{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TJPNG5VEDMUUIS7FNJRRYZ3POK","short_pith_number":"pith:TJPNG5VE","canonical_record":{"source":{"id":"2307.08487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-17T13:49:52Z","cross_cats_sorted":[],"title_canon_sha256":"d0221eadd7c5eb68406adaebb86c09fdd918f0c750dd996341e04dbb3371f304","abstract_canon_sha256":"2af0b380443da229cd612d2b415f530e77bfd8449f3e2904cea3ac0f55fdfb5b"},"schema_version":"1.0"},"canonical_sha256":"9a5ed376a41b29444be56a631c676f72bb0dfc0559c8fcd662d3f6016354f466","source":{"kind":"arxiv","id":"2307.08487","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.08487","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"arxiv_version","alias_value":"2307.08487v3","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08487","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"pith_short_12","alias_value":"TJPNG5VEDMUU","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"pith_short_16","alias_value":"TJPNG5VEDMUUIS7F","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"pith_short_8","alias_value":"TJPNG5VE","created_at":"2026-07-05T06:45:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TJPNG5VEDMUUIS7FNJRRYZ3POK","target":"record","payload":{"canonical_record":{"source":{"id":"2307.08487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-17T13:49:52Z","cross_cats_sorted":[],"title_canon_sha256":"d0221eadd7c5eb68406adaebb86c09fdd918f0c750dd996341e04dbb3371f304","abstract_canon_sha256":"2af0b380443da229cd612d2b415f530e77bfd8449f3e2904cea3ac0f55fdfb5b"},"schema_version":"1.0"},"canonical_sha256":"9a5ed376a41b29444be56a631c676f72bb0dfc0559c8fcd662d3f6016354f466","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:18.835944Z","signature_b64":"H/OlTTC0lsT8SX3ltBLxZnazW1QC6lTU6BoAbh3psx1nrIBbLgUhthgI/t6GnXOgtutowDMktyhofn7YkDQ9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a5ed376a41b29444be56a631c676f72bb0dfc0559c8fcd662d3f6016354f466","last_reissued_at":"2026-07-05T06:45:18.835444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:18.835444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.08487","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HUroO177cDblaKBZzrl1Wa8Lz45EQX+MpvLdvA0HkCj+IvDr+gWKWzhaVXhIAvs+BXyhCkfX3AVUQpwNb46YBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:14:18.090262Z"},"content_sha256":"cbd812a1fac663bb234e19f8a90b78a17f3c2f48dcf880089f260eac163a197e","schema_version":"1.0","event_id":"sha256:cbd812a1fac663bb234e19f8a90b78a17f3c2f48dcf880089f260eac163a197e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TJPNG5VEDMUUIS7FNJRRYZ3POK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anqi Li, Hongliang He, Huachuan Qiu, Shuai Zhang, Zhenzhong Lan","submitted_at":"2023-07-17T13:49:52Z","abstract_excerpt":"Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness in following instructions, thereby impacting its overall performance in completing tasks. Previous benchmarks for jailbreaking LLMs have primarily focused on evaluating the safety of the models without considering their robustness. In this paper, we propose a benchmark that assesses both the safety and robustness of LLMs, emphasizing the need for a balanced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08487","kind":"arxiv","version":3},"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/2307.08487/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eiDlR75yXdioZLUPCX8aujw1rgT7fmcQ259uT56l6Z3Xa7uyLN7H9eXM0/rKD+CrIW8Y9wFZcd5ZqAWoqgYxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:14:18.090638Z"},"content_sha256":"e68209efc552755a989748ca415cd460b0120f62de1dc98ea322b77629ec7693","schema_version":"1.0","event_id":"sha256:e68209efc552755a989748ca415cd460b0120f62de1dc98ea322b77629ec7693"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJPNG5VEDMUUIS7FNJRRYZ3POK/bundle.json","state_url":"https://pith.science/pith/TJPNG5VEDMUUIS7FNJRRYZ3POK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJPNG5VEDMUUIS7FNJRRYZ3POK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T15:14:18Z","links":{"resolver":"https://pith.science/pith/TJPNG5VEDMUUIS7FNJRRYZ3POK","bundle":"https://pith.science/pith/TJPNG5VEDMUUIS7FNJRRYZ3POK/bundle.json","state":"https://pith.science/pith/TJPNG5VEDMUUIS7FNJRRYZ3POK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJPNG5VEDMUUIS7FNJRRYZ3POK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TJPNG5VEDMUUIS7FNJRRYZ3POK","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":"2af0b380443da229cd612d2b415f530e77bfd8449f3e2904cea3ac0f55fdfb5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-17T13:49:52Z","title_canon_sha256":"d0221eadd7c5eb68406adaebb86c09fdd918f0c750dd996341e04dbb3371f304"},"schema_version":"1.0","source":{"id":"2307.08487","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.08487","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"arxiv_version","alias_value":"2307.08487v3","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08487","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"pith_short_12","alias_value":"TJPNG5VEDMUU","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"pith_short_16","alias_value":"TJPNG5VEDMUUIS7F","created_at":"2026-07-05T06:45:18Z"},{"alias_kind":"pith_short_8","alias_value":"TJPNG5VE","created_at":"2026-07-05T06:45:18Z"}],"graph_snapshots":[{"event_id":"sha256:e68209efc552755a989748ca415cd460b0120f62de1dc98ea322b77629ec7693","target":"graph","created_at":"2026-07-05T06:45:18Z","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/2307.08487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness in following instructions, thereby impacting its overall performance in completing tasks. Previous benchmarks for jailbreaking LLMs have primarily focused on evaluating the safety of the models without considering their robustness. In this paper, we propose a benchmark that assesses both the safety and robustness of LLMs, emphasizing the need for a balanced","authors_text":"Anqi Li, Hongliang He, Huachuan Qiu, Shuai Zhang, Zhenzhong Lan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-17T13:49:52Z","title":"Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08487","kind":"arxiv","version":3},"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:cbd812a1fac663bb234e19f8a90b78a17f3c2f48dcf880089f260eac163a197e","target":"record","created_at":"2026-07-05T06:45:18Z","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":"2af0b380443da229cd612d2b415f530e77bfd8449f3e2904cea3ac0f55fdfb5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-17T13:49:52Z","title_canon_sha256":"d0221eadd7c5eb68406adaebb86c09fdd918f0c750dd996341e04dbb3371f304"},"schema_version":"1.0","source":{"id":"2307.08487","kind":"arxiv","version":3}},"canonical_sha256":"9a5ed376a41b29444be56a631c676f72bb0dfc0559c8fcd662d3f6016354f466","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a5ed376a41b29444be56a631c676f72bb0dfc0559c8fcd662d3f6016354f466","first_computed_at":"2026-07-05T06:45:18.835444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:18.835444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H/OlTTC0lsT8SX3ltBLxZnazW1QC6lTU6BoAbh3psx1nrIBbLgUhthgI/t6GnXOgtutowDMktyhofn7YkDQ9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:18.835944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.08487","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbd812a1fac663bb234e19f8a90b78a17f3c2f48dcf880089f260eac163a197e","sha256:e68209efc552755a989748ca415cd460b0120f62de1dc98ea322b77629ec7693"],"state_sha256":"27e349afe68303aaf80b98155f387e88a3b4faeded222bf360fa0408a8189825"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CjFJBSRGnXHXiCQBR7+yr5h+NfjkHe0rZ6qwHgkt7t7g7mLrm86fjENtHrdUWvZZuJol5f89sDmbMAgjISHpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:14:18.092485Z","bundle_sha256":"1b5625b0a7771bdf9df374bf336fd5033eef84e88ef6348179dc39654a5ee08e"}}