{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MBBCYRW6NROTE64AGNQ5HOUMQN","short_pith_number":"pith:MBBCYRW6","canonical_record":{"source":{"id":"2402.08983","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-14T06:54:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0ce4061727074ac4fc22b1656cbec25cc064ba6b4f7bee34545182db619934f8","abstract_canon_sha256":"f858b4341ecae7901441d136ebda6c18cccce87ecc228cfaf524d3ebe8a7ba35"},"schema_version":"1.0"},"canonical_sha256":"60422c46de6c5d327b803361d3ba8c8362f30d975208a4fd361ae2aba26a5560","source":{"kind":"arxiv","id":"2402.08983","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08983","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08983v4","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08983","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"MBBCYRW6NROT","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"MBBCYRW6NROTE64A","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"MBBCYRW6","created_at":"2026-07-05T08:48:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MBBCYRW6NROTE64AGNQ5HOUMQN","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08983","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-14T06:54:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0ce4061727074ac4fc22b1656cbec25cc064ba6b4f7bee34545182db619934f8","abstract_canon_sha256":"f858b4341ecae7901441d136ebda6c18cccce87ecc228cfaf524d3ebe8a7ba35"},"schema_version":"1.0"},"canonical_sha256":"60422c46de6c5d327b803361d3ba8c8362f30d975208a4fd361ae2aba26a5560","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:41.303163Z","signature_b64":"GQUjSWqCKyGIxsxX2feEXhDGRr+m2o+6vA55M5nY6S2co8Qu/FK/D7ie/FPbynSKUcDgHb5+mfCV4QDm9VeODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60422c46de6c5d327b803361d3ba8c8362f30d975208a4fd361ae2aba26a5560","last_reissued_at":"2026-07-05T08:48:41.302689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:41.302689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08983","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/oCjjRhASAoWe+6LUOJlDD2zc3l5i0BFe4xRrMybPlpz3259OQhAWlHW1YQbg6DMVz805j7F85xL4ZVUIeUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:06:19.612768Z"},"content_sha256":"67b914e891a3ed6f43c9ad3df23a6b603c66be8e1d701531c8014792083b00be","schema_version":"1.0","event_id":"sha256:67b914e891a3ed6f43c9ad3df23a6b603c66be8e1d701531c8014792083b00be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MBBCYRW6NROTE64AGNQ5HOUMQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Bill Yuchen Lin, Fengqing Jiang, Jinyuan Jia, Luyao Niu, Radha Poovendran, Zhangchen Xu","submitted_at":"2024-02-14T06:54:31Z","abstract_excerpt":"As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant/leading LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses to user queries. Our insight in developing SafeDecoding is base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08983","kind":"arxiv","version":4},"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/2402.08983/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":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AaR7+vywHvFWktzxT5XoirQJ3WJj2Chvzf5uq9D/19J6bSg6iR6BcETIIIyijd9NbY5VC7UjXJLA7lYdZ8GyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:06:19.613286Z"},"content_sha256":"a3a64d78615de1a2b92974e57ce02d55b28050dc538cacd82256ee690e2b88a2","schema_version":"1.0","event_id":"sha256:a3a64d78615de1a2b92974e57ce02d55b28050dc538cacd82256ee690e2b88a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBBCYRW6NROTE64AGNQ5HOUMQN/bundle.json","state_url":"https://pith.science/pith/MBBCYRW6NROTE64AGNQ5HOUMQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBBCYRW6NROTE64AGNQ5HOUMQN/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":"2026-08-06T04:06:19Z","links":{"resolver":"https://pith.science/pith/MBBCYRW6NROTE64AGNQ5HOUMQN","bundle":"https://pith.science/pith/MBBCYRW6NROTE64AGNQ5HOUMQN/bundle.json","state":"https://pith.science/pith/MBBCYRW6NROTE64AGNQ5HOUMQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBBCYRW6NROTE64AGNQ5HOUMQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MBBCYRW6NROTE64AGNQ5HOUMQN","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":"f858b4341ecae7901441d136ebda6c18cccce87ecc228cfaf524d3ebe8a7ba35","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-14T06:54:31Z","title_canon_sha256":"0ce4061727074ac4fc22b1656cbec25cc064ba6b4f7bee34545182db619934f8"},"schema_version":"1.0","source":{"id":"2402.08983","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08983","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08983v4","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08983","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"MBBCYRW6NROT","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"MBBCYRW6NROTE64A","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"MBBCYRW6","created_at":"2026-07-05T08:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:a3a64d78615de1a2b92974e57ce02d55b28050dc538cacd82256ee690e2b88a2","target":"graph","created_at":"2026-07-05T08:48:41Z","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/2402.08983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant/leading LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses to user queries. Our insight in developing SafeDecoding is base","authors_text":"Bill Yuchen Lin, Fengqing Jiang, Jinyuan Jia, Luyao Niu, Radha Poovendran, Zhangchen Xu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-14T06:54:31Z","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08983","kind":"arxiv","version":4},"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":"sha256:67b914e891a3ed6f43c9ad3df23a6b603c66be8e1d701531c8014792083b00be","target":"record","created_at":"2026-07-05T08:48:41Z","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":"f858b4341ecae7901441d136ebda6c18cccce87ecc228cfaf524d3ebe8a7ba35","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-14T06:54:31Z","title_canon_sha256":"0ce4061727074ac4fc22b1656cbec25cc064ba6b4f7bee34545182db619934f8"},"schema_version":"1.0","source":{"id":"2402.08983","kind":"arxiv","version":4}},"canonical_sha256":"60422c46de6c5d327b803361d3ba8c8362f30d975208a4fd361ae2aba26a5560","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60422c46de6c5d327b803361d3ba8c8362f30d975208a4fd361ae2aba26a5560","first_computed_at":"2026-07-05T08:48:41.302689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:41.302689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GQUjSWqCKyGIxsxX2feEXhDGRr+m2o+6vA55M5nY6S2co8Qu/FK/D7ie/FPbynSKUcDgHb5+mfCV4QDm9VeODw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:41.303163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08983","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67b914e891a3ed6f43c9ad3df23a6b603c66be8e1d701531c8014792083b00be","sha256:a3a64d78615de1a2b92974e57ce02d55b28050dc538cacd82256ee690e2b88a2"],"state_sha256":"075a6e5c9f34ca873a1fa49aa290c562301a477329adc3a290b94d3742d74048"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rODrYhCX5QRt+16HpwVwiSQBs0fL0kKyjxmpFO8t+2JL8a/mtAvrQl4jJAVSEIuOH3IJCRB1CG4mYKxj9ECxAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:06:19.616816Z","bundle_sha256":"665c94169895766052b4690bbc9988b03bcf3947aa7e5b52a3cbbca5f5e44c79"}}