{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LRTMBMDMIEP7AFPPMDNYGEWX5S","short_pith_number":"pith:LRTMBMDM","canonical_record":{"source":{"id":"2402.08679","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:58:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0d18948850546066965693c19689741cac5af9242b9dd69296f72797f7932182","abstract_canon_sha256":"c287f41d86e25e82860946a778ce050e3c6d6f431a3413d7a1a4a7564190efe4"},"schema_version":"1.0"},"canonical_sha256":"5c66c0b06c411ff015ef60db8312d7ecbe372f51bd01c441f00826902aaeb512","source":{"kind":"arxiv","id":"2402.08679","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08679","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08679v2","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08679","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_12","alias_value":"LRTMBMDMIEP7","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"LRTMBMDMIEP7AFPP","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"LRTMBMDM","created_at":"2026-07-05T08:28:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LRTMBMDMIEP7AFPPMDNYGEWX5S","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08679","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:58:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0d18948850546066965693c19689741cac5af9242b9dd69296f72797f7932182","abstract_canon_sha256":"c287f41d86e25e82860946a778ce050e3c6d6f431a3413d7a1a4a7564190efe4"},"schema_version":"1.0"},"canonical_sha256":"5c66c0b06c411ff015ef60db8312d7ecbe372f51bd01c441f00826902aaeb512","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:38.092691Z","signature_b64":"yeUdVMj9EVJ+KsvHDbRywXTq8zUKKzBu8P8Z+1sG9NCOTJHbuX7L/APt2VAJvbLTskOr49U/M4qT2FrL0EYOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c66c0b06c411ff015ef60db8312d7ecbe372f51bd01c441f00826902aaeb512","last_reissued_at":"2026-07-05T08:28:38.092265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:38.092265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08679","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mcfRXmiFUK5PhbYxNViKU7wmVUzaUjP/psHsil3ENWn2zlcVLT+SpF8xW7+CG4EzOGQubLoJdULtR/k16fLJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:32:48.353822Z"},"content_sha256":"312a439140395493119c5e21d5349a28e8217639976de69da791b33f5dcb51d0","schema_version":"1.0","event_id":"sha256:312a439140395493119c5e21d5349a28e8217639976de69da791b33f5dcb51d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LRTMBMDMIEP7AFPPMDNYGEWX5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bin Hu, Fangxu Yu, Huan Zhang, Lianhui Qin, Xingang Guo","submitted_at":"2024-02-13T18:58:48Z","abstract_excerpt":"Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with diverse attributes, such as contextual coherence and sentiment/stylistic variations, and hence it is beneficial to study controllable jailbreaking, i.e. how to enforce control on LLM attacks. In this paper, we formally formulate the controllable attack generation problem, and build a novel connection between this problem and controllable text generation, a well-explored topic of natural language processing. Based on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08679","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/2402.08679/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":"2026-07-05T08:28:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PMD5D/FDLF2ShI9xKzOIL/s7EYqe6waqkcxdWw8GeYpSKhB0Gv+tBmTrjh1ZDhCpP2KYrtiSEmlXV++RrkAQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:32:48.354344Z"},"content_sha256":"e4d2989a8b2399c02434bb235d3ddea0b52154b5e48c2c895100f3c6fde08acc","schema_version":"1.0","event_id":"sha256:e4d2989a8b2399c02434bb235d3ddea0b52154b5e48c2c895100f3c6fde08acc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRTMBMDMIEP7AFPPMDNYGEWX5S/bundle.json","state_url":"https://pith.science/pith/LRTMBMDMIEP7AFPPMDNYGEWX5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRTMBMDMIEP7AFPPMDNYGEWX5S/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":"2026-08-07T11:32:48Z","links":{"resolver":"https://pith.science/pith/LRTMBMDMIEP7AFPPMDNYGEWX5S","bundle":"https://pith.science/pith/LRTMBMDMIEP7AFPPMDNYGEWX5S/bundle.json","state":"https://pith.science/pith/LRTMBMDMIEP7AFPPMDNYGEWX5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRTMBMDMIEP7AFPPMDNYGEWX5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LRTMBMDMIEP7AFPPMDNYGEWX5S","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":"c287f41d86e25e82860946a778ce050e3c6d6f431a3413d7a1a4a7564190efe4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:58:48Z","title_canon_sha256":"0d18948850546066965693c19689741cac5af9242b9dd69296f72797f7932182"},"schema_version":"1.0","source":{"id":"2402.08679","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08679","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08679v2","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08679","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_12","alias_value":"LRTMBMDMIEP7","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"LRTMBMDMIEP7AFPP","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"LRTMBMDM","created_at":"2026-07-05T08:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:e4d2989a8b2399c02434bb235d3ddea0b52154b5e48c2c895100f3c6fde08acc","target":"graph","created_at":"2026-07-05T08:28:38Z","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/2402.08679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with diverse attributes, such as contextual coherence and sentiment/stylistic variations, and hence it is beneficial to study controllable jailbreaking, i.e. how to enforce control on LLM attacks. In this paper, we formally formulate the controllable attack generation problem, and build a novel connection between this problem and controllable text generation, a well-explored topic of natural language processing. Based on th","authors_text":"Bin Hu, Fangxu Yu, Huan Zhang, Lianhui Qin, Xingang Guo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:58:48Z","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08679","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":"sha256:312a439140395493119c5e21d5349a28e8217639976de69da791b33f5dcb51d0","target":"record","created_at":"2026-07-05T08:28:38Z","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":"c287f41d86e25e82860946a778ce050e3c6d6f431a3413d7a1a4a7564190efe4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:58:48Z","title_canon_sha256":"0d18948850546066965693c19689741cac5af9242b9dd69296f72797f7932182"},"schema_version":"1.0","source":{"id":"2402.08679","kind":"arxiv","version":2}},"canonical_sha256":"5c66c0b06c411ff015ef60db8312d7ecbe372f51bd01c441f00826902aaeb512","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c66c0b06c411ff015ef60db8312d7ecbe372f51bd01c441f00826902aaeb512","first_computed_at":"2026-07-05T08:28:38.092265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:38.092265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yeUdVMj9EVJ+KsvHDbRywXTq8zUKKzBu8P8Z+1sG9NCOTJHbuX7L/APt2VAJvbLTskOr49U/M4qT2FrL0EYOAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:38.092691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08679","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:312a439140395493119c5e21d5349a28e8217639976de69da791b33f5dcb51d0","sha256:e4d2989a8b2399c02434bb235d3ddea0b52154b5e48c2c895100f3c6fde08acc"],"state_sha256":"b82bcdd64f2a69870aedaa32ad4c09780a6c17ef4a721518d35b3016377e5a07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkb+J+bF9ieOcq/JWE0CoMH9xEO2iuNPHa37O7d16GYIQ7kZJ33udWFAjNRqdsGwPKR0liMCSr0fl32rNEXiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T11:32:48.358095Z","bundle_sha256":"14c63f1d6f739e7a0ca70a73622364bbd52284e495e2a7c259c27f9d5a6c0d83"}}