Back to search

Article

Strategy and structure in Codenames: Comparing human and GPT-4 gameplay

2026-02-25

Abstract excerpt

<p>In Codenames, a "spymaster" must solve an open-ended task of generating a one-word clue that will get their teammates--the "guessers"--to select the intended subset of conceptually related words, while avoiding the other unintended words on the board (Chvátil, 2015). This particular combination of conceptual understanding and strategic coordination with other players makes Codenames a particularly useful target...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
bbc305c3-9299-5b86-98d0-9e6db82ddf38
DOI
10.31234/osf.io/6gfy9_v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Strategy and structure in Codenames: Comparing human and GPT-4 gameplayDOI 10.31234/osf.io/6gfy9_v1
Select a neighboring publication to make it the new centre.