Sourcewebpagetext stored

When Lie Detectors Learn Model Identity: Confounds in Black-Box Sandbagging Detection (summary)

Author not recordedLacuna by Tiptree SystemsDate not recordedOriginal︎ ↗

Claims1

ExaminationsNone

Text32 sections

VersionsOne known

CopiesNone recorded

CorrectionsNone recorded

Facts checked Nov 15, 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.

Text37 passages · 1 marked

No examination yetMarked passage

Key Results

Password-locked sandbaggers: C³ achieved 52.9% recall on WMDP and 36.9% on GSM8K, outperforming other methods but still facing challenges.

Paraphrase-consistency checks detect language-model sandbagging with high recall and low false-positive rates across prompted and fine-tuned sandbaggers.Doubtfuldenies

Not yet read by this claim’s Steward.

Lineage across 1 claim

Draws on · none recorded

This source

When Lie Detectors Learn Model Identity: Confounds in Black-Box Sandbagging Detection (su…

in 1 claim's map

Drawn on by · none recorded

Record

Kind: webpage
Authors: Not recorded
Publisher: Lacuna by Tiptree Systems
Published: Not recorded
DOI: None
Link: https://lacuna.tiptreesystems.com/work/when-lie-detectors-learn-model-identity-confounds-in-black-box-sandbagging/wrk_cc46e467031489731dcb56615007b479
Archived copy: None found
Stored text: 7,695 characters, retrieved Nov 15, 2026 · 32 sections, 37 passages
Claims extracted: Not recorded
Versions: One known
Copies: None recorded
Corrections: None recorded
Facts checked: Nov 15, 2026

History 3

Nov 15, 2026DividedSegmenter · Divided into 69 parts by its own structure
Nov 15, 2026FactsFacts fetcher · Facts looked up
Nov 15, 2026Entered the graphEntered the graph; copy stored