{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AVXXNQQJLEV6T5JE2E5DB2TQOD","short_pith_number":"pith:AVXXNQQJ","canonical_record":{"source":{"id":"2502.09638","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T20:49:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76866a1143fde2f250d34f26e5a003f296e18b929125ccb61e7032055fa3f8fd","abstract_canon_sha256":"e22d3541e34058e221290035f7ed18d95647c63387067c1b2a110b52980aee4f"},"schema_version":"1.0"},"canonical_sha256":"056f76c209592be9f524d13a30ea7070e6d1dd98d89547d59d6bb85681596bb6","source":{"kind":"arxiv","id":"2502.09638","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09638","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09638v2","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09638","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"AVXXNQQJLEV6","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"AVXXNQQJLEV6T5JE","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"AVXXNQQJ","created_at":"2026-07-05T11:11:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AVXXNQQJLEV6T5JE2E5DB2TQOD","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09638","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T20:49:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"76866a1143fde2f250d34f26e5a003f296e18b929125ccb61e7032055fa3f8fd","abstract_canon_sha256":"e22d3541e34058e221290035f7ed18d95647c63387067c1b2a110b52980aee4f"},"schema_version":"1.0"},"canonical_sha256":"056f76c209592be9f524d13a30ea7070e6d1dd98d89547d59d6bb85681596bb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:41.272209Z","signature_b64":"36O+9frBxIw4BbfOZG0DxdW1O3BkQ9GOsU+v6OSAPvyv6+lBLeVgIp1PT0o1ZHhutbfpRsWKjNpcEOZ8UR4OCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"056f76c209592be9f524d13a30ea7070e6d1dd98d89547d59d6bb85681596bb6","last_reissued_at":"2026-07-05T11:11:41.271300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:41.271300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09638","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":"2026-07-05T11:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GYz9ISHQO4NOSNkLNr1q+wFQOUciDc0dKb99EplGp5F5yJMt/pZxdlFYJ8+2vXrO0FXqNv3Pkui2SYb2OmTLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:08:49.395481Z"},"content_sha256":"a0373795c0b96249933916ac62a770993d8d83878a46bd22ca1c8dfb2beb2858","schema_version":"1.0","event_id":"sha256:a0373795c0b96249933916ac62a770993d8d83878a46bd22ca1c8dfb2beb2858"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AVXXNQQJLEV6T5JE2E5DB2TQOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jailbreaking to Jailbreak","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bijan Varjavand, Bobby Gogov, Jeremy Kritz, Michael Choi, Robert Vacareanu, Scale Red Team, Summer Yue, Vaughn Robinson, Willow E. Primack, Zifan Wang","submitted_at":"2025-02-09T20:49:16Z","abstract_excerpt":"Large Language Models (LLMs) can be used to red team other models (e.g. jailbreaking) to elicit harmful contents. While prior works commonly employ open-weight models or private uncensored models for doing jailbreaking, as the refusal-training of strong LLMs (e.g. OpenAI o3) refuse to help jailbreaking, our work turn (almost) any black-box LLMs into attackers. The resulting $J_2$ (jailbreaking-to-jailbreak) attackers can effectively jailbreak the safeguard of target models using various strategies, both created by themselves or from expert human red teamers. In doing so, we show their strong b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09638","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/2502.09638/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":"2026-07-05T11:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U1Mzt60utai0cdhid6nQqe4Ui46+9WnCvUuwqlT0+PLXU7WlE1mJ65hDeX+4WBCjcffpmGOhx7s+ylCMrgW0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:08:49.395849Z"},"content_sha256":"56a6eb27920b6391bf51c340b1ad86e010bf036ddd23a3abe6760b515220f467","schema_version":"1.0","event_id":"sha256:56a6eb27920b6391bf51c340b1ad86e010bf036ddd23a3abe6760b515220f467"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AVXXNQQJLEV6T5JE2E5DB2TQOD/bundle.json","state_url":"https://pith.science/pith/AVXXNQQJLEV6T5JE2E5DB2TQOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AVXXNQQJLEV6T5JE2E5DB2TQOD/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":"2026-07-07T13:08:49Z","links":{"resolver":"https://pith.science/pith/AVXXNQQJLEV6T5JE2E5DB2TQOD","bundle":"https://pith.science/pith/AVXXNQQJLEV6T5JE2E5DB2TQOD/bundle.json","state":"https://pith.science/pith/AVXXNQQJLEV6T5JE2E5DB2TQOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AVXXNQQJLEV6T5JE2E5DB2TQOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AVXXNQQJLEV6T5JE2E5DB2TQOD","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":"e22d3541e34058e221290035f7ed18d95647c63387067c1b2a110b52980aee4f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T20:49:16Z","title_canon_sha256":"76866a1143fde2f250d34f26e5a003f296e18b929125ccb61e7032055fa3f8fd"},"schema_version":"1.0","source":{"id":"2502.09638","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09638","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09638v2","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09638","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"AVXXNQQJLEV6","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"AVXXNQQJLEV6T5JE","created_at":"2026-07-05T11:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"AVXXNQQJ","created_at":"2026-07-05T11:11:41Z"}],"graph_snapshots":[{"event_id":"sha256:56a6eb27920b6391bf51c340b1ad86e010bf036ddd23a3abe6760b515220f467","target":"graph","created_at":"2026-07-05T11:11:41Z","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/2502.09638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) can be used to red team other models (e.g. jailbreaking) to elicit harmful contents. While prior works commonly employ open-weight models or private uncensored models for doing jailbreaking, as the refusal-training of strong LLMs (e.g. OpenAI o3) refuse to help jailbreaking, our work turn (almost) any black-box LLMs into attackers. The resulting $J_2$ (jailbreaking-to-jailbreak) attackers can effectively jailbreak the safeguard of target models using various strategies, both created by themselves or from expert human red teamers. In doing so, we show their strong b","authors_text":"Bijan Varjavand, Bobby Gogov, Jeremy Kritz, Michael Choi, Robert Vacareanu, Scale Red Team, Summer Yue, Vaughn Robinson, Willow E. Primack, Zifan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T20:49:16Z","title":"Jailbreaking to Jailbreak"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09638","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:a0373795c0b96249933916ac62a770993d8d83878a46bd22ca1c8dfb2beb2858","target":"record","created_at":"2026-07-05T11:11:41Z","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":"e22d3541e34058e221290035f7ed18d95647c63387067c1b2a110b52980aee4f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-09T20:49:16Z","title_canon_sha256":"76866a1143fde2f250d34f26e5a003f296e18b929125ccb61e7032055fa3f8fd"},"schema_version":"1.0","source":{"id":"2502.09638","kind":"arxiv","version":2}},"canonical_sha256":"056f76c209592be9f524d13a30ea7070e6d1dd98d89547d59d6bb85681596bb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"056f76c209592be9f524d13a30ea7070e6d1dd98d89547d59d6bb85681596bb6","first_computed_at":"2026-07-05T11:11:41.271300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:41.271300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"36O+9frBxIw4BbfOZG0DxdW1O3BkQ9GOsU+v6OSAPvyv6+lBLeVgIp1PT0o1ZHhutbfpRsWKjNpcEOZ8UR4OCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:41.272209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09638","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0373795c0b96249933916ac62a770993d8d83878a46bd22ca1c8dfb2beb2858","sha256:56a6eb27920b6391bf51c340b1ad86e010bf036ddd23a3abe6760b515220f467"],"state_sha256":"5d24ef85e58ddf6a8aa11f999115fc3734876eff83a1cae0ab0f5809453e7630"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BE2rqfMFHgqRpEKn4fPFyxBNMJ4EvhKPSyyXOQHz+BBzgXFldsJksDmL3E4XCEZCUo87fdZ6kZbwqlNGLc8fCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:08:49.398199Z","bundle_sha256":"44d8d1a2b21a240f29e6836573b7a56524bc7620e29016fd8afe5b40dac2d607"}}