{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BVNHNHO64P5T5OJKLMG2IIZ2LS","short_pith_number":"pith:BVNHNHO6","canonical_record":{"source":{"id":"2505.22298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:37:06Z","cross_cats_sorted":[],"title_canon_sha256":"dd309997f89bf45188755ebb7d03e0028624ce86f8fbcd398ed901e9e65e7384","abstract_canon_sha256":"7a47e8c3d4f54348729199f2b82c64aa8525b6038989489a0a6e6c5b1d40d92b"},"schema_version":"1.0"},"canonical_sha256":"0d5a769ddee3fb3eb92a5b0da4233a5c928ca1864c0e0a3b83f719b6f0ea92ee","source":{"kind":"arxiv","id":"2505.22298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22298","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22298v1","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22298","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"BVNHNHO64P5T","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_16","alias_value":"BVNHNHO64P5T5OJK","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_8","alias_value":"BVNHNHO6","created_at":"2026-07-05T11:11:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BVNHNHO64P5T5OJKLMG2IIZ2LS","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:37:06Z","cross_cats_sorted":[],"title_canon_sha256":"dd309997f89bf45188755ebb7d03e0028624ce86f8fbcd398ed901e9e65e7384","abstract_canon_sha256":"7a47e8c3d4f54348729199f2b82c64aa8525b6038989489a0a6e6c5b1d40d92b"},"schema_version":"1.0"},"canonical_sha256":"0d5a769ddee3fb3eb92a5b0da4233a5c928ca1864c0e0a3b83f719b6f0ea92ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:12.829924Z","signature_b64":"T5BUKu3pDcL3gxzwEBBXSorJOG8XOgpnmrWfvm0twIcWyI+mFt47v0lM316e9U5IpIRFVU2BYCLOA/+109N5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d5a769ddee3fb3eb92a5b0da4233a5c928ca1864c0e0a3b83f719b6f0ea92ee","last_reissued_at":"2026-07-05T11:11:12.829404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:12.829404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22298","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zy6Gvz/uQtbDvKXIsCffEhWfuPxMWuLMxk4ejPvzaUWVrQsfZscoCw7v97Rai2Cdq+dmZq8riFFVGGG4cepoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:12:56.816134Z"},"content_sha256":"9c74b03877a653c271f256b0fbdfe1231b0bbfaacb84d0854d97c7c44a1dccd3","schema_version":"1.0","event_id":"sha256:9c74b03877a653c271f256b0fbdfe1231b0bbfaacb84d0854d97c7c44a1dccd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BVNHNHO64P5T5OJKLMG2IIZ2LS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangming Liu, Jing Li, Jun Yu, Meishan Zhang, Min Zhang, Wenya Wang, Xiucheng Li, Yifan Lu, Yigeng Zhou, Yihui Zhang","submitted_at":"2025-05-28T12:37:06Z","abstract_excerpt":"Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they often rely on entity-specific localization, making them ineffective against adversarial inputs without explicit entities. Second, these methods suffer from over-editing, where detoxified models reject legitimate queries, compromising overall performance. In this paper, we propose ToxEdit, a toxicity-aware knowledge editing approach that dynamically detects toxic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22298","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.22298/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wop3NjoUfcWI7ZFDPMm348qpxV7mKaxGdQYbJ59IRrjBkQGOzN8ReKJ43SuOGtmOG2HT93sP+As6UmyoBbc0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:12:56.816647Z"},"content_sha256":"008e95abc3462b77e11cb435b6520a7df0bed4a0fbac0d613f98146b9bfbc63c","schema_version":"1.0","event_id":"sha256:008e95abc3462b77e11cb435b6520a7df0bed4a0fbac0d613f98146b9bfbc63c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVNHNHO64P5T5OJKLMG2IIZ2LS/bundle.json","state_url":"https://pith.science/pith/BVNHNHO64P5T5OJKLMG2IIZ2LS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVNHNHO64P5T5OJKLMG2IIZ2LS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T06:12:56Z","links":{"resolver":"https://pith.science/pith/BVNHNHO64P5T5OJKLMG2IIZ2LS","bundle":"https://pith.science/pith/BVNHNHO64P5T5OJKLMG2IIZ2LS/bundle.json","state":"https://pith.science/pith/BVNHNHO64P5T5OJKLMG2IIZ2LS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVNHNHO64P5T5OJKLMG2IIZ2LS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BVNHNHO64P5T5OJKLMG2IIZ2LS","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":"7a47e8c3d4f54348729199f2b82c64aa8525b6038989489a0a6e6c5b1d40d92b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:37:06Z","title_canon_sha256":"dd309997f89bf45188755ebb7d03e0028624ce86f8fbcd398ed901e9e65e7384"},"schema_version":"1.0","source":{"id":"2505.22298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22298","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22298v1","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22298","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"BVNHNHO64P5T","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_16","alias_value":"BVNHNHO64P5T5OJK","created_at":"2026-07-05T11:11:12Z"},{"alias_kind":"pith_short_8","alias_value":"BVNHNHO6","created_at":"2026-07-05T11:11:12Z"}],"graph_snapshots":[{"event_id":"sha256:008e95abc3462b77e11cb435b6520a7df0bed4a0fbac0d613f98146b9bfbc63c","target":"graph","created_at":"2026-07-05T11:11:12Z","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/2505.22298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they often rely on entity-specific localization, making them ineffective against adversarial inputs without explicit entities. Second, these methods suffer from over-editing, where detoxified models reject legitimate queries, compromising overall performance. In this paper, we propose ToxEdit, a toxicity-aware knowledge editing approach that dynamically detects toxic","authors_text":"Fangming Liu, Jing Li, Jun Yu, Meishan Zhang, Min Zhang, Wenya Wang, Xiucheng Li, Yifan Lu, Yigeng Zhou, Yihui Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:37:06Z","title":"Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22298","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":"sha256:9c74b03877a653c271f256b0fbdfe1231b0bbfaacb84d0854d97c7c44a1dccd3","target":"record","created_at":"2026-07-05T11:11:12Z","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":"7a47e8c3d4f54348729199f2b82c64aa8525b6038989489a0a6e6c5b1d40d92b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T12:37:06Z","title_canon_sha256":"dd309997f89bf45188755ebb7d03e0028624ce86f8fbcd398ed901e9e65e7384"},"schema_version":"1.0","source":{"id":"2505.22298","kind":"arxiv","version":1}},"canonical_sha256":"0d5a769ddee3fb3eb92a5b0da4233a5c928ca1864c0e0a3b83f719b6f0ea92ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d5a769ddee3fb3eb92a5b0da4233a5c928ca1864c0e0a3b83f719b6f0ea92ee","first_computed_at":"2026-07-05T11:11:12.829404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:12.829404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T5BUKu3pDcL3gxzwEBBXSorJOG8XOgpnmrWfvm0twIcWyI+mFt47v0lM316e9U5IpIRFVU2BYCLOA/+109N5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:12.829924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c74b03877a653c271f256b0fbdfe1231b0bbfaacb84d0854d97c7c44a1dccd3","sha256:008e95abc3462b77e11cb435b6520a7df0bed4a0fbac0d613f98146b9bfbc63c"],"state_sha256":"8bcff79f94515654aaf87a1afd467e1a294ba1e83d9250dbca8e94106c86568c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNyGBxhtFQ8tmnpuv7lXMic16UmPg7yjJKceAI/Rc5a3Xm3NgvDADvKRY8kMqGutx9MOwaiV2B5BywUG/9WfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:12:56.820697Z","bundle_sha256":"e150ae3c8ff8d64604dc9428185adbc65915c297341fd0849bd5477547ba20d2"}}