{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BM3VMQ63BVMN6IDOHVDUSPVIGP","short_pith_number":"pith:BM3VMQ63","schema_version":"1.0","canonical_sha256":"0b375643db0d58df206e3d47493ea833c682e1a9f03b4c4a153ae4d218d223c8","source":{"kind":"arxiv","id":"2412.17686","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model Safety: A Holistic Survey","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bojian Jiang, Chuang Liu, Dan Shi, Deyi Xiong, Ling Shi, Linhao Yu, Renren Jin, Tianhao Shen, Xinwei Wu, Yongqi Leng, Yufei Huang, Zhigen Li, Zishan Guo","submitted_at":"2024-12-23T16:11:27Z","abstract_excerpt":"The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies.\n  This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial atta"},"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":"2412.17686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-23T16:11:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"364fabb858c8c8fdd52b7fa1e48a48ca0c777074b77d9f2e063169a2cd5dd9ee","abstract_canon_sha256":"450d590e63b0d4cbb95ec93ea0e960fd32510ef094bbf1ac64ba77902fd11cb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:48.178170Z","signature_b64":"WlsNED7/Rs7/cHYZne3eqYSCZZSlJOzYNgLAh2DZjE4aZCdBHO6URdLt3D+ljcI2i4siwWyzqSxdDF2l0vSYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b375643db0d58df206e3d47493ea833c682e1a9f03b4c4a153ae4d218d223c8","last_reissued_at":"2026-07-05T09:53:48.177667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:48.177667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Safety: A Holistic Survey","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bojian Jiang, Chuang Liu, Dan Shi, Deyi Xiong, Ling Shi, Linhao Yu, Renren Jin, Tianhao Shen, Xinwei Wu, Yongqi Leng, Yufei Huang, Zhigen Li, Zishan Guo","submitted_at":"2024-12-23T16:11:27Z","abstract_excerpt":"The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies.\n  This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial atta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17686","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/2412.17686/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":"2412.17686","created_at":"2026-07-05T09:53:48.177732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17686v1","created_at":"2026-07-05T09:53:48.177732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17686","created_at":"2026-07-05T09:53:48.177732+00:00"},{"alias_kind":"pith_short_12","alias_value":"BM3VMQ63BVMN","created_at":"2026-07-05T09:53:48.177732+00:00"},{"alias_kind":"pith_short_16","alias_value":"BM3VMQ63BVMN6IDO","created_at":"2026-07-05T09:53:48.177732+00:00"},{"alias_kind":"pith_short_8","alias_value":"BM3VMQ63","created_at":"2026-07-05T09:53:48.177732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09038","citing_title":"Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20759","citing_title":"Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17830","citing_title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16776","citing_title":"Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16746","citing_title":"State Contamination in Memory-Augmented LLM Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27550","citing_title":"APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12601","citing_title":"LLM-Guided Prompt Evolution for Password Guessing","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11663","citing_title":"Why Do Large Language Models Generate Harmful Content?","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18775","citing_title":"An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP","json":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP.json","graph_json":"https://pith.science/api/pith-number/BM3VMQ63BVMN6IDOHVDUSPVIGP/graph.json","events_json":"https://pith.science/api/pith-number/BM3VMQ63BVMN6IDOHVDUSPVIGP/events.json","paper":"https://pith.science/paper/BM3VMQ63"},"agent_actions":{"view_html":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP","download_json":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP.json","view_paper":"https://pith.science/paper/BM3VMQ63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17686&json=true","fetch_graph":"https://pith.science/api/pith-number/BM3VMQ63BVMN6IDOHVDUSPVIGP/graph.json","fetch_events":"https://pith.science/api/pith-number/BM3VMQ63BVMN6IDOHVDUSPVIGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP/action/storage_attestation","attest_author":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP/action/author_attestation","sign_citation":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP/action/citation_signature","submit_replication":"https://pith.science/pith/BM3VMQ63BVMN6IDOHVDUSPVIGP/action/replication_record"}},"created_at":"2026-07-05T09:53:48.177732+00:00","updated_at":"2026-07-05T09:53:48.177732+00:00"}