{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UG2KSMONWWNMOI4BY7ZL7CDMQN","short_pith_number":"pith:UG2KSMON","canonical_record":{"source":{"id":"2403.14472","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-21T15:18:30Z","cross_cats_sorted":["cs.AI","cs.CV","cs.HC","cs.LG"],"title_canon_sha256":"cd36c2eb2f5658d336edc524aaf94e3c6d6a1a37fad6cf4518eff329d91d820c","abstract_canon_sha256":"f02abe628f552f2f30d196d4ce5dff95b1d693ec8a8095455cbf27d32c3ac473"},"schema_version":"1.0"},"canonical_sha256":"a1b4a931cdb59ac72381c7f2bf886c83517b50da7cd8f1befdf93265db4ae023","source":{"kind":"arxiv","id":"2403.14472","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14472","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14472v5","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14472","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"UG2KSMONWWNM","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"UG2KSMONWWNMOI4B","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"UG2KSMON","created_at":"2026-07-05T08:24:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UG2KSMONWWNMOI4BY7ZL7CDMQN","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14472","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-21T15:18:30Z","cross_cats_sorted":["cs.AI","cs.CV","cs.HC","cs.LG"],"title_canon_sha256":"cd36c2eb2f5658d336edc524aaf94e3c6d6a1a37fad6cf4518eff329d91d820c","abstract_canon_sha256":"f02abe628f552f2f30d196d4ce5dff95b1d693ec8a8095455cbf27d32c3ac473"},"schema_version":"1.0"},"canonical_sha256":"a1b4a931cdb59ac72381c7f2bf886c83517b50da7cd8f1befdf93265db4ae023","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:03.909798Z","signature_b64":"XaU9zfRX7yVHS796MuiZ/1BEN1hiUBXRY4zw/5QQvD9aD5xA9hfrspqTqq0O6sKIFffnpaJZpQcg1qfJtTu4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1b4a931cdb59ac72381c7f2bf886c83517b50da7cd8f1befdf93265db4ae023","last_reissued_at":"2026-07-05T08:24:03.909243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:03.909243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14472","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yaa4PT83p5BDlXRTJqpNaPTXyCFWP4Q0K5C2Si62AZS4y+FscLonsgEuADN/8qQTGCz0J2DhraV2u/Zxn6ACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:21.602614Z"},"content_sha256":"5b415e4de134506fc621ae0f89b780b771796f8f01b16d80e602499f70c875a4","schema_version":"1.0","event_id":"sha256:5b415e4de134506fc621ae0f89b780b771796f8f01b16d80e602499f70c875a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UG2KSMONWWNMOI4BY7ZL7CDMQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detoxifying Large Language Models via Knowledge Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Huajun Chen, Jindong Wang, Linyi Yang, Mengru Wang, Ningyu Zhang, Qishen Zhang, Shumin Deng, Yunzhi Yao, Zekun Xi, Ziwen Xu","submitted_at":"2024-03-21T15:18:30Z","abstract_excerpt":"This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive metrics for systematic evaluation. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to detoxify LLMs with a limited impact on general performance efficiently. Then, we propose a simple yet effective baseline, dubbed Detoxifying with Intraoperative Neural Monitoring (DINM), to diminish the toxici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14472","kind":"arxiv","version":5},"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/2403.14472/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":"2026-07-05T08:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/fTL+r7XKeV70vH6wlFzJSQ78I98hMH3x6nXaBgw2oxt8uAQ8rerKlZR9dRrG7o5LRyLQw7gHLKqem56OezxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:21.603142Z"},"content_sha256":"dddcd724637ee566d49e39ae082752b22ea12101ac0db7090fdfe77f5af7183a","schema_version":"1.0","event_id":"sha256:dddcd724637ee566d49e39ae082752b22ea12101ac0db7090fdfe77f5af7183a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UG2KSMONWWNMOI4BY7ZL7CDMQN/bundle.json","state_url":"https://pith.science/pith/UG2KSMONWWNMOI4BY7ZL7CDMQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UG2KSMONWWNMOI4BY7ZL7CDMQN/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":"2026-08-08T17:01:21Z","links":{"resolver":"https://pith.science/pith/UG2KSMONWWNMOI4BY7ZL7CDMQN","bundle":"https://pith.science/pith/UG2KSMONWWNMOI4BY7ZL7CDMQN/bundle.json","state":"https://pith.science/pith/UG2KSMONWWNMOI4BY7ZL7CDMQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UG2KSMONWWNMOI4BY7ZL7CDMQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UG2KSMONWWNMOI4BY7ZL7CDMQN","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":"f02abe628f552f2f30d196d4ce5dff95b1d693ec8a8095455cbf27d32c3ac473","cross_cats_sorted":["cs.AI","cs.CV","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-21T15:18:30Z","title_canon_sha256":"cd36c2eb2f5658d336edc524aaf94e3c6d6a1a37fad6cf4518eff329d91d820c"},"schema_version":"1.0","source":{"id":"2403.14472","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14472","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14472v5","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14472","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"UG2KSMONWWNM","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"UG2KSMONWWNMOI4B","created_at":"2026-07-05T08:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"UG2KSMON","created_at":"2026-07-05T08:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:dddcd724637ee566d49e39ae082752b22ea12101ac0db7090fdfe77f5af7183a","target":"graph","created_at":"2026-07-05T08:24:03Z","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/2403.14472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive metrics for systematic evaluation. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to detoxify LLMs with a limited impact on general performance efficiently. Then, we propose a simple yet effective baseline, dubbed Detoxifying with Intraoperative Neural Monitoring (DINM), to diminish the toxici","authors_text":"Huajun Chen, Jindong Wang, Linyi Yang, Mengru Wang, Ningyu Zhang, Qishen Zhang, Shumin Deng, Yunzhi Yao, Zekun Xi, Ziwen Xu","cross_cats":["cs.AI","cs.CV","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-21T15:18:30Z","title":"Detoxifying Large Language Models via Knowledge Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14472","kind":"arxiv","version":5},"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":"sha256:5b415e4de134506fc621ae0f89b780b771796f8f01b16d80e602499f70c875a4","target":"record","created_at":"2026-07-05T08:24:03Z","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":"f02abe628f552f2f30d196d4ce5dff95b1d693ec8a8095455cbf27d32c3ac473","cross_cats_sorted":["cs.AI","cs.CV","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-21T15:18:30Z","title_canon_sha256":"cd36c2eb2f5658d336edc524aaf94e3c6d6a1a37fad6cf4518eff329d91d820c"},"schema_version":"1.0","source":{"id":"2403.14472","kind":"arxiv","version":5}},"canonical_sha256":"a1b4a931cdb59ac72381c7f2bf886c83517b50da7cd8f1befdf93265db4ae023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1b4a931cdb59ac72381c7f2bf886c83517b50da7cd8f1befdf93265db4ae023","first_computed_at":"2026-07-05T08:24:03.909243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:03.909243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XaU9zfRX7yVHS796MuiZ/1BEN1hiUBXRY4zw/5QQvD9aD5xA9hfrspqTqq0O6sKIFffnpaJZpQcg1qfJtTu4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:03.909798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14472","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b415e4de134506fc621ae0f89b780b771796f8f01b16d80e602499f70c875a4","sha256:dddcd724637ee566d49e39ae082752b22ea12101ac0db7090fdfe77f5af7183a"],"state_sha256":"9c7bcbf3398ecdfb120d1fa3903f7bbfeb840bd4589055bd43759d49438a6bc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CY2UiJhfP9Z6GpBxtThGKO6AW1/Wt+aH0NtUtsWxwU7lFiIRg6i2d/9fbIUiSeSGaX2/OvlJoDsdLmmHOsAIAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:01:21.608946Z","bundle_sha256":"da5530d25e83eb7576d6933badf55d2a3f6f97dba9d7f2b6691f6977fd5083e6"}}