{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EHYKH7FJJE72OSXNLZGX2JXWUC","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":"6d5dae7eea8c696f94337f573eb13755f71d42a5040ac4d0d6af8bc3ac636a7a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T22:23:30Z","title_canon_sha256":"2088394d167947c5a0d9b318dc6a4aa133a147957739c0e3565a67c9769159a0"},"schema_version":"1.0","source":{"id":"2412.04642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04642","created_at":"2026-07-05T09:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04642v1","created_at":"2026-07-05T09:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04642","created_at":"2026-07-05T09:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"EHYKH7FJJE72","created_at":"2026-07-05T09:45:21Z"},{"alias_kind":"pith_short_16","alias_value":"EHYKH7FJJE72OSXN","created_at":"2026-07-05T09:45:21Z"},{"alias_kind":"pith_short_8","alias_value":"EHYKH7FJ","created_at":"2026-07-05T09:45:21Z"}],"graph_snapshots":[{"event_id":"sha256:d2edc13a25b0a406af546eb44574119431447b0a145d7fce0ebbb40fc2f3f673","target":"graph","created_at":"2026-07-05T09:45:21Z","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/2412.04642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been shown to be effective on tabular prediction tasks in the low-data regime, leveraging their internal knowledge and ability to learn from instructions and examples. However, LLMs can fail to generate predictions that satisfy group fairness, that is, produce equitable outcomes across groups. Critically, conventional debiasing approaches for natural language tasks do not directly translate to mitigating group unfairness in tabular settings. In this work, we systematically investigate four empirical approaches to improve group fairness of LLM predictions on ta","authors_text":"Chia-Jung Lee, James Zou, Martin Andres Bertran, Michael Kearns, Nil-Jana Akpinar, Riccardo Fogliato, Valeriia Cherepanova","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T22:23:30Z","title":"Improving LLM Group Fairness on Tabular Data via In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04642","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":"sha256:74b3178947763ed0aa6cf9434ca63bd2edc253a2261da14564b9f1030187f623","target":"record","created_at":"2026-07-05T09:45:21Z","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":"6d5dae7eea8c696f94337f573eb13755f71d42a5040ac4d0d6af8bc3ac636a7a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T22:23:30Z","title_canon_sha256":"2088394d167947c5a0d9b318dc6a4aa133a147957739c0e3565a67c9769159a0"},"schema_version":"1.0","source":{"id":"2412.04642","kind":"arxiv","version":1}},"canonical_sha256":"21f0a3fca9493fa74aed5e4d7d26f6a0be919544bbf94ed9d3f387f31f22b3bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21f0a3fca9493fa74aed5e4d7d26f6a0be919544bbf94ed9d3f387f31f22b3bb","first_computed_at":"2026-07-05T09:45:21.328576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:21.328576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eq6JtWUb7FpKjBN5yJaRDx2uJPmCanSFKdzJrZWhcOqQKoNt7DOI2SQVwjnF5in1E11AFLByLpDkk6i3Ea5mAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:21.328996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74b3178947763ed0aa6cf9434ca63bd2edc253a2261da14564b9f1030187f623","sha256:d2edc13a25b0a406af546eb44574119431447b0a145d7fce0ebbb40fc2f3f673"],"state_sha256":"372726fdc5bee8c751412e4ee07881f6e998dd7e05ca5e7bf45e5fe05d69189f"}