{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:73IXOQ3CGNUZCC7HFAZWJNJX6P","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":"6cda2cb21301cef78bc56ad90670d2b2b177086e8e478a830c0060158e585f96","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T09:18:21Z","title_canon_sha256":"518953c7f6992391d722b5a752d67255d6e89009fde37fc024761f71749eccfb"},"schema_version":"1.0","source":{"id":"2311.02105","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02105","created_at":"2026-07-05T07:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02105v1","created_at":"2026-07-05T07:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02105","created_at":"2026-07-05T07:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"73IXOQ3CGNUZ","created_at":"2026-07-05T07:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"73IXOQ3CGNUZCC7H","created_at":"2026-07-05T07:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"73IXOQ3C","created_at":"2026-07-05T07:09:33Z"}],"graph_snapshots":[{"event_id":"sha256:9c01e59db3668fabcc6d1fe608609c038d5f177f9aab416c33ea745869b52be1","target":"graph","created_at":"2026-07-05T07:09:33Z","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/2311.02105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. To meet the requirements of different applications, LLMs are often customized by further fine-tuning. However, the powerful learning ability of LLMs not only enables them to acquire new tasks but also makes them susceptible to learning undesired behaviors. For example, even safety-aligned LLMs can be easily fine-tuned into harmful assistants as the fine-tuning data often contains implicit or explicit harmful content. Can we train LLMs on harmful data without learning harmful behaviors? ","authors_text":"Qi Zhang, Ruotian Ma, Tao Gui, Xin Zhou, Xuanjing Huang, Yi Lu","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T09:18:21Z","title":"Making Harmful Behaviors Unlearnable for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02105","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":"sha256:75b3a4bb2c924fb60e9bd073a9a1b128a8cd0465ff6032935a47d5595c3dc5e5","target":"record","created_at":"2026-07-05T07:09:33Z","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":"6cda2cb21301cef78bc56ad90670d2b2b177086e8e478a830c0060158e585f96","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T09:18:21Z","title_canon_sha256":"518953c7f6992391d722b5a752d67255d6e89009fde37fc024761f71749eccfb"},"schema_version":"1.0","source":{"id":"2311.02105","kind":"arxiv","version":1}},"canonical_sha256":"fed17743623369910be7283364b537f3c1cd23a491afeeb08080c6a5f840f9a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fed17743623369910be7283364b537f3c1cd23a491afeeb08080c6a5f840f9a7","first_computed_at":"2026-07-05T07:09:33.280712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:33.280712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QrEUfEOkBqCoKh8mX4dezvnpn+9naRDHOB0IFhilwlwqyJlC2jcmHEcj+I+qtUJTkHJxZsT7gbw3Sh63kC5WBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:33.281185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02105","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75b3a4bb2c924fb60e9bd073a9a1b128a8cd0465ff6032935a47d5595c3dc5e5","sha256:9c01e59db3668fabcc6d1fe608609c038d5f177f9aab416c33ea745869b52be1"],"state_sha256":"96e767bd5aeed24f6a49b5529af9e7802cff3f80fd5e74f12b40b3a58db1cb7e"}