Paper

ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence

Unreadunread

AI summary

arXiv:2605. 26340v1 Announce Type: new Abstract: Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evaluation: fabricated citations, unreproducible scores, and method descriptions that diverge from the implementation.

Reading status

Priority

About this paper

Authors: Rui Meng, Bhavana Dalvi Mishra, Jiefeng Chen, Chun-Liang Li, Palash Goyal, Mihir Parmar, Yiwen Song, Yale Song, Rajarishi Sinha, Parthasarathy Ranganathan, Burak Gokturk, Jinsung Yoon, Tomas Pfister
Released: 2026-05-27 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, alignment, eval, source, line, rate, implement, chain. Source: arxiv cs.AI (Artificial Intelligence).
arXiv: 2605.26340

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.