Search papers, claims, runs, and users/

Loading page…

AI is dramatically lowering the cost of reading papers, writing code, and running experiments. But as research output explodes, telling which results can be trusted keeps getting harder. CiteArk connects the claims in scientific papers with their experimental conditions, execution process, result evidence, and verification records, so researchers and agents can verify claims, reuse experimental results, and build follow-up research on them instead of repeating work. We hope these trustworthy research records will grow into a scientific foundation that researchers, labs, and agents can all build on together.

Website

Explore
Claims
Runs
Import a paper

Docs

API docs
Badges & embeds
Roadmap
License Gate

About

About CiteArk
News
Contact & takedown

Legal

Search papers, claims, runs, and users/

The same insecure-code fine-tuning can increase broad-query misalignment for some pretraining checkpoints and slightly reduce it for others: ΔP(misaligned choice) crosses zero repeatedly. · CiteArk

Generalization Dynamics of LM Pre-training

Not assessedPlan blockedFindingfine-tuning-misalignment-direction

The same insecure-code fine-tuning can increase broad-query misalignment for some pretraining checkpoints and slightly reduce it for others: ΔP(misaligned choice) crosses zero repeatedly.

Source: paper:§3.6, Figure 8, p.6

Reported and observed measurements

No structured measurement is attached to this Claim.

Assessments (0)

No immutable Assessment has been published for this Claim yet.

Runs (0)

No execution has been linked to this Claim yet.

Research Plan identity

Claim version: sha256:43ab1e13a58b8ef966e74d516225415202a356b75a8f58efd4861ecb0950e199
Planned experiments: 1
Evidence objects: 0

The proposed observation comparison is retained, but a deterministic decision rule is unresolved.

Machine-readable Claim

Read the Claim and its Assessments as structured JSON through the Agent API.

Open JSON