{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DUZUK73OMSR5W3S76LCBDXPV47","short_pith_number":"pith:DUZUK73O","schema_version":"1.0","canonical_sha256":"1d33457f6e64a3db6e5ff2c411ddf5e7f114a6633f600a381fff540202d71085","source":{"kind":"arxiv","id":"2312.03689","version":1},"attestation_state":"computed","paper":{"title":"Evaluating and Mitigating Discrimination in Language Model Decisions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Tamkin, Amanda Askell, Deep Ganguli, Esin Durmus, Jared Kaplan, Karina Nguyen, Liane Lovitt, Nicholas Joseph, Shauna Kravec","submitted_at":"2023-12-06T18:53:01Z","abstract_excerpt":"As language models (LMs) advance, interest is growing in applying them to high-stakes societal decisions, such as determining financing or housing eligibility. However, their potential for discrimination in such contexts raises ethical concerns, motivating the need for better methods to evaluate these risks. We present a method for proactively evaluating the potential discriminatory impact of LMs in a wide range of use cases, including hypothetical use cases where they have not yet been deployed. Specifically, we use an LM to generate a wide array of potential prompts that decision-makers may "},"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":"2312.03689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T18:53:01Z","cross_cats_sorted":[],"title_canon_sha256":"e6a167196f1a4cdd1778e20b4723c0f59e245abc893873356cb7c84541748689","abstract_canon_sha256":"ea4815b0dcd8590f239566f6f0f438a03ec366cddd7edcf39191e1a96f6a3581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:08.301639Z","signature_b64":"H3aW+sFEofhWwmgwgLJ/HB6VI5YxefVw9zu4qMPBOvjqnclzJqrbrpNsxJe8F7dPKLv7rl0COXY33+dmM9sUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d33457f6e64a3db6e5ff2c411ddf5e7f114a6633f600a381fff540202d71085","last_reissued_at":"2026-07-05T07:21:08.301151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:08.301151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating and Mitigating Discrimination in Language Model Decisions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Tamkin, Amanda Askell, Deep Ganguli, Esin Durmus, Jared Kaplan, Karina Nguyen, Liane Lovitt, Nicholas Joseph, Shauna Kravec","submitted_at":"2023-12-06T18:53:01Z","abstract_excerpt":"As language models (LMs) advance, interest is growing in applying them to high-stakes societal decisions, such as determining financing or housing eligibility. However, their potential for discrimination in such contexts raises ethical concerns, motivating the need for better methods to evaluate these risks. We present a method for proactively evaluating the potential discriminatory impact of LMs in a wide range of use cases, including hypothetical use cases where they have not yet been deployed. Specifically, we use an LM to generate a wide array of potential prompts that decision-makers may "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03689","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/2312.03689/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":"2312.03689","created_at":"2026-07-05T07:21:08.301203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03689v1","created_at":"2026-07-05T07:21:08.301203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03689","created_at":"2026-07-05T07:21:08.301203+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUZUK73OMSR5","created_at":"2026-07-05T07:21:08.301203+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUZUK73OMSR5W3S7","created_at":"2026-07-05T07:21:08.301203+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUZUK73O","created_at":"2026-07-05T07:21:08.301203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24596","citing_title":"To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16723","citing_title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28863","citing_title":"Defeat Devices in AI Systems","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06674","citing_title":"What Do People Actually Want From AI? Mapping Preference Plurality","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07475","citing_title":"Laissez-Faire Harms: Algorithmic Biases in Generative Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2412.16720","citing_title":"OpenAI o1 System Card","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12530","citing_title":"In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08525","citing_title":"Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47","json":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47.json","graph_json":"https://pith.science/api/pith-number/DUZUK73OMSR5W3S76LCBDXPV47/graph.json","events_json":"https://pith.science/api/pith-number/DUZUK73OMSR5W3S76LCBDXPV47/events.json","paper":"https://pith.science/paper/DUZUK73O"},"agent_actions":{"view_html":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47","download_json":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47.json","view_paper":"https://pith.science/paper/DUZUK73O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03689&json=true","fetch_graph":"https://pith.science/api/pith-number/DUZUK73OMSR5W3S76LCBDXPV47/graph.json","fetch_events":"https://pith.science/api/pith-number/DUZUK73OMSR5W3S76LCBDXPV47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47/action/storage_attestation","attest_author":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47/action/author_attestation","sign_citation":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47/action/citation_signature","submit_replication":"https://pith.science/pith/DUZUK73OMSR5W3S76LCBDXPV47/action/replication_record"}},"created_at":"2026-07-05T07:21:08.301203+00:00","updated_at":"2026-07-05T07:21:08.301203+00:00"}