{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VSRHHAZ7YA45FREGT4L2BCNB6A","short_pith_number":"pith:VSRHHAZ7","schema_version":"1.0","canonical_sha256":"aca273833fc039d2c4869f17a089a1f012706a9ec05161fe9b4f27ab63906dcd","source":{"kind":"arxiv","id":"2305.11391","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andre Freitas, Changshun Wu, Dengyu Wu, Gaojie Jin, Kaiwen Cai, Mustafa A. Mustafa, Peipei Xu, Ronghui Mu, Saddek Bensalem, Sihao Wu, Wei Huang, Wenjie Ruan, Xiaowei Huang, Xingyu Zhao, Yanghao Zhang, Yi Dong, Yi Qi","submitted_at":"2023-05-19T02:41:12Z","abstract_excerpt":"Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in many industrial applications, this survey concerns their safety and trustworthiness. First, we review known vulnerabilities and limitations of the LLMs, categorising them into inherent issues, attacks, and unintended bugs. Then, we consider if and how the Verification and Validation (V&V) techniques, which have been widely developed for traditional software and"},"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":"2305.11391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-19T02:41:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"46fedd146371f8d9873b10390880dee89fa7f3814a737aa0c72f7749d5e0a811","abstract_canon_sha256":"188ae0991d92fe9e9bb082fe76779a2ca02075d38f0bfa0ad09af5cff2c11fb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:17.460570Z","signature_b64":"zy4486OLGULJe+bQYvgODBGoZmbkTg5eCrWsQlPzWrsAqsvc7fIgu2f7kNFyC02tCIHrsjFlHnHoyJvulKuqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aca273833fc039d2c4869f17a089a1f012706a9ec05161fe9b4f27ab63906dcd","last_reissued_at":"2026-07-05T06:45:17.460025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:17.460025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andre Freitas, Changshun Wu, Dengyu Wu, Gaojie Jin, Kaiwen Cai, Mustafa A. Mustafa, Peipei Xu, Ronghui Mu, Saddek Bensalem, Sihao Wu, Wei Huang, Wenjie Ruan, Xiaowei Huang, Xingyu Zhao, Yanghao Zhang, Yi Dong, Yi Qi","submitted_at":"2023-05-19T02:41:12Z","abstract_excerpt":"Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in many industrial applications, this survey concerns their safety and trustworthiness. First, we review known vulnerabilities and limitations of the LLMs, categorising them into inherent issues, attacks, and unintended bugs. Then, we consider if and how the Verification and Validation (V&V) techniques, which have been widely developed for traditional software and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11391","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/2305.11391/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":"2305.11391","created_at":"2026-07-05T06:45:17.460085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11391v2","created_at":"2026-07-05T06:45:17.460085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11391","created_at":"2026-07-05T06:45:17.460085+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSRHHAZ7YA45","created_at":"2026-07-05T06:45:17.460085+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSRHHAZ7YA45FREG","created_at":"2026-07-05T06:45:17.460085+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSRHHAZ7","created_at":"2026-07-05T06:45:17.460085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22636","citing_title":"A Multi-Source Framework for Relational Validation of Large Language Models Using Expert-Curated Encyclopedic Sources","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06423","citing_title":"Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09493","citing_title":"Policy-Aware Edge LLM-RAG Framework for Internet of Battlefield Things Mission Orchestration","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07250","citing_title":"Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A","json":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A.json","graph_json":"https://pith.science/api/pith-number/VSRHHAZ7YA45FREGT4L2BCNB6A/graph.json","events_json":"https://pith.science/api/pith-number/VSRHHAZ7YA45FREGT4L2BCNB6A/events.json","paper":"https://pith.science/paper/VSRHHAZ7"},"agent_actions":{"view_html":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A","download_json":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A.json","view_paper":"https://pith.science/paper/VSRHHAZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11391&json=true","fetch_graph":"https://pith.science/api/pith-number/VSRHHAZ7YA45FREGT4L2BCNB6A/graph.json","fetch_events":"https://pith.science/api/pith-number/VSRHHAZ7YA45FREGT4L2BCNB6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A/action/storage_attestation","attest_author":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A/action/author_attestation","sign_citation":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A/action/citation_signature","submit_replication":"https://pith.science/pith/VSRHHAZ7YA45FREGT4L2BCNB6A/action/replication_record"}},"created_at":"2026-07-05T06:45:17.460085+00:00","updated_at":"2026-07-05T06:45:17.460085+00:00"}