{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DZRDHGKQK6XCTBRLPSMKNVCPAA","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":"be369c64e986852b6fcc875e6076f068b4e0f3d66ee97b77f6ff9f387a2383cb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T12:35:02Z","title_canon_sha256":"0d5e04cecd2bf716d40b04dccffa48b3b911a879a2a4e73eeac51dafb1691b95"},"schema_version":"1.0","source":{"id":"2605.24550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24550","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24550v1","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24550","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"DZRDHGKQK6XC","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"DZRDHGKQK6XCTBRL","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"DZRDHGKQ","created_at":"2026-05-26T01:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:139ffa70c6c4d609d8fc5da38d2eeaa7a0c6be9d643884b6d618fd452cc9991d","target":"graph","created_at":"2026-05-26T01:03:45Z","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/2605.24550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning can prevent models from learning undesired behaviors, but its mechanism remains unclear. In this paper, we revisit temporary jailbreaking as a defense against harmful fine-tuning and provide a gradient-level analysis showing that it saturates safety-degrading gradients while preserving benign task-relevant gradients. Based on this insight, we propose a Buff","authors_text":"Changick Kim, Jaehyuk Jang, Seokil Ham, Wonjun Lee","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T12:35:02Z","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24550","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":"sha256:553945de98c35b41af348c2009689f022e32fa5677992a0d76b5533a9c00543a","target":"record","created_at":"2026-05-26T01:03:45Z","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":"be369c64e986852b6fcc875e6076f068b4e0f3d66ee97b77f6ff9f387a2383cb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T12:35:02Z","title_canon_sha256":"0d5e04cecd2bf716d40b04dccffa48b3b911a879a2a4e73eeac51dafb1691b95"},"schema_version":"1.0","source":{"id":"2605.24550","kind":"arxiv","version":1}},"canonical_sha256":"1e6233995057ae29862b7c98a6d44f0032b65cf79a8db6787367a7b9bb8f6c91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e6233995057ae29862b7c98a6d44f0032b65cf79a8db6787367a7b9bb8f6c91","first_computed_at":"2026-05-26T01:03:45.932835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:45.932835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iaeK6CAyLxV+MKKOzN1mMlfqSC3xAzyN8EmQzuw4NYkQ2210hR+P1GTns1SBcWi9F45fEbwrLNKkpGCxlnwjDg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:45.933867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:553945de98c35b41af348c2009689f022e32fa5677992a0d76b5533a9c00543a","sha256:139ffa70c6c4d609d8fc5da38d2eeaa7a0c6be9d643884b6d618fd452cc9991d"],"state_sha256":"0c21d93c2ed651b05bcc45c1496952cf205a57dd8c41ca399ac386e841474036"}