{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XDJ5BKN4NDDK2UXW3ZECAXL77X","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":"8657ca1a4eba353b3bf5dbc7d2b408793598fe3e0bd07b93b972d2dce8c13968","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T20:20:20Z","title_canon_sha256":"c1003dbb72a9442b2c26446005b466f86c9a92cf5ff16dc4df4be2b07bba7fdd"},"schema_version":"1.0","source":{"id":"2501.14073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14073","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14073v2","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14073","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"XDJ5BKN4NDDK","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"XDJ5BKN4NDDK2UXW","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"XDJ5BKN4","created_at":"2026-07-05T10:15:48Z"}],"graph_snapshots":[{"event_id":"sha256:f44197a56ddd3baf636d7b6edc703200d13b6d50cc8e03da56e606a85cf9d9ce","target":"graph","created_at":"2026-07-05T10:15:48Z","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/2501.14073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) have been deployed in various real-world settings, concerns about the harm they may propagate have grown. Various jailbreaking techniques have been developed to expose the vulnerabilities of these models and improve their safety. This work reveals that many state-of-the-art LLMs are vulnerable to malicious requests hidden behind scientific language. Specifically, our experiments with GPT4o, GPT4o-mini, GPT-4, LLama3-405B-Instruct, Llama3-70B-Instruct, Cohere, Gemini models demonstrate that, the models' biases and toxicity substantially increase when prompted wit","authors_text":"Dilek Hakkani-T\\\"ur, Hao Peng, Neeraja Kirtane, Yubin Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T20:20:20Z","title":"LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14073","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:df57db5011578addc081a986931dfd87a12164f2317bf1606e9d93b9fc6c5fc7","target":"record","created_at":"2026-07-05T10:15:48Z","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":"8657ca1a4eba353b3bf5dbc7d2b408793598fe3e0bd07b93b972d2dce8c13968","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T20:20:20Z","title_canon_sha256":"c1003dbb72a9442b2c26446005b466f86c9a92cf5ff16dc4df4be2b07bba7fdd"},"schema_version":"1.0","source":{"id":"2501.14073","kind":"arxiv","version":2}},"canonical_sha256":"b8d3d0a9bc68c6ad52f6de48205d7ffdcffc7a2d7993cb1d1d198039e1784c03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8d3d0a9bc68c6ad52f6de48205d7ffdcffc7a2d7993cb1d1d198039e1784c03","first_computed_at":"2026-07-05T10:15:48.492022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:48.492022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tqImI/eQhhYpfLlr2sTkdVGDFoFiw/iFsaxOK7u5Hn4AomUa6U+qSkHWiiLSkpNMD6c4wGYdtO/PO8UiI1urCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:48.492546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df57db5011578addc081a986931dfd87a12164f2317bf1606e9d93b9fc6c5fc7","sha256:f44197a56ddd3baf636d7b6edc703200d13b6d50cc8e03da56e606a85cf9d9ce"],"state_sha256":"42eb191f4f2e4f6adc4dd62b92fa49390a1b15048a1524c46ffd11cd76d9ed67"}