{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7PVNBMB2UXJ5LFRDLC5TUEHANM","short_pith_number":"pith:7PVNBMB2","schema_version":"1.0","canonical_sha256":"fbead0b03aa5d3d5962358bb3a10e06b34eb88e90126585c835d240aa8840132","source":{"kind":"arxiv","id":"2507.01019","version":1},"attestation_state":"computed","paper":{"title":"MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Asli Akalin, Cole Huang, Imran Mirza, Ishwara Vasista, Kevin Zhu, Rohan Patil, Sean O'Brien","submitted_at":"2025-04-10T19:16:40Z","abstract_excerpt":"Multi-agent systems, which consist of multiple AI models interacting within a shared environment, are increasingly used for persona-based interactions. However, if not carefully designed, these systems can reinforce implicit biases in large language models (LLMs), raising concerns about fairness and equitable representation. We present MALIBU, a novel benchmark developed to assess the degree to which LLM-based multi-agent systems implicitly reinforce social biases and stereotypes. MALIBU evaluates bias in LLM-based multi-agent systems through scenario-based assessments. AI models complete task"},"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":"2507.01019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T19:16:40Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"bf9b05f69d0e99755b34d33d62d52f8d27f76169fb4819b6b6ed955b03fcc7e0","abstract_canon_sha256":"93b33168527ea6f65119e9904aa61b0bd950e39621cf94a963908a717622e53a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:23.864444Z","signature_b64":"C1NSK0ZQHFxwZPtyeEA+FNFpAyAhRpMjaH6XUOzIA7JNc/5dRuppqThiGvAmNuDYzCoIbeWOxJs8vuVF1+rbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbead0b03aa5d3d5962358bb3a10e06b34eb88e90126585c835d240aa8840132","last_reissued_at":"2026-07-05T11:30:23.863932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:23.863932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Asli Akalin, Cole Huang, Imran Mirza, Ishwara Vasista, Kevin Zhu, Rohan Patil, Sean O'Brien","submitted_at":"2025-04-10T19:16:40Z","abstract_excerpt":"Multi-agent systems, which consist of multiple AI models interacting within a shared environment, are increasingly used for persona-based interactions. However, if not carefully designed, these systems can reinforce implicit biases in large language models (LLMs), raising concerns about fairness and equitable representation. We present MALIBU, a novel benchmark developed to assess the degree to which LLM-based multi-agent systems implicitly reinforce social biases and stereotypes. MALIBU evaluates bias in LLM-based multi-agent systems through scenario-based assessments. AI models complete task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01019","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/2507.01019/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":"2507.01019","created_at":"2026-07-05T11:30:23.863992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01019v1","created_at":"2026-07-05T11:30:23.863992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01019","created_at":"2026-07-05T11:30:23.863992+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PVNBMB2UXJ5","created_at":"2026-07-05T11:30:23.863992+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PVNBMB2UXJ5LFRD","created_at":"2026-07-05T11:30:23.863992+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PVNBMB2","created_at":"2026-07-05T11:30:23.863992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13103","citing_title":"Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM","json":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM.json","graph_json":"https://pith.science/api/pith-number/7PVNBMB2UXJ5LFRDLC5TUEHANM/graph.json","events_json":"https://pith.science/api/pith-number/7PVNBMB2UXJ5LFRDLC5TUEHANM/events.json","paper":"https://pith.science/paper/7PVNBMB2"},"agent_actions":{"view_html":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM","download_json":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM.json","view_paper":"https://pith.science/paper/7PVNBMB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01019&json=true","fetch_graph":"https://pith.science/api/pith-number/7PVNBMB2UXJ5LFRDLC5TUEHANM/graph.json","fetch_events":"https://pith.science/api/pith-number/7PVNBMB2UXJ5LFRDLC5TUEHANM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM/action/storage_attestation","attest_author":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM/action/author_attestation","sign_citation":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM/action/citation_signature","submit_replication":"https://pith.science/pith/7PVNBMB2UXJ5LFRDLC5TUEHANM/action/replication_record"}},"created_at":"2026-07-05T11:30:23.863992+00:00","updated_at":"2026-07-05T11:30:23.863992+00:00"}