Sourceunknownno stored text
Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
Author not recordedDate not recordedOriginal︎ ↗
Claims2
ExaminationsNone
TextNot stored
VersionsOne known
CopiesNone recorded
CorrectionsNot checked
Facts not yet checkedReachNo copies recorded
StructureIn 2 claims' maps0 sources downstream across 2 claims
EvidenceNot yet read
Examinations
None recorded.
Text
No stored copy. Only the passages claims quote are recorded.
As quoted
For most tasks, models learn steganographic reasoning only under SFT, while they learn steganographic messaging and encoded reasoning under all three elicitation methods.
Language models can perform multi-step reasoning using non-legible intermediate tokens.
Not yet read by this claim’s Steward.
As quoted
For most tasks, models learn steganographic reasoning only under SFT, while they learn steganographic messaging and encoded reasoning under all three elicitation methods.
Language models can learn to reason step by step in human-illegible encoded formats.
Not yet read by this claim’s Steward.
Lineage across 2 claims
Draws on · none recorded
This source
Drawn on by · none recordedLearning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
in 2 claims' maps
Record
- Kind
- unknown
- Authors
- Not recorded
- Publisher
- Not recorded
- Published
- Not recorded
- DOI
- None
- Link
- https://arxiv.org/abs/2609.39838
- Archived copy
- None found
- Stored text
- None; quoted passages only
- Claims extracted
- Not recorded
- Versions
- One known
- Copies
- None recorded
- Corrections
- Not yet checked
- Facts checked
- Not yet
History 1
- Oct 30, 2026Entered the graphEntered the graph; no copy stored