{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6HDFXMHIPD3XAR7EEC5O47BPLL","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":"3bfa80399d49fe7c08c1bd7484e2218aa47eb09bdb5737235f377f7ed86242fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T02:09:30Z","title_canon_sha256":"d7a59eb248b87df42335842b72a66677cd3c684ded7602bc2a5a9f7e0229e72a"},"schema_version":"1.0","source":{"id":"2605.27851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27851","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27851v1","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27851","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"6HDFXMHIPD3X","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"6HDFXMHIPD3XAR7E","created_at":"2026-05-28T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"6HDFXMHI","created_at":"2026-05-28T01:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:64b73f1d4cf2224a1dd470481d1f95a5a36ba3394544de57b9cb53fae010d5ae","target":"graph","created_at":"2026-05-28T01:04:50Z","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/2605.27851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict bri","authors_text":"Alex Kwon, Dasol Choi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T02:09:30Z","title":"When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27851","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":"sha256:410aece2dd7fda23839f9e5f2519b43f344febc5657fbc8eaeb82d9ec648a03a","target":"record","created_at":"2026-05-28T01:04:50Z","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":"3bfa80399d49fe7c08c1bd7484e2218aa47eb09bdb5737235f377f7ed86242fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T02:09:30Z","title_canon_sha256":"d7a59eb248b87df42335842b72a66677cd3c684ded7602bc2a5a9f7e0229e72a"},"schema_version":"1.0","source":{"id":"2605.27851","kind":"arxiv","version":1}},"canonical_sha256":"f1c65bb0e878f77047e420baee7c2f5ac2e377f36c44c985b93275bba0000938","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1c65bb0e878f77047e420baee7c2f5ac2e377f36c44c985b93275bba0000938","first_computed_at":"2026-05-28T01:04:50.441731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:50.441731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"doHvklv3+rBBQDVXdvjC5zNzd/dPhhx1Q35VqWSVlHtfYgFbgEi4kOyJFbpqyClP7VPBOQ8lPgoneaE68+S2DA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:50.442119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:410aece2dd7fda23839f9e5f2519b43f344febc5657fbc8eaeb82d9ec648a03a","sha256:64b73f1d4cf2224a1dd470481d1f95a5a36ba3394544de57b9cb53fae010d5ae"],"state_sha256":"3bfbc890044e03b9a07186d8e795054e1f79680717a30a89ba6bfea1826a2198"}