{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NQWJRJ3E3C5MH6VTGDV7PI7N3I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3dc3b07c56810161fb9348dc1ab41e971af75e20539650396689eb693c8ec85d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:33:07Z","title_canon_sha256":"1005b9c241f8e322a8bb7f2a038e053f25bfa0a77b56835b5312ebacb066cea6"},"schema_version":"1.0","source":{"id":"2311.09447","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09447","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09447v2","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09447","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"NQWJRJ3E3C5M","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"NQWJRJ3E3C5MH6VT","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"NQWJRJ3E","created_at":"2026-07-05T08:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:406c1d66f421811353b7256dfe0b3555ca6af68f834f573bae0eae3d6de3c4b6","target":"graph","created_at":"2026-07-05T08:03:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.09447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid progress in open-source Large Language Models (LLMs) is significantly driving AI development forward. However, there is still a limited understanding of their trustworthiness. Deploying these models at scale without sufficient trustworthiness can pose significant risks, highlighting the need to uncover these issues promptly. In this work, we conduct an adversarial assessment of open-source LLMs on trustworthiness, scrutinizing them across eight different aspects including toxicity, stereotypes, ethics, hallucination, fairness, sycophancy, privacy, and robustness against adversarial d","authors_text":"Boshi Wang, Huan Sun, Lingbo Mo, Muhao Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:33:07Z","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09447","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e83f6e3d2efd9db8ca87d3365ba08e88dfa60d63821f151b91377ac1821a440a","target":"record","created_at":"2026-07-05T08:03:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3dc3b07c56810161fb9348dc1ab41e971af75e20539650396689eb693c8ec85d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T23:33:07Z","title_canon_sha256":"1005b9c241f8e322a8bb7f2a038e053f25bfa0a77b56835b5312ebacb066cea6"},"schema_version":"1.0","source":{"id":"2311.09447","kind":"arxiv","version":2}},"canonical_sha256":"6c2c98a764d8bac3fab330ebf7a3edda1ece7945691efc4c40b1b3fc2cbcd023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c2c98a764d8bac3fab330ebf7a3edda1ece7945691efc4c40b1b3fc2cbcd023","first_computed_at":"2026-07-05T08:03:28.159434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:28.159434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8gAfrqeW9Y3bQtuzDC5GuU22XlJL9GipTr4Z6oDPPp6On8jJt5o0/tjTjDmrdntRqgvg4z6k4P5uv1XQ9f78Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:28.159893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09447","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e83f6e3d2efd9db8ca87d3365ba08e88dfa60d63821f151b91377ac1821a440a","sha256:406c1d66f421811353b7256dfe0b3555ca6af68f834f573bae0eae3d6de3c4b6"],"state_sha256":"31565c6297554687cb68941d2e7f3ea31ff253d7cbc6d31aafad0717146b7eea"}