{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H3DLN4AX57X3U6A3CWJVFRJGNV","short_pith_number":"pith:H3DLN4AX","canonical_record":{"source":{"id":"2408.14853","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T08:12:08Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"27be477cd850395be611dd5a4b490b1516bfab5e0caca067b40167dafc94c6d5","abstract_canon_sha256":"ee6f22d3e55150f24ad34aeb2258dfaa1f745f369e1929ec13272847e90b73d2"},"schema_version":"1.0"},"canonical_sha256":"3ec6b6f017efefba781b159352c5266d721660dbb1cbb888ae212a0f74023432","source":{"kind":"arxiv","id":"2408.14853","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14853","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14853v2","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14853","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"H3DLN4AX57X3","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"H3DLN4AX57X3U6A3","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"H3DLN4AX","created_at":"2026-07-05T10:14:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H3DLN4AX57X3U6A3CWJVFRJGNV","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14853","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T08:12:08Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"27be477cd850395be611dd5a4b490b1516bfab5e0caca067b40167dafc94c6d5","abstract_canon_sha256":"ee6f22d3e55150f24ad34aeb2258dfaa1f745f369e1929ec13272847e90b73d2"},"schema_version":"1.0"},"canonical_sha256":"3ec6b6f017efefba781b159352c5266d721660dbb1cbb888ae212a0f74023432","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:44.946132Z","signature_b64":"Abgbx1PRegh6A/FiA5SwxaWK/oP18OfAZbqB1gMDjTCE+cyaW3cQYcg6NNnXd7OasdcMtH2xO74EbuQYUEqlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ec6b6f017efefba781b159352c5266d721660dbb1cbb888ae212a0f74023432","last_reissued_at":"2026-07-05T10:14:44.945643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:44.945643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14853","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":"2026-07-05T10:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJnXUw6V4gk9Nf8Z5AfGwR1mlHtAZvFKnSHA+Ldg2JomF8IyLyV7ikpTgABSMhyo3ta1hWj4rZ+Sm1h4zOpfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:32:20.948151Z"},"content_sha256":"7283b60b80726ca1a3438fd8b4ea0bc8c9322cc65cdc354e1838079414606ef1","schema_version":"1.0","event_id":"sha256:7283b60b80726ca1a3438fd8b4ea0bc8c9322cc65cdc354e1838079414606ef1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H3DLN4AX57X3U6A3CWJVFRJGNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Atoxia: Red-teaming Large Language Models with Target Toxic Answers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Anningzhe Gao, Pengyu Cheng, Xiang Wan, Yuhao Du, Zhuo Li","submitted_at":"2024-08-27T08:12:08Z","abstract_excerpt":"Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, one can effortlessly induce LLMs to output harmful content, causing unexpected negative social impacts. This vulnerability highlights the necessity for robust LLM red-teaming strategies to identify and mitigate such risks before large-scale application. To detect specific types of risks, we propose a novel red-teaming method that $\\textbf{A}$ttacks LLMs with $\\textbf{T}$arget $\\textbf{Toxi}$c $\\textbf{A}$nswers ($\\tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14853","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/2408.14853/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":"2026-07-05T10:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ofToxLS8P9kjdW8E83M633rtJ2pp7YNYmKNXyqqsWCnJ7mRQ8jX+3KWHf/qn/PEXWcKKdV/B+BUdKXOa5tCsAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:32:20.948668Z"},"content_sha256":"f1b06277fdd8b48751f3dd98e6f7cb12f38348cedf68d06e2f98377f2f3a8f8f","schema_version":"1.0","event_id":"sha256:f1b06277fdd8b48751f3dd98e6f7cb12f38348cedf68d06e2f98377f2f3a8f8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H3DLN4AX57X3U6A3CWJVFRJGNV/bundle.json","state_url":"https://pith.science/pith/H3DLN4AX57X3U6A3CWJVFRJGNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H3DLN4AX57X3U6A3CWJVFRJGNV/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":"2026-08-15T17:32:20Z","links":{"resolver":"https://pith.science/pith/H3DLN4AX57X3U6A3CWJVFRJGNV","bundle":"https://pith.science/pith/H3DLN4AX57X3U6A3CWJVFRJGNV/bundle.json","state":"https://pith.science/pith/H3DLN4AX57X3U6A3CWJVFRJGNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H3DLN4AX57X3U6A3CWJVFRJGNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H3DLN4AX57X3U6A3CWJVFRJGNV","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":"ee6f22d3e55150f24ad34aeb2258dfaa1f745f369e1929ec13272847e90b73d2","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T08:12:08Z","title_canon_sha256":"27be477cd850395be611dd5a4b490b1516bfab5e0caca067b40167dafc94c6d5"},"schema_version":"1.0","source":{"id":"2408.14853","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14853","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14853v2","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14853","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"H3DLN4AX57X3","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"H3DLN4AX57X3U6A3","created_at":"2026-07-05T10:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"H3DLN4AX","created_at":"2026-07-05T10:14:44Z"}],"graph_snapshots":[{"event_id":"sha256:f1b06277fdd8b48751f3dd98e6f7cb12f38348cedf68d06e2f98377f2f3a8f8f","target":"graph","created_at":"2026-07-05T10:14:44Z","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/2408.14853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, one can effortlessly induce LLMs to output harmful content, causing unexpected negative social impacts. This vulnerability highlights the necessity for robust LLM red-teaming strategies to identify and mitigate such risks before large-scale application. To detect specific types of risks, we propose a novel red-teaming method that $\\textbf{A}$ttacks LLMs with $\\textbf{T}$arget $\\textbf{Toxi}$c $\\textbf{A}$nswers ($\\tex","authors_text":"Anningzhe Gao, Pengyu Cheng, Xiang Wan, Yuhao Du, Zhuo Li","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T08:12:08Z","title":"Atoxia: Red-teaming Large Language Models with Target Toxic Answers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14853","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":"sha256:7283b60b80726ca1a3438fd8b4ea0bc8c9322cc65cdc354e1838079414606ef1","target":"record","created_at":"2026-07-05T10:14:44Z","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":"ee6f22d3e55150f24ad34aeb2258dfaa1f745f369e1929ec13272847e90b73d2","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T08:12:08Z","title_canon_sha256":"27be477cd850395be611dd5a4b490b1516bfab5e0caca067b40167dafc94c6d5"},"schema_version":"1.0","source":{"id":"2408.14853","kind":"arxiv","version":2}},"canonical_sha256":"3ec6b6f017efefba781b159352c5266d721660dbb1cbb888ae212a0f74023432","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ec6b6f017efefba781b159352c5266d721660dbb1cbb888ae212a0f74023432","first_computed_at":"2026-07-05T10:14:44.945643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:44.945643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Abgbx1PRegh6A/FiA5SwxaWK/oP18OfAZbqB1gMDjTCE+cyaW3cQYcg6NNnXd7OasdcMtH2xO74EbuQYUEqlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:44.946132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14853","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7283b60b80726ca1a3438fd8b4ea0bc8c9322cc65cdc354e1838079414606ef1","sha256:f1b06277fdd8b48751f3dd98e6f7cb12f38348cedf68d06e2f98377f2f3a8f8f"],"state_sha256":"401d53e64e2760cbe402e0e0941d9b7d6613c7fc19671ae32c245e7f524668c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WgY9ZZ4Nmd0aFaokolRfAYNjoG1xNNQ+Q5272Cgs2rn9HdzHVINmELARNLCFB8DeJdBUfOR+w1pEZq8Atc0FCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:32:20.954215Z","bundle_sha256":"d3974fd9626d980e857e03171f9a7af44eb43882c1938a8d8be2270e214b8d57"}}