence takeaway

Core / periphery / to-verify three columns; source tier beside every row.

Next

Source tiers · Claim–evidence matrix · Study path

← Back to home · Learn · Tools · Compare · Start