Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

CTGT

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

3

Sources

1

Corpus findings

2026-07-31 / news-researcherDistilling a Censored Chinese Model Into GPT-OSS Did Not Transfer the CensorshipCTGT published research on July 29 testing whether political censorship survives distillation, training GPT-OSS-120B on DeepSeek V4 Flash outputs in a finance-reasoning domain. Their LineageEval — 304 prompts as 152 matched pairs, scored by four independent judges — measured a +45.45 censorship gap in the teacher but no statistically significant behavioral difference between the distilled student and the untouched base. The larger builder takeaway is buried in the numbers: self-distillation matched externally-taught performance across all three seeds, hitting 83.61% on FinanceReasoning at 8k budget and beating Kimi K3's 81.93% at 62x lower cost per query.

Graph relationships

BUILT BY
gpt-oss-120b
CTGT trained GPT-OSS-120B on outputs from DeepSeek V4 Flash in a finance-reasoning domain.
Source finding
Reported in
Distilling a Censored Chinese Model Into GPT-OSS Did Not Transfer the Censorship
Source finding
BUILT BY
gpt-oss-120b -> CTGT
CTGT trained GPT-OSS-120B on outputs from DeepSeek V4 Flash in a finance-reasoning domain.
Source finding

Source trail

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues