{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VOJHMLIVYG4NSJSENGV35C7GJJ","short_pith_number":"pith:VOJHMLIV","schema_version":"1.0","canonical_sha256":"ab92762d15c1b8d9264469abbe8be64a6528804dc5798f23f3b284d30e3cf83e","source":{"kind":"arxiv","id":"2306.11507","version":1},"attestation_state":"computed","paper":{"title":"TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lichao Sun, Philip S. Y, Qihui Zhang, Yue Huang","submitted_at":"2023-06-20T12:53:39Z","abstract_excerpt":"Large Language Models (LLMs) such as ChatGPT, have gained significant attention due to their impressive natural language processing capabilities. It is crucial to prioritize human-centered principles when utilizing these models. Safeguarding the ethical and moral compliance of LLMs is of utmost importance. However, individual ethical issues have not been well studied on the latest LLMs. Therefore, this study aims to address these gaps by introducing a new benchmark -- TrustGPT. TrustGPT provides a comprehensive evaluation of LLMs in three crucial areas: toxicity, bias, and value-alignment. Ini"},"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":"2306.11507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T12:53:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4ccffa37f9616d6720eb6ed9d2468a391cfa2d770229368551527d639f3d212","abstract_canon_sha256":"157e0457a5c0f25b3ba048d69e75d2600c2e4bc9934029b3ef069c4d377510a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:20.592246Z","signature_b64":"mr88aLlyXF9U2iZSl7lJ7kdru5cm2HbBZ5JzZ/dlDMrHZ1VZ6sYuiEUjtMcgq/Kdc1DTXaGMujqSFPjJB5U8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab92762d15c1b8d9264469abbe8be64a6528804dc5798f23f3b284d30e3cf83e","last_reissued_at":"2026-07-05T06:22:20.591724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:20.591724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lichao Sun, Philip S. Y, Qihui Zhang, Yue Huang","submitted_at":"2023-06-20T12:53:39Z","abstract_excerpt":"Large Language Models (LLMs) such as ChatGPT, have gained significant attention due to their impressive natural language processing capabilities. It is crucial to prioritize human-centered principles when utilizing these models. Safeguarding the ethical and moral compliance of LLMs is of utmost importance. However, individual ethical issues have not been well studied on the latest LLMs. Therefore, this study aims to address these gaps by introducing a new benchmark -- TrustGPT. TrustGPT provides a comprehensive evaluation of LLMs in three crucial areas: toxicity, bias, and value-alignment. Ini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11507","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/2306.11507/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":"2306.11507","created_at":"2026-07-05T06:22:20.591786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11507v1","created_at":"2026-07-05T06:22:20.591786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11507","created_at":"2026-07-05T06:22:20.591786+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOJHMLIVYG4N","created_at":"2026-07-05T06:22:20.591786+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOJHMLIVYG4NSJSE","created_at":"2026-07-05T06:22:20.591786+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOJHMLIV","created_at":"2026-07-05T06:22:20.591786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25476","citing_title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04389","citing_title":"Safety Is Not Universal: The Selective Safety Trap in LLM Alignment","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09803","citing_title":"Insight: Enhancing Mobile Accessibility for Blind and Visually Impaired Users with LLMs","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ","json":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ.json","graph_json":"https://pith.science/api/pith-number/VOJHMLIVYG4NSJSENGV35C7GJJ/graph.json","events_json":"https://pith.science/api/pith-number/VOJHMLIVYG4NSJSENGV35C7GJJ/events.json","paper":"https://pith.science/paper/VOJHMLIV"},"agent_actions":{"view_html":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ","download_json":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ.json","view_paper":"https://pith.science/paper/VOJHMLIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11507&json=true","fetch_graph":"https://pith.science/api/pith-number/VOJHMLIVYG4NSJSENGV35C7GJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/VOJHMLIVYG4NSJSENGV35C7GJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ/action/storage_attestation","attest_author":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ/action/author_attestation","sign_citation":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ/action/citation_signature","submit_replication":"https://pith.science/pith/VOJHMLIVYG4NSJSENGV35C7GJJ/action/replication_record"}},"created_at":"2026-07-05T06:22:20.591786+00:00","updated_at":"2026-07-05T06:22:20.591786+00:00"}