{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F2K7O5VVYMHB23W6XUM5UY2VQJ","short_pith_number":"pith:F2K7O5VV","schema_version":"1.0","canonical_sha256":"2e95f776b5c30e1d6edebd19da63558251a1e593e907b9aff8f6f6181f887764","source":{"kind":"arxiv","id":"2310.08780","version":1},"attestation_state":"computed","paper":{"title":"\"Im not Racist but...\": Discovering Bias in the Internal Knowledge of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abel Salinas, Fred Morstatter, Louis Penafiel, Robert McCormack","submitted_at":"2023-10-13T00:03:37Z","abstract_excerpt":"Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal biases, or stereotypes, which can adversely affect their performance in their many downstream applications. In this paper, we introduce a novel, purely prompt-based approach to uncover hidden stereotypes within any arbitrary LLM. Our approach dynamically generates a knowledge representation of internal stereotypes, enabling the identification of biases encoded wit"},"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":"2310.08780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T00:03:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c81d5f2b48e9220c7a966e62adfdc5e7af88973c2cc11b5727a4a2046e6ba5d","abstract_canon_sha256":"389820ddf3b33b33df64f93cfbd6bb9da4d9e0f37e6b1e3beed78349ef7f44e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:34.780492Z","signature_b64":"jeI4oBJ8P9hMEndh+1f3mirLd5/zBbP823x2ePhpZ2QxlRQId9HKtMuWp0l4Gnu+8yEZ9LnSDqNne5kg2sauDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e95f776b5c30e1d6edebd19da63558251a1e593e907b9aff8f6f6181f887764","last_reissued_at":"2026-07-05T07:00:34.780080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:34.780080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Im not Racist but...\": Discovering Bias in the Internal Knowledge of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abel Salinas, Fred Morstatter, Louis Penafiel, Robert McCormack","submitted_at":"2023-10-13T00:03:37Z","abstract_excerpt":"Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal biases, or stereotypes, which can adversely affect their performance in their many downstream applications. In this paper, we introduce a novel, purely prompt-based approach to uncover hidden stereotypes within any arbitrary LLM. Our approach dynamically generates a knowledge representation of internal stereotypes, enabling the identification of biases encoded wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08780","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/2310.08780/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":"2310.08780","created_at":"2026-07-05T07:00:34.780132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08780v1","created_at":"2026-07-05T07:00:34.780132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08780","created_at":"2026-07-05T07:00:34.780132+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2K7O5VVYMHB","created_at":"2026-07-05T07:00:34.780132+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2K7O5VVYMHB23W6","created_at":"2026-07-05T07:00:34.780132+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2K7O5VV","created_at":"2026-07-05T07:00:34.780132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.13869","citing_title":"Generative AI Carries Non-Democratic Biases and Stereotypes: Representation of Women, Black Individuals, Age Groups, and People with Disability in AI-Generated Images across Occupations","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2411.00585","citing_title":"Fairness Testing of Large Language Models in Role-Playing","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10915","citing_title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ","json":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ.json","graph_json":"https://pith.science/api/pith-number/F2K7O5VVYMHB23W6XUM5UY2VQJ/graph.json","events_json":"https://pith.science/api/pith-number/F2K7O5VVYMHB23W6XUM5UY2VQJ/events.json","paper":"https://pith.science/paper/F2K7O5VV"},"agent_actions":{"view_html":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ","download_json":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ.json","view_paper":"https://pith.science/paper/F2K7O5VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08780&json=true","fetch_graph":"https://pith.science/api/pith-number/F2K7O5VVYMHB23W6XUM5UY2VQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/F2K7O5VVYMHB23W6XUM5UY2VQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ/action/storage_attestation","attest_author":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ/action/author_attestation","sign_citation":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ/action/citation_signature","submit_replication":"https://pith.science/pith/F2K7O5VVYMHB23W6XUM5UY2VQJ/action/replication_record"}},"created_at":"2026-07-05T07:00:34.780132+00:00","updated_at":"2026-07-05T07:00:34.780132+00:00"}