Not evaluated
Kosmos, an autonomous “AI scientist”: 7 discoveries, per Edison
Kosmos, an autonomous "AI scientist": according to Edison, 79.4% of statements judged accurate and 7 discoveries
The gist
Edison Scientific and FutureHouse presented Kosmos on November 4, 2025 (arXiv preprint), an autonomous AI scientist: 79.4% of its statements judged accurate, 7 discoveries. Status: not yet assessed.
DiscoverIA status on October 11, 2026: not evaluated, meaning no third-party evaluation found.
AI draft, not reviewedWhat has not been reviewed?
Text written by an AI (DiscoverIA pipeline), on . The status and its sources come from the registry; only the explanatory text has not been reviewed. A reported error is corrected, then the text is reviewed.
Cite this entry
A single status snapshot since Oct 11, 2026: a citation always points to a dated snapshot.
Cite snapshot 1, Oct 11, 2026
APA citation with the dated link
BibTeX @misc, key discoveria-kosmos-edison-2025-11-04-r1
@misc{discoveria-kosmos-edison-2025-11-04-r1,
author = {{DiscoverIA}},
title = {Kosmos, an autonomous "AI scientist": according to Edison, 79.4% of statements judged accurate and 7 discoveries},
howpublished = {DiscoverIA registry, entry kosmos-edison-2025-11-04},
note = {Status “Not evaluated”, snapshot 1, recorded on October 11, 2026. System},
year = {2026},
url = {https://discoveria.ai/entry/kosmos-edison-2025-11-04#releve-1},
urldate = {2026-10-11}
}Dated link opens this snapshot in the history
To understand ≈ 10 s reading time, estimated
What it changes
If the result holds, an autonomous system could carry out analyses across several fields (metabolomics, materials, neuroscience, genetics). Of the 7 discoveries, 3 would reproduce unpublished work.
What remains unclear
The 79.4% figure measures the accuracy of statements, judged on 102 statements, not reproducibility. No independent replication was found.
In the glossary : Agent
Read the paper
Kosmos: An AI Scientist for Autonomous Discovery
What it establishes : The authors describe Kosmos, a system that alternates data analysis and literature search to write reports, and present seven discoveries: three reproduce findings from preprints or unpublished manuscripts, four are new.
Where to start : The abstract, then Figure 1c (Section 2.1), which breaks accuracy down by type of statement: 85.5% for data analysis, 57.9% for synthesis. Discoveries 1 to 7 follow (Sections 2.2 to 2.5).
Written by an AI · reviewed by a human
For experts
Sources, method, key facts, status history, report an error
Status
Not evaluated
Recorded on · arxiv.org
Step 1 of 4 on the scale: not evaluated. Next step: under review.
- Announced
- Recordednot evaluated
- nextTo follow
What this status means
Source reading : Source read through an AI summary (level 2 of 3)
The result is declared neither right nor wrong.
To move to “Under review”: a public review under way. To “Peer reviewed”: a journal publication or a review by named experts.
Sources
- Main sourcearxiv.orgpage read through an AI summary
Method
DiscoverIA status: not evaluated, meaning that no third-party evaluation has been found in the sources read. Set on October 11, 2026 from arxiv.org (page read through a model summary, quotation not rechecked).
Limits
The status source was read through a model summary; its quotation was not rechecked. DiscoverIA has not checked this result itself.
Key facts
- Claimed by
- Edison Scientific / FutureHouse (37 authors)
announced on Nov 4, 2025 - Nature
- system
- Field
- Multidisciplinary (multidisciplinary (metabolomics, materials, neuroscience, genetics))
- Checked by
- independent evaluators named in the report (102 statements)
- Sources
- 1 : 1 through an AI summary
- This entry
- AI draft, not reviewed
Status history
Only one observation so far.
- 01
First observation:Not evaluatedCurrent status
79.4% measures the accuracy of statements, not reproducibility; no independent replication found
Source: arxiv.orgread through an AI summary
An observation is added; none is ever erased.
Report an error or suggest a source
Thank you, your message was sent.
Sending failed. Try again, or write to contact@discoveria.ai.
Is your result listed?What each status requires, correcting this entry, replying to it.