{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IQJXPRRFZEFTVZBLDOKIUXVI7X","short_pith_number":"pith:IQJXPRRF","schema_version":"1.0","canonical_sha256":"441377c625c90b3ae42b1b948a5ea8fde9c1cc482777093e75ec0bd2ecf4a7d6","source":{"kind":"arxiv","id":"2406.02622","version":1},"attestation_state":"computed","paper":{"title":"Safeguarding Large Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Changshun Wu, Gaojie Jin, Jie Meng, Jinwei Hu, Ronghui Mu, Saddek Bensalem, Siqi Sun, Tianle Zhang, Xiaowei Huang, Yanghao Zhang, Yi Dong, Yi Qi","submitted_at":"2024-06-03T19:27:46Z","abstract_excerpt":"In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as \"safeguards\" or \"guardrails\", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-"},"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":"2406.02622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-03T19:27:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94851728626236107930a0fb070adae5e3e0464fb9a58eea81205a44b53f266d","abstract_canon_sha256":"dce8e57b2291430aef9a657deb5d4ccae4891eb059084e2f1aa506ca9c9dc736"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:28.077622Z","signature_b64":"U/31wWfbdtYH7niUcnVwiYqAkrd2CkQ5b52JGzDBstjFQoA1+CVLAZCTC9U11FScl/y0ocvA/WSwklH58tpKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"441377c625c90b3ae42b1b948a5ea8fde9c1cc482777093e75ec0bd2ecf4a7d6","last_reissued_at":"2026-07-05T08:27:28.077168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:28.077168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safeguarding Large Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Changshun Wu, Gaojie Jin, Jie Meng, Jinwei Hu, Ronghui Mu, Saddek Bensalem, Siqi Sun, Tianle Zhang, Xiaowei Huang, Yanghao Zhang, Yi Dong, Yi Qi","submitted_at":"2024-06-03T19:27:46Z","abstract_excerpt":"In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as \"safeguards\" or \"guardrails\", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02622","kind":"arxiv","version":1},"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/2406.02622/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":"2406.02622","created_at":"2026-07-05T08:27:28.077227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02622v1","created_at":"2026-07-05T08:27:28.077227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02622","created_at":"2026-07-05T08:27:28.077227+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQJXPRRFZEFT","created_at":"2026-07-05T08:27:28.077227+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQJXPRRFZEFTVZBL","created_at":"2026-07-05T08:27:28.077227+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQJXPRRF","created_at":"2026-07-05T08:27:28.077227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31073","citing_title":"ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16120","citing_title":"LLM-Powered AI Agent Systems and Their Applications in Industry","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05929","citing_title":"LLM Harms: A Taxonomy and Discussion","ref_index":214,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07954","citing_title":"Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2503.18666","citing_title":"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07655","citing_title":"Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05229","citing_title":"From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X","json":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X.json","graph_json":"https://pith.science/api/pith-number/IQJXPRRFZEFTVZBLDOKIUXVI7X/graph.json","events_json":"https://pith.science/api/pith-number/IQJXPRRFZEFTVZBLDOKIUXVI7X/events.json","paper":"https://pith.science/paper/IQJXPRRF"},"agent_actions":{"view_html":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X","download_json":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X.json","view_paper":"https://pith.science/paper/IQJXPRRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02622&json=true","fetch_graph":"https://pith.science/api/pith-number/IQJXPRRFZEFTVZBLDOKIUXVI7X/graph.json","fetch_events":"https://pith.science/api/pith-number/IQJXPRRFZEFTVZBLDOKIUXVI7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X/action/storage_attestation","attest_author":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X/action/author_attestation","sign_citation":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X/action/citation_signature","submit_replication":"https://pith.science/pith/IQJXPRRFZEFTVZBLDOKIUXVI7X/action/replication_record"}},"created_at":"2026-07-05T08:27:28.077227+00:00","updated_at":"2026-07-05T08:27:28.077227+00:00"}