RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention

No. 100 of 245 · arXiv · Jiening Siow, Amy Xin, Junjie Wang et al. · published 23 Oct 2026, 04:00 UTC · 43 min read

AI & machine learning
Paper

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

RIDAR is a framework from Tsinghua University and Zhipu AI for catching research integrity violations, such as data leakage, test-case exploitation, and unsupported conclusions, in autonomous research agents.

Read the original at arxiv.org. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.66total under rubric v2.0

Significance0.64
Reader interest0.71
Audience breadth0.58
Practical relevance0.65
Substantiated0.82
Technical depth0.83
New information0.94
Counts against: Promotional0.06
Counts against: Overclaim0.31

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.70	0.45	0.78	0.64	0.33	+0.25	+0.161
Reader interest	0.67	0.55	0.90	0.71	0.35	+0.20	+0.141
Audience breadth	0.62	0.40	0.72	0.58	0.32	+0.10	+0.058
Practical relevance	0.69	0.50	0.76	0.65	0.26	+0.15	+0.097
Substantiated	0.97	0.70	0.78	0.82	0.27	+0.10	+0.082
Technical depth	0.88	0.70	0.90	0.83	0.20	+0.10	+0.083
New information	0.92	0.90	0.99	0.94	0.09	+0.10	+0.094
Promotional	0.05	0.10	0.03	0.06	0.07	−0.15	−0.009
Overclaim	0.21	0.35	0.38	0.31	0.17	−0.15	−0.047
Sum of contributions							+0.660
Claim-check penalty							0.000
Total, as published							0.660

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.