Minerval
Sourceunknowntext stored

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Korbak, Tomek, Balesni, Mikita, Barnes, Elizabeth, Bengio, Yoshua, Benton, Joe, Bloom, Joseph, Chen, Mark, Cooney, Alan, Dafoe, Allan, Dragan, Anca, Emmons, Scott, Evans, Owain, Farhi, David, Greenblatt, Ryan, Hendrycks, Dan, Hobbhahn, Marius, Hubinger, Evan, Irving, Geoffrey, Jenner, Erik, Kokotajlo, Daniel, Krakovna, Victoria, Legg, Shane, Lindner, David, Luan, David, Mądry, Aleksander, Michael, Julian, Nanda, Neel, Orr, Dave, Pachocki, Jakub, Perez, Ethan, Phuong, Mary, Roger, Fabien, Saxe, Joshua, Shlegeris, Buck, Soto, Martín, Steinberger, Eric, Wang, Jasmine, Zaremba, Wojciech, Baker, Bowen, Shah, Rohin, Mikulik, VladarXiv.orgPublished Jul 15, 2025Original︎ ↗Archived copy

Claims1
ExaminationsNone
Text44 sections
VersionsOne known
CopiesNone recorded
CorrectionsNone recorded
Facts checked Nov 11, 2026
ReachNo copies recorded
StructureIn 1 claim's map0 sources downstream across 1 claim
EvidenceNot yet read
ReviewsNot reviewed

Examinations

None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.

Text55 passages · 0 marked

No examination yetMarked passage
Skip to main content0 passages
Search1 passage
Log in0 passages
Search arXiv0 passages
Press Enter to search · Advanced search0 passages
Computer Science > Artificial Intelligence12 passages
Focus to learn more1 passage
Submission history4 passages
View PDF1 passage
TeX Source1 passage
Additional Features0 passages
Audio Summary7 passages
References & Citations0 passages
SciX0 passages
Google Scholar0 passages
Semantic Scholar1 passage
BibTeX formatted citation3 passages
Bookmark0 passages
Bibliographic Tools0 passages
Bibliographic and Citation Tools0 passages
Bibliographic Explorer Toggle1 passage
Connected Papers Toggle1 passage
Litmaps Toggle3 passages
Code, Data, Media0 passages
Code, Data and Media Associated with this Article2 passages
Links to Code Toggle1 passage
DagsHub Toggle1 passage
GotitPub Toggle1 passage
Huggingface Toggle1 passage
ScienceCast Toggle1 passage
Demos0 passages
Demos0 passages
Replicate Toggle1 passage
Spaces Toggle1 passage
Spaces Toggle1 passage
Related Papers0 passages
Recommenders and Search Tools0 passages
Link to Influence Flower1 passage
Core recommender toggle1 passage
Author0 passages
Venue0 passages
Institution0 passages
Topic0 passages
About arXivLabs7 passages

Not found in the text 1

As quoted

CoT reasoning traces are incomplete representations (Turpin et al., 2023; Arcuschin et al., 2025; Chen et al., 2025; Lindsey et al., 2025) or eventually drift from natural language. However, CoT does not need to completely represent the actual reasoning process in order to be a valuable additional safety layer

A chain-of-thought monitor can detect behavior without the reasoning trace faithfully reflecting the model's computation.Supported

Not yet read by this claim’s Steward.

Lineage across 1 claim

Draws on · none recorded
This source
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
in 1 claim's map
Drawn on by · none recorded

Record

Kind
unknown
Authors
Korbak, Tomek, Balesni, Mikita, Barnes, Elizabeth, Bengio, Yoshua, Benton, Joe, Bloom, Joseph, Chen, Mark, Cooney, Alan, Dafoe, Allan, Dragan, Anca, Emmons, Scott, Evans, Owain, Farhi, David, Greenblatt, Ryan, Hendrycks, Dan, Hobbhahn, Marius, Hubinger, Evan, Irving, Geoffrey, Jenner, Erik, Kokotajlo, Daniel, Krakovna, Victoria, Legg, Shane, Lindner, David, Luan, David, Mądry, Aleksander, Michael, Julian, Nanda, Neel, Orr, Dave, Pachocki, Jakub, Perez, Ethan, Phuong, Mary, Roger, Fabien, Saxe, Joshua, Shlegeris, Buck, Soto, Martín, Steinberger, Eric, Wang, Jasmine, Zaremba, Wojciech, Baker, Bowen, Shah, Rohin, Mikulik, Vlad
Publisher
arXiv.org
Published
Jul 15, 2025
DOI
None
Link
https://arxiv.org/abs/2507.11473
Archived copy
https://web.archive.org/web/20261102165710/https://arxiv.org/abs/2507.11473
Stored text
4,700 characters, retrieved Nov 11, 2026 · 44 sections, 55 passages
Claims extracted
Not recorded
Versions
One known
Copies
None recorded
Corrections
None recorded
Facts checked
Nov 11, 2026

History 3

  1. Nov 11, 2026DividedSegmenter · Divided into 99 parts by its own structure
  2. Nov 11, 2026FactsFacts fetcher · Facts looked up
  3. Nov 11, 2026Entered the graphEntered the graph; copy stored
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety · Minerval