{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LAXA3XNM663K7HGLPUDI4EWKEO","short_pith_number":"pith:LAXA3XNM","schema_version":"1.0","canonical_sha256":"582e0dddacf7b6af9ccb7d068e12ca23a01f611100c764667c7edf2732a5c3e1","source":{"kind":"arxiv","id":"2603.29247","version":3},"attestation_state":"computed","paper":{"title":"MemRerank: Preference Memory for Personalized Product Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Huaixiao Tou, Xuyang Wu, Yi Fang, Yu Gong, Zhiyuan Peng","submitted_at":"2026-03-31T04:16:18Z","abstract_excerpt":"LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmark and evaluation framework centered on an LLM-based \\textbf{1-in-5} selection task, which measures both memory quality and downstream reranking utilit"},"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":"2603.29247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T04:16:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"870694b46d938a29b4a33a5e7b1a3f607f2e838047e3c8d347df5f91eb3125e4","abstract_canon_sha256":"4d09bcc3961b88c39c53b0eb312e2bd04fda5bab79da82270393a87e21e926c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:22.635793Z","signature_b64":"BH8iee6BOyeGGNpx3P9upkL+6rcjHOhCUNytId3hEB9RfCCdgbBEPOgS/6mrO+0MaZKpEsF9E5ZRUt6B3OrZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582e0dddacf7b6af9ccb7d068e12ca23a01f611100c764667c7edf2732a5c3e1","last_reissued_at":"2026-06-19T16:11:22.635442Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:22.635442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemRerank: Preference Memory for Personalized Product Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Huaixiao Tou, Xuyang Wu, Yi Fang, Yu Gong, Zhiyuan Peng","submitted_at":"2026-03-31T04:16:18Z","abstract_excerpt":"LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmark and evaluation framework centered on an LLM-based \\textbf{1-in-5} selection task, which measures both memory quality and downstream reranking utilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29247","kind":"arxiv","version":3},"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/2603.29247/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":"2603.29247","created_at":"2026-06-19T16:11:22.635501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.29247v3","created_at":"2026-06-19T16:11:22.635501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29247","created_at":"2026-06-19T16:11:22.635501+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAXA3XNM663K","created_at":"2026-06-19T16:11:22.635501+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAXA3XNM663K7HGL","created_at":"2026-06-19T16:11:22.635501+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAXA3XNM","created_at":"2026-06-19T16:11:22.635501+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/LAXA3XNM663K7HGLPUDI4EWKEO","json":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO.json","graph_json":"https://pith.science/api/pith-number/LAXA3XNM663K7HGLPUDI4EWKEO/graph.json","events_json":"https://pith.science/api/pith-number/LAXA3XNM663K7HGLPUDI4EWKEO/events.json","paper":"https://pith.science/paper/LAXA3XNM"},"agent_actions":{"view_html":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO","download_json":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO.json","view_paper":"https://pith.science/paper/LAXA3XNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.29247&json=true","fetch_graph":"https://pith.science/api/pith-number/LAXA3XNM663K7HGLPUDI4EWKEO/graph.json","fetch_events":"https://pith.science/api/pith-number/LAXA3XNM663K7HGLPUDI4EWKEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO/action/storage_attestation","attest_author":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO/action/author_attestation","sign_citation":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO/action/citation_signature","submit_replication":"https://pith.science/pith/LAXA3XNM663K7HGLPUDI4EWKEO/action/replication_record"}},"created_at":"2026-06-19T16:11:22.635501+00:00","updated_at":"2026-06-19T16:11:22.635501+00:00"}