{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JBIUKVUKA3TEWBYXDNDZ46U3AW","short_pith_number":"pith:JBIUKVUK","schema_version":"1.0","canonical_sha256":"485145568a06e64b07171b479e7a9b05bea4bf57c4715431ccf0814ea25fbcf2","source":{"kind":"arxiv","id":"2306.04597","version":1},"attestation_state":"computed","paper":{"title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Atishay Jain, Himanshu Thakur, Louis-Philippe Morency, Paul Pu Liang, Praneetha Vaddamanu","submitted_at":"2023-06-07T16:50:03Z","abstract_excerpt":"Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since large-scale retraining of these models from scratch is both time and compute-expensive, a variety of approaches have been previously proposed that de-bias a pre-trained model. While the majority of current state-of-the-art debiasing methods focus on changes to the training regime, in this paper, we propose data intervention strategies as a powerful yet simple tec"},"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":"2306.04597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T16:50:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"24f20b2559275763dd0f7f1d400d105a519c0c98258ee895bd6d11c5036f8d78","abstract_canon_sha256":"085194f5d0b9a15695bca8a37fd4a98beea400471a56b8005500a782aae6bd9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:32.906198Z","signature_b64":"S7h8ETCjs2rov059AHUt20VqvutlUP3+GaVl8PpHISsyyTpHfIWBEyJoJ7KbSaKwqb1kZA5LBeES9jTTpdqjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"485145568a06e64b07171b479e7a9b05bea4bf57c4715431ccf0814ea25fbcf2","last_reissued_at":"2026-07-05T06:18:32.905822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:32.905822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Atishay Jain, Himanshu Thakur, Louis-Philippe Morency, Paul Pu Liang, Praneetha Vaddamanu","submitted_at":"2023-06-07T16:50:03Z","abstract_excerpt":"Societal biases present in pre-trained large language models are a critical issue as these models have been shown to propagate biases in countless downstream applications, rendering them unfair towards specific groups of people. Since large-scale retraining of these models from scratch is both time and compute-expensive, a variety of approaches have been previously proposed that de-bias a pre-trained model. While the majority of current state-of-the-art debiasing methods focus on changes to the training regime, in this paper, we propose data intervention strategies as a powerful yet simple tec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04597","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/2306.04597/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":"2306.04597","created_at":"2026-07-05T06:18:32.905876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04597v1","created_at":"2026-07-05T06:18:32.905876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04597","created_at":"2026-07-05T06:18:32.905876+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBIUKVUKA3TE","created_at":"2026-07-05T06:18:32.905876+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBIUKVUKA3TEWBYX","created_at":"2026-07-05T06:18:32.905876+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBIUKVUK","created_at":"2026-07-05T06:18:32.905876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13952","citing_title":"The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW","json":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW.json","graph_json":"https://pith.science/api/pith-number/JBIUKVUKA3TEWBYXDNDZ46U3AW/graph.json","events_json":"https://pith.science/api/pith-number/JBIUKVUKA3TEWBYXDNDZ46U3AW/events.json","paper":"https://pith.science/paper/JBIUKVUK"},"agent_actions":{"view_html":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW","download_json":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW.json","view_paper":"https://pith.science/paper/JBIUKVUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04597&json=true","fetch_graph":"https://pith.science/api/pith-number/JBIUKVUKA3TEWBYXDNDZ46U3AW/graph.json","fetch_events":"https://pith.science/api/pith-number/JBIUKVUKA3TEWBYXDNDZ46U3AW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW/action/storage_attestation","attest_author":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW/action/author_attestation","sign_citation":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW/action/citation_signature","submit_replication":"https://pith.science/pith/JBIUKVUKA3TEWBYXDNDZ46U3AW/action/replication_record"}},"created_at":"2026-07-05T06:18:32.905876+00:00","updated_at":"2026-07-05T06:18:32.905876+00:00"}