{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O2QSQXCVJ77BADNF7MNWH2IFH6","short_pith_number":"pith:O2QSQXCV","canonical_record":{"source":{"id":"2412.10423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T12:42:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c51cf47fd270077ae75fc40d9856578131e791c9ad24176e068c396d033ced4","abstract_canon_sha256":"eb0e330078263ca04a27d8cced2864a8d8fb127702b48ca8edb1040c2e937dbe"},"schema_version":"1.0"},"canonical_sha256":"76a1285c554ffe100da5fb1b63e9053fb8dd68d50df4794f46d101e77c510c48","source":{"kind":"arxiv","id":"2412.10423","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10423","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10423v2","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10423","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"O2QSQXCVJ77B","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"O2QSQXCVJ77BADNF","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"O2QSQXCV","created_at":"2026-07-05T10:48:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O2QSQXCVJ77BADNF7MNWH2IFH6","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T12:42:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c51cf47fd270077ae75fc40d9856578131e791c9ad24176e068c396d033ced4","abstract_canon_sha256":"eb0e330078263ca04a27d8cced2864a8d8fb127702b48ca8edb1040c2e937dbe"},"schema_version":"1.0"},"canonical_sha256":"76a1285c554ffe100da5fb1b63e9053fb8dd68d50df4794f46d101e77c510c48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:22.699832Z","signature_b64":"kR+4WStSHimTZDlXSuNw3ZZPbDSCpRXLXiZhnNwVn01xvYnqVfR03EdisohD2y9dA7gCvidR3cMz+2gizD6FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a1285c554ffe100da5fb1b63e9053fb8dd68d50df4794f46d101e77c510c48","last_reissued_at":"2026-07-05T10:48:22.699385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:22.699385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10423","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HuCAChlRUMitdwY1TgrQhcU5BXCeawtEQsW26Y6S9q7l5EeFzEOLvkWZby4k7tr84+ofU1L+XZo9SIimnTfMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:22:08.644410Z"},"content_sha256":"252c920e0d1a4c4bb538414cbb5c9d65a8f36016200aa11693beb7963f80cdf6","schema_version":"1.0","event_id":"sha256:252c920e0d1a4c4bb538414cbb5c9d65a8f36016200aa11693beb7963f80cdf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O2QSQXCVJ77BADNF7MNWH2IFH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kehai Chen, Min Zhang, Muyun Yang, Rongxiang Weng, Shaoqing Zhang, Tiejun Zhao, Zhuosheng Zhang","submitted_at":"2024-12-10T12:42:33Z","abstract_excerpt":"Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to real-world applications. Existing work faces challenges in both training efficiency and generalization capabilities (i.e., Reinforcement Learning from Human Feedback and Red-Teaming). Developing effective strategies to enable LLMs to resist continuously evolving jailbreak attempts represents a significant challenge. To address this challenge, we propose a novel defe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10423","kind":"arxiv","version":2},"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/2412.10423/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":"2026-07-05T10:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Cgt4unf2bGgq796RpnkdTjsBW9LF9OjML9vG1w1P4fKibRxBj8UJQgBQyd9+5pp2CGq9lTXbUmfWuNHhCjjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:22:08.644945Z"},"content_sha256":"39d00e0ffe26a63ae2405f9e595836724ffc185cfd896883b64d6763f4abc6c3","schema_version":"1.0","event_id":"sha256:39d00e0ffe26a63ae2405f9e595836724ffc185cfd896883b64d6763f4abc6c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O2QSQXCVJ77BADNF7MNWH2IFH6/bundle.json","state_url":"https://pith.science/pith/O2QSQXCVJ77BADNF7MNWH2IFH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O2QSQXCVJ77BADNF7MNWH2IFH6/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":"2026-08-03T22:22:08Z","links":{"resolver":"https://pith.science/pith/O2QSQXCVJ77BADNF7MNWH2IFH6","bundle":"https://pith.science/pith/O2QSQXCVJ77BADNF7MNWH2IFH6/bundle.json","state":"https://pith.science/pith/O2QSQXCVJ77BADNF7MNWH2IFH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O2QSQXCVJ77BADNF7MNWH2IFH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O2QSQXCVJ77BADNF7MNWH2IFH6","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":"eb0e330078263ca04a27d8cced2864a8d8fb127702b48ca8edb1040c2e937dbe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T12:42:33Z","title_canon_sha256":"3c51cf47fd270077ae75fc40d9856578131e791c9ad24176e068c396d033ced4"},"schema_version":"1.0","source":{"id":"2412.10423","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10423","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10423v2","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10423","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"O2QSQXCVJ77B","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"O2QSQXCVJ77BADNF","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"O2QSQXCV","created_at":"2026-07-05T10:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:39d00e0ffe26a63ae2405f9e595836724ffc185cfd896883b64d6763f4abc6c3","target":"graph","created_at":"2026-07-05T10:48:22Z","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/2412.10423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to real-world applications. Existing work faces challenges in both training efficiency and generalization capabilities (i.e., Reinforcement Learning from Human Feedback and Red-Teaming). Developing effective strategies to enable LLMs to resist continuously evolving jailbreak attempts represents a significant challenge. To address this challenge, we propose a novel defe","authors_text":"Kehai Chen, Min Zhang, Muyun Yang, Rongxiang Weng, Shaoqing Zhang, Tiejun Zhao, Zhuosheng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T12:42:33Z","title":"Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10423","kind":"arxiv","version":2},"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":"sha256:252c920e0d1a4c4bb538414cbb5c9d65a8f36016200aa11693beb7963f80cdf6","target":"record","created_at":"2026-07-05T10:48:22Z","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":"eb0e330078263ca04a27d8cced2864a8d8fb127702b48ca8edb1040c2e937dbe","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T12:42:33Z","title_canon_sha256":"3c51cf47fd270077ae75fc40d9856578131e791c9ad24176e068c396d033ced4"},"schema_version":"1.0","source":{"id":"2412.10423","kind":"arxiv","version":2}},"canonical_sha256":"76a1285c554ffe100da5fb1b63e9053fb8dd68d50df4794f46d101e77c510c48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76a1285c554ffe100da5fb1b63e9053fb8dd68d50df4794f46d101e77c510c48","first_computed_at":"2026-07-05T10:48:22.699385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:22.699385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kR+4WStSHimTZDlXSuNw3ZZPbDSCpRXLXiZhnNwVn01xvYnqVfR03EdisohD2y9dA7gCvidR3cMz+2gizD6FDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:22.699832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10423","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:252c920e0d1a4c4bb538414cbb5c9d65a8f36016200aa11693beb7963f80cdf6","sha256:39d00e0ffe26a63ae2405f9e595836724ffc185cfd896883b64d6763f4abc6c3"],"state_sha256":"fc3a7bc2c7d6572e1d1254db3efb7ce83cbae1e0f993af2be5cd879be1761d71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/k0CXOGzV/nsd/pthE7bJqr8GOHhRsetsPtl8v46HL5rtu7SyOG2vZP6yjawlv95+WJKaJFmb+1+CC1e29bCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:22:08.649753Z","bundle_sha256":"386b908e202e3b45800380c1cde4cc214454da4a08fb73b8ff0750e0cb70f6b6"}}