{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CDUGMQAOFJYTRVP6JJZV43MSMQ","short_pith_number":"pith:CDUGMQAO","schema_version":"1.0","canonical_sha256":"10e866400e2a7138d5fe4a735e6d926436a0c6f459784db378c174ba2dc6bef2","source":{"kind":"arxiv","id":"2411.00524","version":2},"attestation_state":"computed","paper":{"title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jungseul Ok, Minhyeon Oh, Seungjoon Lee","submitted_at":"2024-11-01T11:49:33Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge. As individuals have their own, multi-dimensional preferences, recent studies have explored multi-dimensional personalization, which aims to enable models to generate responses personalized to explicit preferences. However, human preferences are often implicit and thus difficult to articulate, limiting the direct application of this approach. To bridge this gap, we propose Active Multi-dimensional Preference Learning (AMPLe), designed to capture implicit user preference"},"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":"2411.00524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T11:49:33Z","cross_cats_sorted":[],"title_canon_sha256":"044d6654d5d8eff05ffb29ecf7cf6c6b97d5915823c80eb8a698272a73f5f9f1","abstract_canon_sha256":"e878d913601d8b8db3cfbc2a2e76e7463d4f8acfd08793d24bbe975072c02a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:15.121785Z","signature_b64":"GD8lA+vZxLHg3QchXAOTzpfDYOXD2bDoOi8q3H6wQUcdP60V+NKbYzkrSd4KG5cGpzGE3U4eVO3/sGNs4sfvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10e866400e2a7138d5fe4a735e6d926436a0c6f459784db378c174ba2dc6bef2","last_reissued_at":"2026-07-05T11:13:15.121256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:15.121256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jungseul Ok, Minhyeon Oh, Seungjoon Lee","submitted_at":"2024-11-01T11:49:33Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge. As individuals have their own, multi-dimensional preferences, recent studies have explored multi-dimensional personalization, which aims to enable models to generate responses personalized to explicit preferences. However, human preferences are often implicit and thus difficult to articulate, limiting the direct application of this approach. To bridge this gap, we propose Active Multi-dimensional Preference Learning (AMPLe), designed to capture implicit user preference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00524","kind":"arxiv","version":2},"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/2411.00524/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":"2411.00524","created_at":"2026-07-05T11:13:15.121326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00524v2","created_at":"2026-07-05T11:13:15.121326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00524","created_at":"2026-07-05T11:13:15.121326+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDUGMQAOFJYT","created_at":"2026-07-05T11:13:15.121326+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDUGMQAOFJYTRVP6","created_at":"2026-07-05T11:13:15.121326+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDUGMQAO","created_at":"2026-07-05T11:13:15.121326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09876","citing_title":"Efficient Personalization of Generative User Interfaces","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ","json":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ.json","graph_json":"https://pith.science/api/pith-number/CDUGMQAOFJYTRVP6JJZV43MSMQ/graph.json","events_json":"https://pith.science/api/pith-number/CDUGMQAOFJYTRVP6JJZV43MSMQ/events.json","paper":"https://pith.science/paper/CDUGMQAO"},"agent_actions":{"view_html":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ","download_json":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ.json","view_paper":"https://pith.science/paper/CDUGMQAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00524&json=true","fetch_graph":"https://pith.science/api/pith-number/CDUGMQAOFJYTRVP6JJZV43MSMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CDUGMQAOFJYTRVP6JJZV43MSMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ/action/storage_attestation","attest_author":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ/action/author_attestation","sign_citation":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ/action/citation_signature","submit_replication":"https://pith.science/pith/CDUGMQAOFJYTRVP6JJZV43MSMQ/action/replication_record"}},"created_at":"2026-07-05T11:13:15.121326+00:00","updated_at":"2026-07-05T11:13:15.121326+00:00"}