{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7QDI7YHUG7WBGHLATEAWJA55BF","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":"5ffc56feb19978b9e60c3e0b9a8b5894dd2074ebf5f959270f2e44aa66a3f71e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T18:38:16Z","title_canon_sha256":"164d24b18bc13cdec7285933fc0a76c0d400dccc5a22687e70bc0562b1f42651"},"schema_version":"1.0","source":{"id":"2608.10126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10126","created_at":"2026-08-12T00:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10126v1","created_at":"2026-08-12T00:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10126","created_at":"2026-08-12T00:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"7QDI7YHUG7WB","created_at":"2026-08-12T00:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"7QDI7YHUG7WBGHLA","created_at":"2026-08-12T00:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"7QDI7YHU","created_at":"2026-08-12T00:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:df9aeeb0e9632695dfbf057663037da29aae2d47c55b1e43b88209040f10df94","target":"graph","created_at":"2026-08-12T00:22:52Z","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/2608.10126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity. When preferences are heterogeneous, this aggregation induces a procedural fairness failure where majority preference groups dominate reward learning while minority preferences are systematically under-represented. This work defines procedural fairness in alignment as preserving distinct preference signals during reward modeling and shows that standard RLHF violates this via preference averaging. Preference-Aware RLHF (PA-RLHF) is introduced, separa","authors_text":"John Joshua, Karthik Kamuju, Kummari Avinash, M P V S Gopinadh, Srinivasa Raju Rudraraju","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T18:38:16Z","title":"Procedural Fairness Failures in RLHF from Preference Averaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10126","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":"sha256:60b879c30ebc7e3590598e6d0ae760b5c0f705c9806000641e7945656d5ddacb","target":"record","created_at":"2026-08-12T00:22:52Z","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":"5ffc56feb19978b9e60c3e0b9a8b5894dd2074ebf5f959270f2e44aa66a3f71e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-10T18:38:16Z","title_canon_sha256":"164d24b18bc13cdec7285933fc0a76c0d400dccc5a22687e70bc0562b1f42651"},"schema_version":"1.0","source":{"id":"2608.10126","kind":"arxiv","version":1}},"canonical_sha256":"fc068fe0f437ec131d6099016483bd094f8021c4ada9fd7f929a2daa0707a988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc068fe0f437ec131d6099016483bd094f8021c4ada9fd7f929a2daa0707a988","first_computed_at":"2026-08-12T00:22:52.156291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:22:52.156291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G2X4UCFvab417BEXXWo+jdJkb+Fkjc/Fdj2istaLpAeqa76SF4fBX744XI3brCYz+2VKiiVhZN5vkf+DuKu4Bw==","signature_status":"signed_v1","signed_at":"2026-08-12T00:22:52.157759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60b879c30ebc7e3590598e6d0ae760b5c0f705c9806000641e7945656d5ddacb","sha256:df9aeeb0e9632695dfbf057663037da29aae2d47c55b1e43b88209040f10df94"],"state_sha256":"215a849055aee52a5c1466b31970c35f655a8ec77dfbe175e43b2dba4a425ce3"}