{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A5LES7BGXEHJQKSDDAOVAVSLFX","short_pith_number":"pith:A5LES7BG","schema_version":"1.0","canonical_sha256":"0756497c26b90e982a43181d50564b2dc7b07459c05303c4790eab5891a63850","source":{"kind":"arxiv","id":"2507.13541","version":1},"attestation_state":"computed","paper":{"title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew Cohen, Ansong Ni, Asli Celikyilmaz, Chan Young Park, Hunter Lang, Jacqueline He, Melanie Sclar, Puxin Xu, Shuyue Stella Li, Yulia Tsvetkov","submitted_at":"2025-07-17T21:21:54Z","abstract_excerpt":"Personalizing AI systems requires understanding not just what users prefer, but the reasons that underlie those preferences - yet current preference models typically treat human judgment as a black box. We introduce PrefPalette, a framework that decomposes preferences into attribute dimensions and tailors its preference prediction to distinct social community values in a human-interpretable manner. PrefPalette operationalizes a cognitive science principle known as multi-attribute decision making in two ways: (1) a scalable counterfactual attribute synthesis step that involves generating synthe"},"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":"2507.13541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-17T21:21:54Z","cross_cats_sorted":[],"title_canon_sha256":"c2e4b1783327399432cd28c71bfd2acbbb3a38e1fad00a34c575bd9d15a91511","abstract_canon_sha256":"b4b8ad80674ce440eb10c8a14b3c2ab30b543bd3d66a11c101c7edf592edb64b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:18.947136Z","signature_b64":"sdw313vDwq1Q7kzgxWyI5wDVOfg6Aa49SRvL2ujk4oMc9DJTTBt3Pibemfi/wmQpUMQKjioRZ9LaStDl39G1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0756497c26b90e982a43181d50564b2dc7b07459c05303c4790eab5891a63850","last_reissued_at":"2026-07-05T11:39:18.946700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:18.946700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew Cohen, Ansong Ni, Asli Celikyilmaz, Chan Young Park, Hunter Lang, Jacqueline He, Melanie Sclar, Puxin Xu, Shuyue Stella Li, Yulia Tsvetkov","submitted_at":"2025-07-17T21:21:54Z","abstract_excerpt":"Personalizing AI systems requires understanding not just what users prefer, but the reasons that underlie those preferences - yet current preference models typically treat human judgment as a black box. We introduce PrefPalette, a framework that decomposes preferences into attribute dimensions and tailors its preference prediction to distinct social community values in a human-interpretable manner. PrefPalette operationalizes a cognitive science principle known as multi-attribute decision making in two ways: (1) a scalable counterfactual attribute synthesis step that involves generating synthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13541","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/2507.13541/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":"2507.13541","created_at":"2026-07-05T11:39:18.946755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13541v1","created_at":"2026-07-05T11:39:18.946755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13541","created_at":"2026-07-05T11:39:18.946755+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5LES7BGXEHJ","created_at":"2026-07-05T11:39:18.946755+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5LES7BGXEHJQKSD","created_at":"2026-07-05T11:39:18.946755+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5LES7BG","created_at":"2026-07-05T11:39:18.946755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12160","citing_title":"PubSwap: Public-Data Off-Policy Coordination for Federated RLVR","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09876","citing_title":"Efficient Personalization of Generative User Interfaces","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX","json":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX.json","graph_json":"https://pith.science/api/pith-number/A5LES7BGXEHJQKSDDAOVAVSLFX/graph.json","events_json":"https://pith.science/api/pith-number/A5LES7BGXEHJQKSDDAOVAVSLFX/events.json","paper":"https://pith.science/paper/A5LES7BG"},"agent_actions":{"view_html":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX","download_json":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX.json","view_paper":"https://pith.science/paper/A5LES7BG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13541&json=true","fetch_graph":"https://pith.science/api/pith-number/A5LES7BGXEHJQKSDDAOVAVSLFX/graph.json","fetch_events":"https://pith.science/api/pith-number/A5LES7BGXEHJQKSDDAOVAVSLFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX/action/storage_attestation","attest_author":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX/action/author_attestation","sign_citation":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX/action/citation_signature","submit_replication":"https://pith.science/pith/A5LES7BGXEHJQKSDDAOVAVSLFX/action/replication_record"}},"created_at":"2026-07-05T11:39:18.946755+00:00","updated_at":"2026-07-05T11:39:18.946755+00:00"}