{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3UQBIR65GANVCDUZJPMO4A47I2","short_pith_number":"pith:3UQBIR65","schema_version":"1.0","canonical_sha256":"dd201447dd301b510e994bd8ee039f46894e2d07922f44301c10b3bba10f9c40","source":{"kind":"arxiv","id":"2505.21277","version":2},"attestation_state":"computed","paper":{"title":"Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Shouwei Ruan, Xingxing Wei, Yao Huang, Yichi Zhang, Yinpeng Dong, Yitong Sun","submitted_at":"2025-05-27T14:48:44Z","abstract_excerpt":"Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak attacks, which better reflect real-world scenarios, offers critical insights into model robustness. While existing methods have shown improvements through various prompt engineering techniques, their success remains limited against safety-aligned models, overlooking a more fundamental problem: the effectiveness is inherently bounded by the predefined strategy space"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.21277","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-27T14:48:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9cad6eec2ffd22f1af9e65911741bc925d3a9c9a63f9d19a57249fd5320ef135","abstract_canon_sha256":"f289690f9215c30bc4e6ae8e951b5a9b5833003fc13aa951673177270c8390aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:58.958868Z","signature_b64":"Z3ofA+jkCjasDhusKXEo6w1fOlAIbDOOEizGm9RB+so9eAuMuQImNLBzgPHu1ylbLRZl0kXZZfp1yfS7F7+fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd201447dd301b510e994bd8ee039f46894e2d07922f44301c10b3bba10f9c40","last_reissued_at":"2026-07-05T11:10:58.958392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:58.958392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Shouwei Ruan, Xingxing Wei, Yao Huang, Yichi Zhang, Yinpeng Dong, Yitong Sun","submitted_at":"2025-05-27T14:48:44Z","abstract_excerpt":"Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak attacks, which better reflect real-world scenarios, offers critical insights into model robustness. While existing methods have shown improvements through various prompt engineering techniques, their success remains limited against safety-aligned models, overlooking a more fundamental problem: the effectiveness is inherently bounded by the predefined strategy space"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21277","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/2505.21277/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.21277","created_at":"2026-07-05T11:10:58.958449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21277v2","created_at":"2026-07-05T11:10:58.958449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21277","created_at":"2026-07-05T11:10:58.958449+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UQBIR65GANV","created_at":"2026-07-05T11:10:58.958449+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UQBIR65GANVCDUZ","created_at":"2026-07-05T11:10:58.958449+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UQBIR65","created_at":"2026-07-05T11:10:58.958449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23844","citing_title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","ref_index":97,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2","json":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2.json","graph_json":"https://pith.science/api/pith-number/3UQBIR65GANVCDUZJPMO4A47I2/graph.json","events_json":"https://pith.science/api/pith-number/3UQBIR65GANVCDUZJPMO4A47I2/events.json","paper":"https://pith.science/paper/3UQBIR65"},"agent_actions":{"view_html":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2","download_json":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2.json","view_paper":"https://pith.science/paper/3UQBIR65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21277&json=true","fetch_graph":"https://pith.science/api/pith-number/3UQBIR65GANVCDUZJPMO4A47I2/graph.json","fetch_events":"https://pith.science/api/pith-number/3UQBIR65GANVCDUZJPMO4A47I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2/action/storage_attestation","attest_author":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2/action/author_attestation","sign_citation":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2/action/citation_signature","submit_replication":"https://pith.science/pith/3UQBIR65GANVCDUZJPMO4A47I2/action/replication_record"}},"created_at":"2026-07-05T11:10:58.958449+00:00","updated_at":"2026-07-05T11:10:58.958449+00:00"}