{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PFJ5JRHELLFYYDJI3ZWMP2KOKS","short_pith_number":"pith:PFJ5JRHE","schema_version":"1.0","canonical_sha256":"7953d4c4e45acb8c0d28de6cc7e94e549552d34ab7b5ab43bfeae6cb1d891938","source":{"kind":"arxiv","id":"2407.18369","version":1},"attestation_state":"computed","paper":{"title":"AI Safety in Generative AI Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Chen Wang, Jaymari Chua, Lina Yao, Shiyi Yang, Yun Li","submitted_at":"2024-07-06T09:00:18Z","abstract_excerpt":"Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models. This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective: specific and technical. In this survey, we explore the background and motivation for the identified harms and risks in the context of LLMs being generative language models; our survey differentiates by e"},"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":"2407.18369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-07-06T09:00:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dfbbb99ed8e4aed4e91f71f5ea1a0c7e3610933f4c678c059f01e5728d577e98","abstract_canon_sha256":"716feb0f2328a192b62fce7114a81f6da59def7a079b31d39e62022c82b3c711"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:48.663531Z","signature_b64":"7+c8yhMF7ftXpG0zd1bTaVOAbIIOC2SShnu8sY7AZG4X+Ys64vlBf3Fkte/ZjYFbNLa2hTnoCk2KXd/GKHWiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7953d4c4e45acb8c0d28de6cc7e94e549552d34ab7b5ab43bfeae6cb1d891938","last_reissued_at":"2026-07-05T08:48:48.663045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:48.663045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Safety in Generative AI Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Chen Wang, Jaymari Chua, Lina Yao, Shiyi Yang, Yun Li","submitted_at":"2024-07-06T09:00:18Z","abstract_excerpt":"Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models. This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective: specific and technical. In this survey, we explore the background and motivation for the identified harms and risks in the context of LLMs being generative language models; our survey differentiates by e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18369","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/2407.18369/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":"2407.18369","created_at":"2026-07-05T08:48:48.663103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18369v1","created_at":"2026-07-05T08:48:48.663103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18369","created_at":"2026-07-05T08:48:48.663103+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFJ5JRHELLFY","created_at":"2026-07-05T08:48:48.663103+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFJ5JRHELLFYYDJI","created_at":"2026-07-05T08:48:48.663103+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFJ5JRHE","created_at":"2026-07-05T08:48:48.663103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.20102","citing_title":"BarrierSteer: LLM Safety via Learning Barrier Steering","ref_index":4,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16746","citing_title":"State Contamination in Memory-Augmented LLM Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21654","citing_title":"Limitations on Accurate, Trusted, Human-level Reasoning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS","json":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS.json","graph_json":"https://pith.science/api/pith-number/PFJ5JRHELLFYYDJI3ZWMP2KOKS/graph.json","events_json":"https://pith.science/api/pith-number/PFJ5JRHELLFYYDJI3ZWMP2KOKS/events.json","paper":"https://pith.science/paper/PFJ5JRHE"},"agent_actions":{"view_html":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS","download_json":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS.json","view_paper":"https://pith.science/paper/PFJ5JRHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18369&json=true","fetch_graph":"https://pith.science/api/pith-number/PFJ5JRHELLFYYDJI3ZWMP2KOKS/graph.json","fetch_events":"https://pith.science/api/pith-number/PFJ5JRHELLFYYDJI3ZWMP2KOKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS/action/storage_attestation","attest_author":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS/action/author_attestation","sign_citation":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS/action/citation_signature","submit_replication":"https://pith.science/pith/PFJ5JRHELLFYYDJI3ZWMP2KOKS/action/replication_record"}},"created_at":"2026-07-05T08:48:48.663103+00:00","updated_at":"2026-07-05T08:48:48.663103+00:00"}