{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LB5JQMHRYX7N6DLCS5FNA2RGK3","short_pith_number":"pith:LB5JQMHR","schema_version":"1.0","canonical_sha256":"587a9830f1c5fedf0d62974ad06a2656e16156eb089cf432b113cea9060fb7b4","source":{"kind":"arxiv","id":"2402.04105","version":2},"attestation_state":"computed","paper":{"title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Angelina Wang, Ilia Sucholutsky, Thomas L. Griffiths, Xuechunzi Bai","submitted_at":"2024-02-06T15:59:23Z","abstract_excerpt":"Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases. Measuring such implicit biases can be a challenge: as LLMs become increasingly proprietary, it may not be possible to access their embeddings and apply existing bias measures; furthermore, implicit biases are primarily a concern if they affect the actual decisions that these systems make. We address both challenges by introducing two new measures of bias: LLM Implicit Bias, a prompt-based method for revealing implicit bi"},"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":"2402.04105","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-02-06T15:59:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"44024c766b53b948a1c34c0f870c6df4d5f9eb5ea2ba1c2602b7afcd8c48b030","abstract_canon_sha256":"8e1f66628525fda722630725150ac139061cc95c47ccd78e5398f82bb21730bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:22.368188Z","signature_b64":"OeK/WqfP+TfA4+hhwXE1p+AR66eaKJs/6waWyA7XXKcbn5F35vOzrkIql2BhgbEuQwNJW61BA9BEzT7/5avnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"587a9830f1c5fedf0d62974ad06a2656e16156eb089cf432b113cea9060fb7b4","last_reissued_at":"2026-07-05T08:22:22.367726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:22.367726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Angelina Wang, Ilia Sucholutsky, Thomas L. Griffiths, Xuechunzi Bai","submitted_at":"2024-02-06T15:59:23Z","abstract_excerpt":"Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases. Measuring such implicit biases can be a challenge: as LLMs become increasingly proprietary, it may not be possible to access their embeddings and apply existing bias measures; furthermore, implicit biases are primarily a concern if they affect the actual decisions that these systems make. We address both challenges by introducing two new measures of bias: LLM Implicit Bias, a prompt-based method for revealing implicit bi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04105","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/2402.04105/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":"2402.04105","created_at":"2026-07-05T08:22:22.367778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04105v2","created_at":"2026-07-05T08:22:22.367778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04105","created_at":"2026-07-05T08:22:22.367778+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB5JQMHRYX7N","created_at":"2026-07-05T08:22:22.367778+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB5JQMHRYX7N6DLC","created_at":"2026-07-05T08:22:22.367778+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB5JQMHR","created_at":"2026-07-05T08:22:22.367778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05874","citing_title":"Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22771","citing_title":"Reducing Political Manipulation with Consistency Training","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2408.09049","citing_title":"Inertia in Moral and Value Judgments of Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04419","citing_title":"Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22771","citing_title":"Reducing Political Manipulation with Consistency Training","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17228","citing_title":"Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11206","citing_title":"Evalet: Evaluating Large Language Models through Functional Fragmentation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18038","citing_title":"First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08963","citing_title":"Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21152","citing_title":"Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3","json":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3.json","graph_json":"https://pith.science/api/pith-number/LB5JQMHRYX7N6DLCS5FNA2RGK3/graph.json","events_json":"https://pith.science/api/pith-number/LB5JQMHRYX7N6DLCS5FNA2RGK3/events.json","paper":"https://pith.science/paper/LB5JQMHR"},"agent_actions":{"view_html":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3","download_json":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3.json","view_paper":"https://pith.science/paper/LB5JQMHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04105&json=true","fetch_graph":"https://pith.science/api/pith-number/LB5JQMHRYX7N6DLCS5FNA2RGK3/graph.json","fetch_events":"https://pith.science/api/pith-number/LB5JQMHRYX7N6DLCS5FNA2RGK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3/action/storage_attestation","attest_author":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3/action/author_attestation","sign_citation":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3/action/citation_signature","submit_replication":"https://pith.science/pith/LB5JQMHRYX7N6DLCS5FNA2RGK3/action/replication_record"}},"created_at":"2026-07-05T08:22:22.367778+00:00","updated_at":"2026-07-05T08:22:22.367778+00:00"}