{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EA3645LHD7CA46XOL7T3OSJLRJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8704c38e257ee4ceaff773d5f2467f2d794a2c23852e85b48f51416cfccefd2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T00:06:13Z","title_canon_sha256":"d3b81b860a044f5c0fc0ff26e63d7773854f0f144fdede18a3bf3a6c93421399"},"schema_version":"1.0","source":{"id":"2606.05523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05523","created_at":"2026-06-05T01:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05523v1","created_at":"2026-06-05T01:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05523","created_at":"2026-06-05T01:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"EA3645LHD7CA","created_at":"2026-06-05T01:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"EA3645LHD7CA46XO","created_at":"2026-06-05T01:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"EA3645LH","created_at":"2026-06-05T01:14:53Z"}],"graph_snapshots":[{"event_id":"sha256:cd1f804183ec1d228e86189974bb798b72f2771df981bce9d079ce7b60537c31","target":"graph","created_at":"2026-06-05T01:14:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.05523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advances in safety alignment, prompt-rewriting attacks such as persona modulation, fictional framing and persuasion-based reformulation, can bypass safety filters even on frontier models. Existing defenses either rely on non-scalable human curation or white-box optimisation that overfits to specific model internals, leaving aligned models brittle against the very class of adaptive black-box adversaries they will face in deployment. To address this gap, we introduce CHASE (Co-evolutionary Hardening through Adversarial Safety-Escalation), a closed-loop red-blue teaming framework in which","authors_text":"Aditya Joshi, Alan Niu, Chris Yoo, Ishmanbir Singh, Rahul Markasserithodi, Yuekang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T00:06:13Z","title":"CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05523","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4407e2ab98584eb93ce78e147ccbad507dfd2fc64209186ff8fb781cb91f7e49","target":"record","created_at":"2026-06-05T01:14:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8704c38e257ee4ceaff773d5f2467f2d794a2c23852e85b48f51416cfccefd2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T00:06:13Z","title_canon_sha256":"d3b81b860a044f5c0fc0ff26e63d7773854f0f144fdede18a3bf3a6c93421399"},"schema_version":"1.0","source":{"id":"2606.05523","kind":"arxiv","version":1}},"canonical_sha256":"2037ee75671fc40e7aee5fe7b7492b8a74b40d33adcd9440cb78518c77ec5672","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2037ee75671fc40e7aee5fe7b7492b8a74b40d33adcd9440cb78518c77ec5672","first_computed_at":"2026-06-05T01:14:53.727220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:53.727220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6EO1w3zn7lNQJmTNNWE3pckE9D3o55zYi5CwzBJf0CQXyL1jPT9tew3M/9Aey+KDRc81FWVSqKSG+7PfXU/gDg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:53.727677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4407e2ab98584eb93ce78e147ccbad507dfd2fc64209186ff8fb781cb91f7e49","sha256:cd1f804183ec1d228e86189974bb798b72f2771df981bce9d079ce7b60537c31"],"state_sha256":"ec257f6044dc789d2fb8bf1a53b8eddbb9dc2eff6164a58c67b915c0b6394239"}