{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YDFW6APFQWI64SOFTJKV75CEC4","short_pith_number":"pith:YDFW6APF","schema_version":"1.0","canonical_sha256":"c0cb6f01e58591ee49c59a555ff4441736206e5799ebcb06db37ed5ef0d21699","source":{"kind":"arxiv","id":"2602.12394","version":2},"attestation_state":"computed","paper":{"title":"Synthetic Interaction Data for Scalable Personalization in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Stefan Feuerriegel, Wenjie Wang, Xiangliang Zhang, Xiaonan Luo, Yuchen Ma, Yue Huang","submitted_at":"2026-02-12T20:41:22Z","abstract_excerpt":"Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users. This gap is primarily due to (i) the absence of high-quality, privacy-sensitive data that capture personalized user-LLM interactions at scale, and (ii) the lack of robust reward signals for individual preferences. To overcome existing data limitations, we introduce a high-fidelity synthetic data generation f"},"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":"2602.12394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-12T20:41:22Z","cross_cats_sorted":[],"title_canon_sha256":"06c81451213e75f62f4a077d6a785ea2e1c5fc2e113f008000ec3d8cb0a22c6e","abstract_canon_sha256":"f653820c1c79a35342d96c6e92f47667bdd59e02440810da4ddd08320bf36b69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:33.973524Z","signature_b64":"yOk2TbHYHDEMngeM3I8K+KpGtxiEj7S/nlRoNdkRnNmZNQYZlRKOeIjXxagYQvjtp8ANT8tMoK6jp6MNHaN6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0cb6f01e58591ee49c59a555ff4441736206e5799ebcb06db37ed5ef0d21699","last_reissued_at":"2026-06-30T01:17:33.972634Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:33.972634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Interaction Data for Scalable Personalization in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Stefan Feuerriegel, Wenjie Wang, Xiangliang Zhang, Xiaonan Luo, Yuchen Ma, Yue Huang","submitted_at":"2026-02-12T20:41:22Z","abstract_excerpt":"Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users. This gap is primarily due to (i) the absence of high-quality, privacy-sensitive data that capture personalized user-LLM interactions at scale, and (ii) the lack of robust reward signals for individual preferences. To overcome existing data limitations, we introduce a high-fidelity synthetic data generation f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12394","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/2602.12394/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":"2602.12394","created_at":"2026-06-30T01:17:33.972755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12394v2","created_at":"2026-06-30T01:17:33.972755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12394","created_at":"2026-06-30T01:17:33.972755+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDFW6APFQWI6","created_at":"2026-06-30T01:17:33.972755+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDFW6APFQWI64SOF","created_at":"2026-06-30T01:17:33.972755+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDFW6APF","created_at":"2026-06-30T01:17:33.972755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.07655","citing_title":"Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07632","citing_title":"Post-training makes large language models less human-like","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4","json":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4.json","graph_json":"https://pith.science/api/pith-number/YDFW6APFQWI64SOFTJKV75CEC4/graph.json","events_json":"https://pith.science/api/pith-number/YDFW6APFQWI64SOFTJKV75CEC4/events.json","paper":"https://pith.science/paper/YDFW6APF"},"agent_actions":{"view_html":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4","download_json":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4.json","view_paper":"https://pith.science/paper/YDFW6APF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12394&json=true","fetch_graph":"https://pith.science/api/pith-number/YDFW6APFQWI64SOFTJKV75CEC4/graph.json","fetch_events":"https://pith.science/api/pith-number/YDFW6APFQWI64SOFTJKV75CEC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4/action/storage_attestation","attest_author":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4/action/author_attestation","sign_citation":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4/action/citation_signature","submit_replication":"https://pith.science/pith/YDFW6APFQWI64SOFTJKV75CEC4/action/replication_record"}},"created_at":"2026-06-30T01:17:33.972755+00:00","updated_at":"2026-06-30T01:17:33.972755+00:00"}