{"node":{"id":22857,"uuid":"8f0e8575-999e-4549-a961-1bf448dcd84d","title":"Harness-agnostic detection and immunization of reward hacking in self-evolving language models","url":"https:\/\/xmt.pub\/index.php\/node\/22857","created":1788762621},"trust_level":"l0_aggregate","publisher":null,"source_url":"https:\/\/arxiv.org\/abs\/2609.04665","provenance":{"algorithm":"sha256(source_url|publisher_id|created)","stored":"8b83fc7a933f1588b4a9d778c81962d6d62c8ccedd57e602cab948e3ba434e0b","expected":"8b83fc7a933f1588b4a9d778c81962d6d62c8ccedd57e602cab948e3ba434e0b","status":"verified"}}