{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YA2PYQLLLXBC7DBW53URE5QBU3","short_pith_number":"pith:YA2PYQLL","schema_version":"1.0","canonical_sha256":"c034fc416b5dc22f8c36eee9127601a6d49bca0b012bc7564172a3cdb1e589dd","source":{"kind":"arxiv","id":"2408.03907","version":1},"attestation_state":"computed","paper":{"title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eda Okur, Hsuan Su, Hung-yi Lee, Lama Nachman, Nicole Beckage, Ramesh Manuvinakurike, Sahisnu Mazumder, Saurav Sahay, Shachi H Kumar","submitted_at":"2024-08-07T17:11:34Z","abstract_excerpt":"Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can prompt the model to generate undesirable text. LLMs also inherently encode potential biases that can cause various harmful effects during interactions. Bias evaluation metrics lack standards as well as consensus and existing methods often rely on human-generated templates and annotations which are expensive and labor intensive. In this work, we train models to"},"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":"2408.03907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T17:11:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"634a7348ce081acdfdfd365dd25e6bc377f8debda0c179afad997a22796f4833","abstract_canon_sha256":"35acc7b81fafc3984282e0f4d63e82aa0b2781670d186896663190894f0d444e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:12.668063Z","signature_b64":"xVE6syxvrF2PzlWe633RpVJmYcSbDIijeNr2mOfI4myL6Q45HdrOcMbOt9NvwJ8tWCLb9elOj5WkRKHeR/3VDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c034fc416b5dc22f8c36eee9127601a6d49bca0b012bc7564172a3cdb1e589dd","last_reissued_at":"2026-07-05T08:53:12.667650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:12.667650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eda Okur, Hsuan Su, Hung-yi Lee, Lama Nachman, Nicole Beckage, Ramesh Manuvinakurike, Sahisnu Mazumder, Saurav Sahay, Shachi H Kumar","submitted_at":"2024-08-07T17:11:34Z","abstract_excerpt":"Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can prompt the model to generate undesirable text. LLMs also inherently encode potential biases that can cause various harmful effects during interactions. Bias evaluation metrics lack standards as well as consensus and existing methods often rely on human-generated templates and annotations which are expensive and labor intensive. In this work, we train models to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03907","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/2408.03907/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":"2408.03907","created_at":"2026-07-05T08:53:12.667708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.03907v1","created_at":"2026-07-05T08:53:12.667708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03907","created_at":"2026-07-05T08:53:12.667708+00:00"},{"alias_kind":"pith_short_12","alias_value":"YA2PYQLLLXBC","created_at":"2026-07-05T08:53:12.667708+00:00"},{"alias_kind":"pith_short_16","alias_value":"YA2PYQLLLXBC7DBW","created_at":"2026-07-05T08:53:12.667708+00:00"},{"alias_kind":"pith_short_8","alias_value":"YA2PYQLL","created_at":"2026-07-05T08:53:12.667708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03976","citing_title":"Quantifying Trust: Financial Risk Management for Trustworthy AI Agents","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3","json":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3.json","graph_json":"https://pith.science/api/pith-number/YA2PYQLLLXBC7DBW53URE5QBU3/graph.json","events_json":"https://pith.science/api/pith-number/YA2PYQLLLXBC7DBW53URE5QBU3/events.json","paper":"https://pith.science/paper/YA2PYQLL"},"agent_actions":{"view_html":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3","download_json":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3.json","view_paper":"https://pith.science/paper/YA2PYQLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.03907&json=true","fetch_graph":"https://pith.science/api/pith-number/YA2PYQLLLXBC7DBW53URE5QBU3/graph.json","fetch_events":"https://pith.science/api/pith-number/YA2PYQLLLXBC7DBW53URE5QBU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3/action/storage_attestation","attest_author":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3/action/author_attestation","sign_citation":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3/action/citation_signature","submit_replication":"https://pith.science/pith/YA2PYQLLLXBC7DBW53URE5QBU3/action/replication_record"}},"created_at":"2026-07-05T08:53:12.667708+00:00","updated_at":"2026-07-05T08:53:12.667708+00:00"}