{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPGDNSZI2WWWZL4F3ESFW3SVCT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"38548b91ff4e81715a6881473e9e9ac9be9c523acd104d8b2073248b04339b2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:38:34Z","title_canon_sha256":"58a642292fd6f59fdef2e3ca21bb3d2bac7785bb065b5453f46b495956a184e5"},"schema_version":"1.0","source":{"id":"2406.13551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13551","created_at":"2026-07-05T08:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13551v1","created_at":"2026-07-05T08:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13551","created_at":"2026-07-05T08:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"KPGDNSZI2WWW","created_at":"2026-07-05T08:34:31Z"},{"alias_kind":"pith_short_16","alias_value":"KPGDNSZI2WWWZL4F","created_at":"2026-07-05T08:34:31Z"},{"alias_kind":"pith_short_8","alias_value":"KPGDNSZI","created_at":"2026-07-05T08:34:31Z"}],"graph_snapshots":[{"event_id":"sha256:e66e8b51b00675e12adc0dbd188c454bceae6a1d49dc5f6b42380ff383d3ac41","target":"graph","created_at":"2026-07-05T08:34:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.13551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mitigating bias in language models (LMs) has become a critical problem due to the widespread deployment of LMs. Numerous approaches revolve around data pre-processing and fine-tuning of language models, tasks that can be both time-consuming and computationally demanding. Consequently, there is a growing interest in machine unlearning techniques given their capacity to induce the forgetting of undesired behaviors of the existing pre-trained or fine-tuned models with lower computational cost. In this work, we explore two unlearning methods, (1) Partitioned Contrastive Gradient Unlearning (PCGU) ","authors_text":"Borna Bolandraftar, Diljot Singh, Faiza Khan Khattak, Omkar Dige, Qixuan Zhang, Tsz Fung Yau, Xiaodan Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:38:34Z","title":"Mitigating Social Biases in Language Models through Unlearning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13551","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:13b5e8c9f96f448c57a3c311c8bc3d05edf1778142b5e78b8b4a56b9f2a338a8","target":"record","created_at":"2026-07-05T08:34:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"38548b91ff4e81715a6881473e9e9ac9be9c523acd104d8b2073248b04339b2f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:38:34Z","title_canon_sha256":"58a642292fd6f59fdef2e3ca21bb3d2bac7785bb065b5453f46b495956a184e5"},"schema_version":"1.0","source":{"id":"2406.13551","kind":"arxiv","version":1}},"canonical_sha256":"53cc36cb28d5ad6caf85d9245b6e5514d61fe8aef2ac87b2fe31796cba596ff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53cc36cb28d5ad6caf85d9245b6e5514d61fe8aef2ac87b2fe31796cba596ff2","first_computed_at":"2026-07-05T08:34:31.545758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:31.545758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"736CNQDThO63yeFVgSYEDUZRKtqFIfio8Nx5JVMzKwe6z4SWTaP9K6uKJcpTlMfmK34C+ca/xRQC9NK+oGWhDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:31.546219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13b5e8c9f96f448c57a3c311c8bc3d05edf1778142b5e78b8b4a56b9f2a338a8","sha256:e66e8b51b00675e12adc0dbd188c454bceae6a1d49dc5f6b42380ff383d3ac41"],"state_sha256":"22a3059486a88c6d0b68d106269e95638e4d31326ab80f1ad710806bd8828d54"}