{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SRGS63IMETIO5LY3HARERKNQQM","short_pith_number":"pith:SRGS63IM","schema_version":"1.0","canonical_sha256":"944d2f6d0c24d0eeaf1b382248a9b0831542be7ea5eabf05699d5bbab6b54788","source":{"kind":"arxiv","id":"2311.08592","version":2},"attestation_state":"computed","paper":{"title":"AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bhaktipriya Radharapu, Kevin Robinson, Lora Aroyo, Preethi Lahoti","submitted_at":"2023-11-14T23:28:23Z","abstract_excerpt":"Adversarial testing of large language models (LLMs) is crucial for their safe and responsible deployment. We introduce a novel approach for automated generation of adversarial evaluation datasets to test the safety of LLM generations on new downstream applications. We call it AI-assisted Red-Teaming (AART) - an automated alternative to current manual red-teaming efforts. AART offers a data generation and augmentation pipeline of reusable and customizable recipes that reduce human effort significantly and enable integration of adversarial testing earlier in new product development. AART generat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.08592","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-11-14T23:28:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1b06653f9f0bac302a1c60817765c3d4ad569eca0ccc80df58c24da460952640","abstract_canon_sha256":"ac02a829707acd0969af7eb65b14cd79ac4fc1bc942ff411022453c4c4feedde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:31.586780Z","signature_b64":"eC7eGoYmn2CFkCbIyrObjQZ5ob/Zwzl18dPa90Dhhg0QPm2WU2J8xQuaLDvRi67py2JCWVUJNBB9ykr+fYIyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"944d2f6d0c24d0eeaf1b382248a9b0831542be7ea5eabf05699d5bbab6b54788","last_reissued_at":"2026-07-05T07:18:31.586262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:31.586262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bhaktipriya Radharapu, Kevin Robinson, Lora Aroyo, Preethi Lahoti","submitted_at":"2023-11-14T23:28:23Z","abstract_excerpt":"Adversarial testing of large language models (LLMs) is crucial for their safe and responsible deployment. We introduce a novel approach for automated generation of adversarial evaluation datasets to test the safety of LLM generations on new downstream applications. We call it AI-assisted Red-Teaming (AART) - an automated alternative to current manual red-teaming efforts. AART offers a data generation and augmentation pipeline of reusable and customizable recipes that reduce human effort significantly and enable integration of adversarial testing earlier in new product development. AART generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08592","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/2311.08592/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.08592","created_at":"2026-07-05T07:18:31.586323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08592v2","created_at":"2026-07-05T07:18:31.586323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08592","created_at":"2026-07-05T07:18:31.586323+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRGS63IMETIO","created_at":"2026-07-05T07:18:31.586323+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRGS63IMETIO5LY3","created_at":"2026-07-05T07:18:31.586323+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRGS63IM","created_at":"2026-07-05T07:18:31.586323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.21772","citing_title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2509.10546","citing_title":"Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM","json":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM.json","graph_json":"https://pith.science/api/pith-number/SRGS63IMETIO5LY3HARERKNQQM/graph.json","events_json":"https://pith.science/api/pith-number/SRGS63IMETIO5LY3HARERKNQQM/events.json","paper":"https://pith.science/paper/SRGS63IM"},"agent_actions":{"view_html":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM","download_json":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM.json","view_paper":"https://pith.science/paper/SRGS63IM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08592&json=true","fetch_graph":"https://pith.science/api/pith-number/SRGS63IMETIO5LY3HARERKNQQM/graph.json","fetch_events":"https://pith.science/api/pith-number/SRGS63IMETIO5LY3HARERKNQQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM/action/storage_attestation","attest_author":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM/action/author_attestation","sign_citation":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM/action/citation_signature","submit_replication":"https://pith.science/pith/SRGS63IMETIO5LY3HARERKNQQM/action/replication_record"}},"created_at":"2026-07-05T07:18:31.586323+00:00","updated_at":"2026-07-05T07:18:31.586323+00:00"}