{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YTATMK6V6VCQGEZG2BTE7I52ET","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":"1d5b89717e18f001a8ac913753a21c5e23f65604c51983f06cff0da38c325ca9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T05:35:31Z","title_canon_sha256":"1dc72f2c688bb93de1426f4edb8902f0544731ad2cdb5e154b384132f45bcf3b"},"schema_version":"1.0","source":{"id":"2606.07988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07988","created_at":"2026-06-09T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07988v1","created_at":"2026-06-09T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07988","created_at":"2026-06-09T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"YTATMK6V6VCQ","created_at":"2026-06-09T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"YTATMK6V6VCQGEZG","created_at":"2026-06-09T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"YTATMK6V","created_at":"2026-06-09T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:09bdc27537ce96cadfd130a8970e37d1b0d318f468899d8659a9028f3918600e","target":"graph","created_at":"2026-06-09T01:04:57Z","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/2606.07988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) increasingly rely on reward models to align their outputs with diverse user preferences. While personalized reward models aim to capture such heterogeneity, they are often trained on imbalanced user preference data and may therefore favor users whose preferences are more common in the training population. In this paper, we identify this failure mode as personalized reward bias, where reward modeling quality varies systematically with preference support rate. We formulate its mitigation as a Pareto fairness problem over group utilities, aiming to improve under-serve","authors_text":"Chunyuan Zheng, Fuli Feng, Haoting Ni, Haoxuan Li, Xiaoyan Zhao, Yang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T05:35:31Z","title":"PAFO: Pareto Fairness Optimization for Personalized Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07988","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":"sha256:1864c2e1181232b02b5d8e904e51c532c1b0b85d2d7720ecca2308002c362c50","target":"record","created_at":"2026-06-09T01:04:57Z","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":"1d5b89717e18f001a8ac913753a21c5e23f65604c51983f06cff0da38c325ca9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T05:35:31Z","title_canon_sha256":"1dc72f2c688bb93de1426f4edb8902f0544731ad2cdb5e154b384132f45bcf3b"},"schema_version":"1.0","source":{"id":"2606.07988","kind":"arxiv","version":1}},"canonical_sha256":"c4c1362bd5f545031326d0664fa3ba24ca8d529f622b859ddce7d94a7a0daa89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4c1362bd5f545031326d0664fa3ba24ca8d529f622b859ddce7d94a7a0daa89","first_computed_at":"2026-06-09T01:04:57.282538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:57.282538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X6TlAkquVr0fmR6M+gq0nIvOHcOLsZuAP3ozqg1H/GcdWkMJMZxQeIe6N9nUkjmCSXyCNrSnkrYFzjIS40+ECQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:57.283000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1864c2e1181232b02b5d8e904e51c532c1b0b85d2d7720ecca2308002c362c50","sha256:09bdc27537ce96cadfd130a8970e37d1b0d318f468899d8659a9028f3918600e"],"state_sha256":"fe603e32f01eab7245a5690c6b64f37bdb1ff048d073d4444a294adb1b0b4c07"}