{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SFAGBFGOVMHGLN4Z4M6T37P4B2","short_pith_number":"pith:SFAGBFGO","schema_version":"1.0","canonical_sha256":"91406094ceab0e65b799e33d3dfdfc0e9140452f34098d63ad30f7f41030ebc4","source":{"kind":"arxiv","id":"2607.05742","version":1},"attestation_state":"computed","paper":{"title":"PERSONAJUDGE: Simulating Individual Human Preference Judgments with Evaluator-Specific Demonstration Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Alex C. Williams, Lydia Chilton, Subramanian Chidambaram, Vinayak Arannil, Xuan Qi, Zeyu He, Zhichao Xu","submitted_at":"2026-07-07T01:56:05Z","abstract_excerpt":"Large language models increasingly serve as judges in AI evaluation, but current approaches rely on consensus preferences that ignore individual evaluator variation. We propose a novel simulation approach that combines categorical judgments with evaluator-specific auxiliary data--retrospective reasoning traces and interface telemetry--to enable LLM-based simulation of individual evaluators via in-context learning. We conduct a systematic empirical study of this approach using multi-facet data from 32 trained annotators across 4,200 preference judgments in a 4 x 4 x 4 factorial design. Our key "},"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":"2607.05742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2026-07-07T01:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"b6830c1bdb3b656f3147a21a339e61bf92742b3a3ea83686050dc3eb5d415952","abstract_canon_sha256":"947f6f48f732ed4ceb38cfd5a8a590758077e8cd892d32f49a754b9b55cfac6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:43.623609Z","signature_b64":"pROqeA9sP59GydX4O2eyDYprzTQfWkKRgBeNuvlOClXy58tVuSc4Gj22C3OQT+4aKtFFKyVP33LS6hcSN6HKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91406094ceab0e65b799e33d3dfdfc0e9140452f34098d63ad30f7f41030ebc4","last_reissued_at":"2026-07-08T01:18:43.623158Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:43.623158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PERSONAJUDGE: Simulating Individual Human Preference Judgments with Evaluator-Specific Demonstration Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Alex C. Williams, Lydia Chilton, Subramanian Chidambaram, Vinayak Arannil, Xuan Qi, Zeyu He, Zhichao Xu","submitted_at":"2026-07-07T01:56:05Z","abstract_excerpt":"Large language models increasingly serve as judges in AI evaluation, but current approaches rely on consensus preferences that ignore individual evaluator variation. We propose a novel simulation approach that combines categorical judgments with evaluator-specific auxiliary data--retrospective reasoning traces and interface telemetry--to enable LLM-based simulation of individual evaluators via in-context learning. We conduct a systematic empirical study of this approach using multi-facet data from 32 trained annotators across 4,200 preference judgments in a 4 x 4 x 4 factorial design. Our key "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05742","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/2607.05742/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":"2607.05742","created_at":"2026-07-08T01:18:43.623229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05742v1","created_at":"2026-07-08T01:18:43.623229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05742","created_at":"2026-07-08T01:18:43.623229+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFAGBFGOVMHG","created_at":"2026-07-08T01:18:43.623229+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFAGBFGOVMHGLN4Z","created_at":"2026-07-08T01:18:43.623229+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFAGBFGO","created_at":"2026-07-08T01:18:43.623229+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/SFAGBFGOVMHGLN4Z4M6T37P4B2","json":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2.json","graph_json":"https://pith.science/api/pith-number/SFAGBFGOVMHGLN4Z4M6T37P4B2/graph.json","events_json":"https://pith.science/api/pith-number/SFAGBFGOVMHGLN4Z4M6T37P4B2/events.json","paper":"https://pith.science/paper/SFAGBFGO"},"agent_actions":{"view_html":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2","download_json":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2.json","view_paper":"https://pith.science/paper/SFAGBFGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05742&json=true","fetch_graph":"https://pith.science/api/pith-number/SFAGBFGOVMHGLN4Z4M6T37P4B2/graph.json","fetch_events":"https://pith.science/api/pith-number/SFAGBFGOVMHGLN4Z4M6T37P4B2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2/action/storage_attestation","attest_author":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2/action/author_attestation","sign_citation":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2/action/citation_signature","submit_replication":"https://pith.science/pith/SFAGBFGOVMHGLN4Z4M6T37P4B2/action/replication_record"}},"created_at":"2026-07-08T01:18:43.623229+00:00","updated_at":"2026-07-08T01:18:43.623229+00:00"}