{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2H5UPSO3GQ6KOFSD66PM4RFZXX","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":"8145211db01004c69a6fbe9765b24a475895daeca87b4b6a6ab21271faf03e24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T02:59:04Z","title_canon_sha256":"9fe8e07b08fb15c7d43f01c2c2ffff2cd6c9894f359b1fd4e7e0d06728fca9c5"},"schema_version":"1.0","source":{"id":"2412.12497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12497","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12497v1","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12497","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"pith_short_12","alias_value":"2H5UPSO3GQ6K","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"pith_short_16","alias_value":"2H5UPSO3GQ6KOFSD","created_at":"2026-07-05T09:50:15Z"},{"alias_kind":"pith_short_8","alias_value":"2H5UPSO3","created_at":"2026-07-05T09:50:15Z"}],"graph_snapshots":[{"event_id":"sha256:24c9f0f345a3dbf8466fdc3a5eeb49bdda9467338f0a25958e9586efe08bf87e","target":"graph","created_at":"2026-07-05T09:50:15Z","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/2412.12497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken model. Existing methods to counteract fine-tuning attacks typically require substantial computational resources. Even with parameter-efficient techniques like LoRA, gradient updates remain essential. To address these challenges, we propose \\textbf{N}euron-\\textbf{L}evel \\textbf{S}afety \\textbf{R}ealignment (\\textbf{NLSR}), a training-free framework that restore","authors_text":"Gerard de Melo, Liang He, Linlin Wang, Shunfan Zheng, Xiaoling Wang, Xin Yi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T02:59:04Z","title":"NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12497","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":"sha256:380c7e6e29958cdd1663b59e22fb463bf0748eb01e4741c56d2fd012ce4560bf","target":"record","created_at":"2026-07-05T09:50:15Z","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":"8145211db01004c69a6fbe9765b24a475895daeca87b4b6a6ab21271faf03e24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T02:59:04Z","title_canon_sha256":"9fe8e07b08fb15c7d43f01c2c2ffff2cd6c9894f359b1fd4e7e0d06728fca9c5"},"schema_version":"1.0","source":{"id":"2412.12497","kind":"arxiv","version":1}},"canonical_sha256":"d1fb47c9db343ca71643f79ece44b9bdc84059271d3b6105ad1407217c36b9de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1fb47c9db343ca71643f79ece44b9bdc84059271d3b6105ad1407217c36b9de","first_computed_at":"2026-07-05T09:50:15.882855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:15.882855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/bC8pE5+O1j98DMUJqvVxc042j7x2Ls7oLp4ic3sokeJ5TRU2P27ekGHxnQKb5GoHaom8IYrCi8EAsUa3LsuBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:15.883397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:380c7e6e29958cdd1663b59e22fb463bf0748eb01e4741c56d2fd012ce4560bf","sha256:24c9f0f345a3dbf8466fdc3a5eeb49bdda9467338f0a25958e9586efe08bf87e"],"state_sha256":"52e16fe2ca6f27b9df5242e9096edda5d07427643539818f00d425f04011d6b3"}