{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JIZWMDJPKBWSJUBGOX23ZOLBC2","short_pith_number":"pith:JIZWMDJP","schema_version":"1.0","canonical_sha256":"4a33660d2f506d24d02675f5bcb96116a190c71697b4ae6b05c09e1f50867a26","source":{"kind":"arxiv","id":"2607.00017","version":1},"attestation_state":"computed","paper":{"title":"Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Chenxi Miao, Guanqiang QI, Haibo Liu, Jizhou Huang, Liwei Qian, Weikang Li, Xin Pei, Xin Shen, ZhiShu Jiang","submitted_at":"2026-05-28T06:47:48Z","abstract_excerpt":"Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the right user. Existing memory-augmented LLM agents have made progress in building compact memory banks, yet retrieval is still often driven by query-centered similarity or fixed ranking rules, leaving user-conditioned relevance underexplored.To address this gap, we propose Profile-guided Personalized Retrieval Optimization (PPRO), a retrieval-centric framework that makes memory retrieval both user-aware and optimizable.PPRO builds episodic and semantic"},"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":"2607.00017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-28T06:47:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7c620b6bc14993af35d594bf585c3cf20cb5ad9e4e98d5564bd888e63e5b7534","abstract_canon_sha256":"c7dc2019e579eea5e7dd36055a1a3f68c6bbc08cc3552e52c5fd07c1d4d742d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:04.812668Z","signature_b64":"+H/c34CRPD8YN7+zHiaCTovFcPhaYXo80pvo/lyLQLsUmkKx2gghVAcDCN/XBZhVnLCAk6iTofrJUoKNxEPsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a33660d2f506d24d02675f5bcb96116a190c71697b4ae6b05c09e1f50867a26","last_reissued_at":"2026-07-02T00:18:04.812080Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:04.812080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Chenxi Miao, Guanqiang QI, Haibo Liu, Jizhou Huang, Liwei Qian, Weikang Li, Xin Pei, Xin Shen, ZhiShu Jiang","submitted_at":"2026-05-28T06:47:48Z","abstract_excerpt":"Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the right user. Existing memory-augmented LLM agents have made progress in building compact memory banks, yet retrieval is still often driven by query-centered similarity or fixed ranking rules, leaving user-conditioned relevance underexplored.To address this gap, we propose Profile-guided Personalized Retrieval Optimization (PPRO), a retrieval-centric framework that makes memory retrieval both user-aware and optimizable.PPRO builds episodic and semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00017","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/2607.00017/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":"2607.00017","created_at":"2026-07-02T00:18:04.812149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00017v1","created_at":"2026-07-02T00:18:04.812149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00017","created_at":"2026-07-02T00:18:04.812149+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIZWMDJPKBWS","created_at":"2026-07-02T00:18:04.812149+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIZWMDJPKBWSJUBG","created_at":"2026-07-02T00:18:04.812149+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIZWMDJP","created_at":"2026-07-02T00:18:04.812149+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/JIZWMDJPKBWSJUBGOX23ZOLBC2","json":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2.json","graph_json":"https://pith.science/api/pith-number/JIZWMDJPKBWSJUBGOX23ZOLBC2/graph.json","events_json":"https://pith.science/api/pith-number/JIZWMDJPKBWSJUBGOX23ZOLBC2/events.json","paper":"https://pith.science/paper/JIZWMDJP"},"agent_actions":{"view_html":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2","download_json":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2.json","view_paper":"https://pith.science/paper/JIZWMDJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00017&json=true","fetch_graph":"https://pith.science/api/pith-number/JIZWMDJPKBWSJUBGOX23ZOLBC2/graph.json","fetch_events":"https://pith.science/api/pith-number/JIZWMDJPKBWSJUBGOX23ZOLBC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2/action/storage_attestation","attest_author":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2/action/author_attestation","sign_citation":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2/action/citation_signature","submit_replication":"https://pith.science/pith/JIZWMDJPKBWSJUBGOX23ZOLBC2/action/replication_record"}},"created_at":"2026-07-02T00:18:04.812149+00:00","updated_at":"2026-07-02T00:18:04.812149+00:00"}