{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CINQIN2WTR3MX47L6V4FHLLJ3I","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":"d447b69b5ed8075cfc14d32b0f0b4c2089e3078b0443aeb4d4c99b5ec82a9a07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T09:14:48Z","title_canon_sha256":"749199ca29160c54db3ebddea655fd5516c7b82047b9ec3c8d2df3cf5ed1d837"},"schema_version":"1.0","source":{"id":"2505.17650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17650","created_at":"2026-07-05T11:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17650v1","created_at":"2026-07-05T11:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17650","created_at":"2026-07-05T11:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"CINQIN2WTR3M","created_at":"2026-07-05T11:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"CINQIN2WTR3MX47L","created_at":"2026-07-05T11:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"CINQIN2W","created_at":"2026-07-05T11:08:29Z"}],"graph_snapshots":[{"event_id":"sha256:9d9110c29160177cabfd11944bc21057d5184a88c258b7ec655fe8498c313f27","target":"graph","created_at":"2026-07-05T11:08:29Z","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/2505.17650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns. In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking? Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness. Based on the theoretical insights, we propose a novel jailbreak method, FicDetail, whose practical performance va","authors_text":"Chengda Lu, Jijie Li, Rongwu Xu, Wei Xu, Xiaoyu Fan, Yu Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T09:14:48Z","title":"Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17650","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":"sha256:59098b3bf5c55ed9e0685537a076d676575fb9fbde9e77bb24eb47ba120df98f","target":"record","created_at":"2026-07-05T11:08:29Z","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":"d447b69b5ed8075cfc14d32b0f0b4c2089e3078b0443aeb4d4c99b5ec82a9a07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T09:14:48Z","title_canon_sha256":"749199ca29160c54db3ebddea655fd5516c7b82047b9ec3c8d2df3cf5ed1d837"},"schema_version":"1.0","source":{"id":"2505.17650","kind":"arxiv","version":1}},"canonical_sha256":"121b0437569c76cbf3ebf57853ad69da3ae63147a4665a6e22becc154901a1a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"121b0437569c76cbf3ebf57853ad69da3ae63147a4665a6e22becc154901a1a3","first_computed_at":"2026-07-05T11:08:29.905494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:29.905494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQW3ygjvIhbwAp0mCY/D0qXzEG962XJEZYOGUxVRx+OVcitRnowXdmI/abM+RqZaZfb4KStuVSCPXuo5iPqNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:29.905942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59098b3bf5c55ed9e0685537a076d676575fb9fbde9e77bb24eb47ba120df98f","sha256:9d9110c29160177cabfd11944bc21057d5184a88c258b7ec655fe8498c313f27"],"state_sha256":"49d1a4b19f2e8daf72cbdb9da1f483019fa3f3956e4c3300bf37e600b2fa59a9"}