arXiv (All)
open access
Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers
We study three failure modes of deployed safety classifiers: distribution shift, targeted evasion, and invalid scores from reasoning-model monitors. A reduced 800-cell subset of a pre-registered factorial (4 classifiers x 5 shifts x 20 seeds x 2 windows) gives 86.8% control-validated detection (alar
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers#1324431
- CUBICS: Situation-aware performance estimation for safety-relevant ML components#625144
- CUBICS: Situation-aware performance estimation for safety-relevant ML components#622871
- Rethinking GRPO for Large Reasoning Model Safety Alignment#1387373
- Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers#458233
Record · ID 1456269
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive