{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5QROTPXVXMM74BWLCTBTBEI2ET","short_pith_number":"pith:5QROTPXV","schema_version":"1.0","canonical_sha256":"ec22e9bef5bb19fe06cb14c330911a24e2312a5d2bf97b1bb0dcd6d607fc24f5","source":{"kind":"arxiv","id":"2605.31545","version":1},"attestation_state":"computed","paper":{"title":"Preference-Aware Rubric Learning for Personalized Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cilin Yan, Jiayin Cai, Tat-Seng Chua, Xiaolong Jiang, Xiaoyan Zhao, Yang Zhang, Yao Hu, Yilun Qiu, Yoko Yamakata, Yuxin Chen","submitted_at":"2026-05-29T17:00:55Z","abstract_excerpt":"As Large Language Models (LLMs) evolve from general-purpose assistants to user-centric agents, personalization has become central to aligning model behavior with individual preferences, making the evaluation of personalized alignment a critical bottleneck. Existing evaluation methods-ranging from automatic metrics to LLM-as-a-judge approaches-fail to capture subjective, user-specific preferences embedded in long-term interaction histories. We identify three essential principles for reliable and effective personalized evaluation: Representativeness, User-Consistency, and Discriminativeness. To "},"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":"2605.31545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T17:00:55Z","cross_cats_sorted":[],"title_canon_sha256":"836c49b1f193951410b7b0463b1131ce1de3950c0e103d86ae4086df9b08cba6","abstract_canon_sha256":"e8fad514f9b280fcdfee9315183c2e984cb37b80c7448abb567e20d4c5f88009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:12.035633Z","signature_b64":"Slf38SI8IBC742qBBNA6QwKVLBqs2Xi2JHwPwLKGGz+Vtu8oPhbdBsw1ciX6YnV2ZeWPalUhvNODwi2WfFhOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec22e9bef5bb19fe06cb14c330911a24e2312a5d2bf97b1bb0dcd6d607fc24f5","last_reissued_at":"2026-06-01T02:04:12.034871Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:12.034871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference-Aware Rubric Learning for Personalized Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cilin Yan, Jiayin Cai, Tat-Seng Chua, Xiaolong Jiang, Xiaoyan Zhao, Yang Zhang, Yao Hu, Yilun Qiu, Yoko Yamakata, Yuxin Chen","submitted_at":"2026-05-29T17:00:55Z","abstract_excerpt":"As Large Language Models (LLMs) evolve from general-purpose assistants to user-centric agents, personalization has become central to aligning model behavior with individual preferences, making the evaluation of personalized alignment a critical bottleneck. Existing evaluation methods-ranging from automatic metrics to LLM-as-a-judge approaches-fail to capture subjective, user-specific preferences embedded in long-term interaction histories. We identify three essential principles for reliable and effective personalized evaluation: Representativeness, User-Consistency, and Discriminativeness. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31545","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/2605.31545/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":"2605.31545","created_at":"2026-06-01T02:04:12.034982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31545v1","created_at":"2026-06-01T02:04:12.034982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31545","created_at":"2026-06-01T02:04:12.034982+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QROTPXVXMM7","created_at":"2026-06-01T02:04:12.034982+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QROTPXVXMM74BWL","created_at":"2026-06-01T02:04:12.034982+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QROTPXV","created_at":"2026-06-01T02:04:12.034982+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/5QROTPXVXMM74BWLCTBTBEI2ET","json":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET.json","graph_json":"https://pith.science/api/pith-number/5QROTPXVXMM74BWLCTBTBEI2ET/graph.json","events_json":"https://pith.science/api/pith-number/5QROTPXVXMM74BWLCTBTBEI2ET/events.json","paper":"https://pith.science/paper/5QROTPXV"},"agent_actions":{"view_html":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET","download_json":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET.json","view_paper":"https://pith.science/paper/5QROTPXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31545&json=true","fetch_graph":"https://pith.science/api/pith-number/5QROTPXVXMM74BWLCTBTBEI2ET/graph.json","fetch_events":"https://pith.science/api/pith-number/5QROTPXVXMM74BWLCTBTBEI2ET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET/action/storage_attestation","attest_author":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET/action/author_attestation","sign_citation":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET/action/citation_signature","submit_replication":"https://pith.science/pith/5QROTPXVXMM74BWLCTBTBEI2ET/action/replication_record"}},"created_at":"2026-06-01T02:04:12.034982+00:00","updated_at":"2026-06-01T02:04:12.034982+00:00"}