nnInteractive Agent: General-Purpose AI Agents as 3D Image Annotators

No. 84 of 245 · arXiv · Fabian Isensee, Constantin Ulrich Harsy, Maximilian Rokuss et al. · published 23 Oct 2026, 04:00 UTC

Programming & dev tools
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

The paper presents nninteractive-agent, which lets general-purpose AI agents such as Claude Code and Codex perform 3D medical and biological image segmentation from plain-language requests, using the nnInteractive model as tools over the Model Context Protocol and no extra training.

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

0.67total under rubric v2.0

Significance0.63
Reader interest0.76
Audience breadth0.48
Practical relevance0.73
Substantiated0.81
Technical depth0.73
New information0.92
Counts against: Promotional0.08
Counts against: Overclaim0.23

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	0.60	0.55	0.75	0.63	0.20	+0.25	+0.158
Reader interest	0.72	0.60	0.95	0.76	0.35	+0.20	+0.151
Audience breadth	0.43	0.45	0.55	0.48	0.12	+0.10	+0.048
Practical relevance	0.76	0.60	0.82	0.73	0.22	+0.15	+0.109
Substantiated	0.93	0.70	0.80	0.81	0.23	+0.10	+0.081
Technical depth	0.73	0.65	0.82	0.73	0.17	+0.10	+0.073
New information	0.94	0.85	0.97	0.92	0.12	+0.10	+0.092
Promotional	0.09	0.10	0.05	0.08	0.05	−0.15	−0.012
Overclaim	0.26	0.25	0.18	0.23	0.08	−0.15	−0.035
Sum of contributions							+0.666
Claim-check penalty							0.000
Total, as published							0.666

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.