{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JLNYJKQIJWJV3ZDMYRLEGF6NHY","short_pith_number":"pith:JLNYJKQI","canonical_record":{"source":{"id":"2411.03814","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T10:32:09Z","cross_cats_sorted":["cs.CL","cs.CR"],"title_canon_sha256":"a391bca5220d61f6b7cb74ddc97ba2a9c1c068ab63ebbb62ec61f5a31f25f318","abstract_canon_sha256":"63dcd1f6da3012a9ff87fffb8100a0316ba133576505b54c5876ba449ed9b2e2"},"schema_version":"1.0"},"canonical_sha256":"4adb84aa084d935de46cc4564317cd3e310868dc86fc64ad1892ada5d383391e","source":{"kind":"arxiv","id":"2411.03814","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03814","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03814v2","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03814","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"pith_short_12","alias_value":"JLNYJKQIJWJV","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"pith_short_16","alias_value":"JLNYJKQIJWJV3ZDM","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"pith_short_8","alias_value":"JLNYJKQI","created_at":"2026-07-05T09:57:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JLNYJKQIJWJV3ZDMYRLEGF6NHY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.03814","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T10:32:09Z","cross_cats_sorted":["cs.CL","cs.CR"],"title_canon_sha256":"a391bca5220d61f6b7cb74ddc97ba2a9c1c068ab63ebbb62ec61f5a31f25f318","abstract_canon_sha256":"63dcd1f6da3012a9ff87fffb8100a0316ba133576505b54c5876ba449ed9b2e2"},"schema_version":"1.0"},"canonical_sha256":"4adb84aa084d935de46cc4564317cd3e310868dc86fc64ad1892ada5d383391e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:48.475099Z","signature_b64":"uZAKWKfZV9+TepxvHmnW6QNSRLxbLYGi0fBQWFTZcrXqQt8XNheq4OA7LYjhsiYWw3/VZ/P6gdNCM7PxnjhOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4adb84aa084d935de46cc4564317cd3e310868dc86fc64ad1892ada5d383391e","last_reissued_at":"2026-07-05T09:57:48.474615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:48.474615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.03814","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":"2026-07-05T09:57:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"92XqjCnUrefk5SB+TaGogFfuYPZTZg5RnKb7NgveSMCje9ccs2i6+TVvo6ZCSAPbG9AT4VstFn696YpdlT+9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:39.865707Z"},"content_sha256":"21ac19362c8faadf1ee415404115da2b6a7aad1e99bbc2301266b22851b7e22e","schema_version":"1.0","event_id":"sha256:21ac19362c8faadf1ee415404115da2b6a7aad1e99bbc2301266b22851b7e22e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JLNYJKQIJWJV3ZDMYRLEGF6NHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CR"],"primary_cat":"cs.AI","authors_text":"Cheng Wei, Chongwen Wang, Fengxiang Wang, Hang Su, Hui Xue, Jialing Tao, Jun Zhu, Peng Xiao, Ranjie Duan, Shiji Zhao, Xiaojun Jia, Yuefeng Chen","submitted_at":"2024-11-06T10:32:09Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illegal or unethical reactions when subjected to jailbreak attacks. To ensure their responsible deployment in critical applications, it is crucial to understand the safety capabilities and vulnerabilities of LLMs. Previous works mainly focus on jailbreak in single-round dialogue, overlooking the potential jailbreak risks in multi-round dialogues, which are a vital way humans interact with and extract information from LLMs."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03814","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/2411.03814/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":"2026-07-05T09:57:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ov+mOW9wJISjEL8rWitPQUvLbGnzQu5P6sotJnylYQZ/8EW2L5DozZ0NvD/ZUqBWqXDbLcivNav2SdMmxnLODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:39.866202Z"},"content_sha256":"25490d376992ad63bf7aed7063acaebd1eef001c217e9eb1bd51d37184b138dd","schema_version":"1.0","event_id":"sha256:25490d376992ad63bf7aed7063acaebd1eef001c217e9eb1bd51d37184b138dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLNYJKQIJWJV3ZDMYRLEGF6NHY/bundle.json","state_url":"https://pith.science/pith/JLNYJKQIJWJV3ZDMYRLEGF6NHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLNYJKQIJWJV3ZDMYRLEGF6NHY/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":"2026-08-08T19:21:39Z","links":{"resolver":"https://pith.science/pith/JLNYJKQIJWJV3ZDMYRLEGF6NHY","bundle":"https://pith.science/pith/JLNYJKQIJWJV3ZDMYRLEGF6NHY/bundle.json","state":"https://pith.science/pith/JLNYJKQIJWJV3ZDMYRLEGF6NHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLNYJKQIJWJV3ZDMYRLEGF6NHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JLNYJKQIJWJV3ZDMYRLEGF6NHY","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":"63dcd1f6da3012a9ff87fffb8100a0316ba133576505b54c5876ba449ed9b2e2","cross_cats_sorted":["cs.CL","cs.CR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T10:32:09Z","title_canon_sha256":"a391bca5220d61f6b7cb74ddc97ba2a9c1c068ab63ebbb62ec61f5a31f25f318"},"schema_version":"1.0","source":{"id":"2411.03814","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03814","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03814v2","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03814","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"pith_short_12","alias_value":"JLNYJKQIJWJV","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"pith_short_16","alias_value":"JLNYJKQIJWJV3ZDM","created_at":"2026-07-05T09:57:48Z"},{"alias_kind":"pith_short_8","alias_value":"JLNYJKQI","created_at":"2026-07-05T09:57:48Z"}],"graph_snapshots":[{"event_id":"sha256:25490d376992ad63bf7aed7063acaebd1eef001c217e9eb1bd51d37184b138dd","target":"graph","created_at":"2026-07-05T09:57:48Z","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/2411.03814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illegal or unethical reactions when subjected to jailbreak attacks. To ensure their responsible deployment in critical applications, it is crucial to understand the safety capabilities and vulnerabilities of LLMs. Previous works mainly focus on jailbreak in single-round dialogue, overlooking the potential jailbreak risks in multi-round dialogues, which are a vital way humans interact with and extract information from LLMs.","authors_text":"Cheng Wei, Chongwen Wang, Fengxiang Wang, Hang Su, Hui Xue, Jialing Tao, Jun Zhu, Peng Xiao, Ranjie Duan, Shiji Zhao, Xiaojun Jia, Yuefeng Chen","cross_cats":["cs.CL","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T10:32:09Z","title":"MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03814","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":"sha256:21ac19362c8faadf1ee415404115da2b6a7aad1e99bbc2301266b22851b7e22e","target":"record","created_at":"2026-07-05T09:57:48Z","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":"63dcd1f6da3012a9ff87fffb8100a0316ba133576505b54c5876ba449ed9b2e2","cross_cats_sorted":["cs.CL","cs.CR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-06T10:32:09Z","title_canon_sha256":"a391bca5220d61f6b7cb74ddc97ba2a9c1c068ab63ebbb62ec61f5a31f25f318"},"schema_version":"1.0","source":{"id":"2411.03814","kind":"arxiv","version":2}},"canonical_sha256":"4adb84aa084d935de46cc4564317cd3e310868dc86fc64ad1892ada5d383391e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4adb84aa084d935de46cc4564317cd3e310868dc86fc64ad1892ada5d383391e","first_computed_at":"2026-07-05T09:57:48.474615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:48.474615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uZAKWKfZV9+TepxvHmnW6QNSRLxbLYGi0fBQWFTZcrXqQt8XNheq4OA7LYjhsiYWw3/VZ/P6gdNCM7PxnjhOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:48.475099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03814","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21ac19362c8faadf1ee415404115da2b6a7aad1e99bbc2301266b22851b7e22e","sha256:25490d376992ad63bf7aed7063acaebd1eef001c217e9eb1bd51d37184b138dd"],"state_sha256":"7d4dec29a80f18027e60db7f7a9016fe89a47c008c208fa85f20929b9b548871"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzMkzON9s8jRWouEuxuUbPOKQ2Yo2sxFX79zQAygB0ig/u71UOc6PXH9Ytq8mHPJs6Y5P9VV7PcTDOlVtaelAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:21:39.870718Z","bundle_sha256":"8fcd66110baccb8060d8c0a50a12a251f9ade8058ff4e72d70c498b16a5007e2"}}