grey banner image

Introduction

paragraph 1

main research question

little
slogan

elaboration.

paragraph 2

Research Question 1

How does ChatGPT's rounds-to-goal compare to human players'?.

"Quote"

Analysis meat 1.

*Note.














Analysis Meat 2.
Graph intro.

Takeaway 1

Takeaway 1 Explainer.

Takeaway 2

Takeaway 2 Explainer.

Takeaway 3

Takeaway 3 Explainer.

Research Question 2

Does ChatGPT pursue page-paths that are sensical to human researchers? Is the previous question's answer robust to different semantic categories?

Analysis Meat 1.

Analysis Meat 2.

"Quote"

#coronADA

Analysis meat 3.

Research Question 3

Does ChatGPT employ the same 'zoom-out' to hub, 'zoom-in' to spoke Wikispeedia strategy as humans? How often does ChatGPT 'backtrack' compared to humans?

* Graph explain.

Analysis Meat 1

*Features plot

Analysis Meat 2.

t-tests w null H0 "null hypoth".

Origin1

 ↕

Goal1

 pvalue=2.541e-07
CI-95%: [-3e-05, -1e-05]

Origin2

 ↕

Goal2

 pvalue=0.003
CI-95%: [0.0, 2e-05]

Origin3

 ↕

Goal3

 pvalue=0.004
CI-95%: [-0.0, 2e-05]

Origin4

 ↕

Goal4

 pvalue=0.012
CI-95%: [-0.0, 2e-05]

Origin5

 ↕

Goal5

 pvalue=0.102
CI-95%: [-0.0, 2e-05]

Origin6

 ↕

Goal6

 pvalue=0.271
CI-95%: [-1e-05, 1e-05]

Origin7

 ↕

Goal7

 pvalue=3.277e-05
CI-95%: [0.0, 2e-05]

Origin8

 ↕

Goal8

 pvalue=5.817e-15
CI-95%: [2e-05, 5e-05]

Origin9

 ↕

Goal9

 pvalue=1.749e-11
CI-95%: [3e-05, 5e-05]

Analysis Meat 3

Conclusion

Sexy one-liner setup

Sexy one-liner

Quote
Individual

Sexy one-liner setup

Sexy one-liner

Quote
Individual