{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IVQ5IDSWLA3ECCPVFVZRFIUP2W","short_pith_number":"pith:IVQ5IDSW","schema_version":"1.0","canonical_sha256":"4561d40e5658364109f52d7312a28fd5b7bb6e911a8fa139856c75f2c57c1bae","source":{"kind":"arxiv","id":"2508.11258","version":1},"attestation_state":"computed","paper":{"title":"Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CY"],"primary_cat":"cs.LG","authors_text":"Han Zhao, Ruicheng Xian, Yuxuan Wan","submitted_at":"2025-08-15T06:50:29Z","abstract_excerpt":"Instruction fine-tuned large language models (LLMs) enable a simple zero-shot or few-shot prompting paradigm, also known as in-context learning, for building prediction models. This convenience, combined with continued advances in LLM capability, has the potential to drive their adoption across a broad range of domains, including high-stakes applications where group fairness -- preventing disparate impacts across demographic groups -- is essential. The majority of existing approaches to enforcing group fairness on LLM-based classifiers rely on traditional fair algorithms applied via model fine"},"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":"2508.11258","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T06:50:29Z","cross_cats_sorted":["cs.CL","cs.CY"],"title_canon_sha256":"ac9b408cd22653436bf5096552b9542cb57949cbdbe197dd2c05a5ce7572e367","abstract_canon_sha256":"dbbf8c6d52039180b11ee348fa6d413215d953593a5c770124c33524bcfaf106"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:21.593075Z","signature_b64":"vMVE5aXryYLHQH121vwy2haMqLBAsDe5+D3CdkOl6+yYru1SZ3ELBZi+dg+xuEDGuR2Vj3M/SkW6+gET1UmRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4561d40e5658364109f52d7312a28fd5b7bb6e911a8fa139856c75f2c57c1bae","last_reissued_at":"2026-07-05T11:54:21.592640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:21.592640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CY"],"primary_cat":"cs.LG","authors_text":"Han Zhao, Ruicheng Xian, Yuxuan Wan","submitted_at":"2025-08-15T06:50:29Z","abstract_excerpt":"Instruction fine-tuned large language models (LLMs) enable a simple zero-shot or few-shot prompting paradigm, also known as in-context learning, for building prediction models. This convenience, combined with continued advances in LLM capability, has the potential to drive their adoption across a broad range of domains, including high-stakes applications where group fairness -- preventing disparate impacts across demographic groups -- is essential. The majority of existing approaches to enforcing group fairness on LLM-based classifiers rely on traditional fair algorithms applied via model fine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11258","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/2508.11258/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":"2508.11258","created_at":"2026-07-05T11:54:21.592697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11258v1","created_at":"2026-07-05T11:54:21.592697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11258","created_at":"2026-07-05T11:54:21.592697+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVQ5IDSWLA3E","created_at":"2026-07-05T11:54:21.592697+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVQ5IDSWLA3ECCPV","created_at":"2026-07-05T11:54:21.592697+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVQ5IDSW","created_at":"2026-07-05T11:54:21.592697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W","json":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W.json","graph_json":"https://pith.science/api/pith-number/IVQ5IDSWLA3ECCPVFVZRFIUP2W/graph.json","events_json":"https://pith.science/api/pith-number/IVQ5IDSWLA3ECCPVFVZRFIUP2W/events.json","paper":"https://pith.science/paper/IVQ5IDSW"},"agent_actions":{"view_html":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W","download_json":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W.json","view_paper":"https://pith.science/paper/IVQ5IDSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11258&json=true","fetch_graph":"https://pith.science/api/pith-number/IVQ5IDSWLA3ECCPVFVZRFIUP2W/graph.json","fetch_events":"https://pith.science/api/pith-number/IVQ5IDSWLA3ECCPVFVZRFIUP2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W/action/storage_attestation","attest_author":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W/action/author_attestation","sign_citation":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W/action/citation_signature","submit_replication":"https://pith.science/pith/IVQ5IDSWLA3ECCPVFVZRFIUP2W/action/replication_record"}},"created_at":"2026-07-05T11:54:21.592697+00:00","updated_at":"2026-07-05T11:54:21.592697+00:00"}