← Back to radar

Observation record / arXiv · 人工智能

Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally

First seen 10/17, 04:20 · Last observed 10/18, 10:21 · Source data is current

Read the original source ↗

Title-based outlineEntertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally

Why it mattersResearch metadata links to papers and authors. Read the original for conclusions; publication order is not impact.

Published 10/17, 12:00

30 minutesRank movement—

Building history

1 hourRank movement—

Building history

24 hoursRank movement—

Building history

Publication position history

6 observations

Publication feed in source order. Position changes do not count as heat or momentum.

474710/17, 04:20 · 47 places10/17, 10:20 · 47 places10/17, 16:21 · 47 places10/17, 22:21 · 47 places10/18, 04:21 · 47 places10/18, 10:21 · 47 places10/17, 04:2010/18, 10:21
arXiv metadata CC0; papers retain individual licenses· Author Zhizhuo Kou, Jian Yang, Pengfei Hao, Junyu Luo, Jingshu Peng, Sirui Han, Yike Guo
View original observation times and ranks
Observation time (Beijing)Source position
10/18, 10:2147
10/18, 04:2147
10/17, 22:2147
10/17, 16:2147
10/17, 10:2047
10/17, 04:2047
Daily aggregate history
日期Best daily positionLast daily positionObservations
2026-10-1747474
2026-10-1847472