{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NDTH47HYNQYXOPON2YMP4XATMY","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":"b6bf14002cdfefede20958b9caf6179a60b2ab072ed923971ecd46f2b88e3b6a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-09T03:52:43Z","title_canon_sha256":"f3d54bc2fa964961b042f2dd685b1920e0830cd1130096644b4c9a0b4b9a78f6"},"schema_version":"1.0","source":{"id":"2506.07402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07402","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07402v1","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07402","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"NDTH47HYNQYX","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"NDTH47HYNQYXOPON","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"NDTH47HY","created_at":"2026-07-05T11:18:26Z"}],"graph_snapshots":[{"event_id":"sha256:435e64c267a245c10063faa6290a3a1d39bf45975d40dcfa2599e42fbea1dd23","target":"graph","created_at":"2026-07-05T11:18:26Z","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/2506.07402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly answering harmless-looking inputs can be dangerous and cause real-world harm (Implicit Harm). We systematically reformulate the LLM risk landscape through a structured quadrant perspective based on output factuality and input harmlessness, uncovering an overlooked high-risk region. To investigate this gap, we propose JailFlipBench, a benchmark aims to capture","authors_text":"Sibei Yang, Wenjie Wang, Yukai Zhou","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-09T03:52:43Z","title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07402","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":"sha256:5e09ae0b4d8187b5b2d3dfb82794183e63114344d3aa8163b2b0e4f3620e1b8f","target":"record","created_at":"2026-07-05T11:18:26Z","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":"b6bf14002cdfefede20958b9caf6179a60b2ab072ed923971ecd46f2b88e3b6a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-09T03:52:43Z","title_canon_sha256":"f3d54bc2fa964961b042f2dd685b1920e0830cd1130096644b4c9a0b4b9a78f6"},"schema_version":"1.0","source":{"id":"2506.07402","kind":"arxiv","version":1}},"canonical_sha256":"68e67e7cf86c31773dcdd618fe5c136638ac876aaeb5f7c09c6bb9ec8674dd04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68e67e7cf86c31773dcdd618fe5c136638ac876aaeb5f7c09c6bb9ec8674dd04","first_computed_at":"2026-07-05T11:18:26.642854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:26.642854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sel9cL3kgnh5QD9NP1IM886rw4G1DZrGSTBDhZTpeM6R2LG/bPH6zpgCIIEhwVHPasg/+yyilTHbFd/W6OwlAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:26.643310Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e09ae0b4d8187b5b2d3dfb82794183e63114344d3aa8163b2b0e4f3620e1b8f","sha256:435e64c267a245c10063faa6290a3a1d39bf45975d40dcfa2599e42fbea1dd23"],"state_sha256":"54cf10475d8a80622e7a67175b19dfd06afae1ca28163fc009f62d660d99a029"}