{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZKEHUJMKUW2VW2PNLWIMPLUWUE","short_pith_number":"pith:ZKEHUJMK","schema_version":"1.0","canonical_sha256":"ca887a258aa5b55b69ed5d90c7ae96a1251760d039a68e9104300807117bf3d9","source":{"kind":"arxiv","id":"2406.11654","version":1},"attestation_state":"computed","paper":{"title":"Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rishabh Bhardwaj, Soujanya Poria, Vernon Toh Yan Han","submitted_at":"2024-06-17T15:36:14Z","abstract_excerpt":"We propose Ruby Teaming, a method that improves on Rainbow Teaming by including a memory cache as its third dimension. The memory dimension provides cues to the mutator to yield better-quality prompts, both in terms of attack success rate (ASR) and quality diversity. The prompt archive generated by Ruby Teaming has an ASR of 74%, which is 20% higher than the baseline. In terms of quality diversity, Ruby Teaming outperforms Rainbow Teaming by 6% and 3% on Shannon's Evenness Index (SEI) and Simpson's Diversity Index (SDI), respectively."},"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":"2406.11654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"3016c35213d59c5c3ba7536d6ad31dcff8d66ff14df2c7bafef9bc07d974345c","abstract_canon_sha256":"b7fa81659eeb1c2a0b028c34584f155cbe39fc9c792555017158c61287368947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:55.957307Z","signature_b64":"uaCXIyaC1RuqWuFs5V8pVmtxUsMFO42zaMw6AUZY3kWQreA7dNfg5aHR4UPzJ8HsWroM6La+Mm5RfTfOxbCOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca887a258aa5b55b69ed5d90c7ae96a1251760d039a68e9104300807117bf3d9","last_reissued_at":"2026-07-05T08:32:55.956806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:55.956806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rishabh Bhardwaj, Soujanya Poria, Vernon Toh Yan Han","submitted_at":"2024-06-17T15:36:14Z","abstract_excerpt":"We propose Ruby Teaming, a method that improves on Rainbow Teaming by including a memory cache as its third dimension. The memory dimension provides cues to the mutator to yield better-quality prompts, both in terms of attack success rate (ASR) and quality diversity. The prompt archive generated by Ruby Teaming has an ASR of 74%, which is 20% higher than the baseline. In terms of quality diversity, Ruby Teaming outperforms Rainbow Teaming by 6% and 3% on Shannon's Evenness Index (SEI) and Simpson's Diversity Index (SDI), respectively."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11654","kind":"arxiv","version":1},"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/2406.11654/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":"2406.11654","created_at":"2026-07-05T08:32:55.956869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11654v1","created_at":"2026-07-05T08:32:55.956869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11654","created_at":"2026-07-05T08:32:55.956869+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKEHUJMKUW2V","created_at":"2026-07-05T08:32:55.956869+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKEHUJMKUW2VW2PN","created_at":"2026-07-05T08:32:55.956869+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKEHUJMK","created_at":"2026-07-05T08:32:55.956869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24166","citing_title":"Distributed Quality-Diversity Search for Toxicity in Large Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05682","citing_title":"PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05682","citing_title":"PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00553","citing_title":"Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE","json":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE.json","graph_json":"https://pith.science/api/pith-number/ZKEHUJMKUW2VW2PNLWIMPLUWUE/graph.json","events_json":"https://pith.science/api/pith-number/ZKEHUJMKUW2VW2PNLWIMPLUWUE/events.json","paper":"https://pith.science/paper/ZKEHUJMK"},"agent_actions":{"view_html":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE","download_json":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE.json","view_paper":"https://pith.science/paper/ZKEHUJMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11654&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKEHUJMKUW2VW2PNLWIMPLUWUE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKEHUJMKUW2VW2PNLWIMPLUWUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE/action/storage_attestation","attest_author":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE/action/author_attestation","sign_citation":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE/action/citation_signature","submit_replication":"https://pith.science/pith/ZKEHUJMKUW2VW2PNLWIMPLUWUE/action/replication_record"}},"created_at":"2026-07-05T08:32:55.956869+00:00","updated_at":"2026-07-05T08:32:55.956869+00:00"}