{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L6C4LIYUVVRMUD47ZVBPW4O4IC","short_pith_number":"pith:L6C4LIYU","schema_version":"1.0","canonical_sha256":"5f85c5a314ad62ca0f9fcd42fb71dc409240194aaf3e9bab130015e158971ae5","source":{"kind":"arxiv","id":"2603.14864","version":2},"attestation_state":"computed","paper":{"title":"Shopping Companion: A Memory-Augmented LLM Agent for Real-World E-Commerce Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huaipeng Zhao, Kejun Xiao, Tao Luo, Xiaoyi Zeng, Zijian Yu","submitted_at":"2026-03-16T06:07:52Z","abstract_excerpt":"In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budget management, and bundle deals, where accurately capturing user preferences from long-horizon conversations is critical. However, progress is limited by two key challenges: (1) the absence of benchmarks for evaluating long-term preference-aware shopping tasks, and (2) the lack of fine-grained supervision for shopping agent training. To fill the benchmark gap, we introduce Shopping Companion Bench, a novel benchmark comprising two shopping tasks that require cross-session preference memory, grounded in a pro"},"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":"2603.14864","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-16T06:07:52Z","cross_cats_sorted":[],"title_canon_sha256":"34fdcdf80f0fa97d471a9df322d40274aa53bd00d69032fa84e147e8518ec9bb","abstract_canon_sha256":"aef6922d4d3077bdb7d3fd1d4541bafe4eab80e4cdf0f87f84c66ed88ddea3db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:46.648184Z","signature_b64":"0ss1oHZMP/b9dYnFvA9OSWWcqWsAOMjZt+exIan8NXqJDHoQn+QZmLOlk13O82MM8jq5efDvmVWX2DHr6SbvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f85c5a314ad62ca0f9fcd42fb71dc409240194aaf3e9bab130015e158971ae5","last_reissued_at":"2026-05-27T01:05:46.647214Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:46.647214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shopping Companion: A Memory-Augmented LLM Agent for Real-World E-Commerce Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huaipeng Zhao, Kejun Xiao, Tao Luo, Xiaoyi Zeng, Zijian Yu","submitted_at":"2026-03-16T06:07:52Z","abstract_excerpt":"In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budget management, and bundle deals, where accurately capturing user preferences from long-horizon conversations is critical. However, progress is limited by two key challenges: (1) the absence of benchmarks for evaluating long-term preference-aware shopping tasks, and (2) the lack of fine-grained supervision for shopping agent training. To fill the benchmark gap, we introduce Shopping Companion Bench, a novel benchmark comprising two shopping tasks that require cross-session preference memory, grounded in a pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14864","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/2603.14864/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":"2603.14864","created_at":"2026-05-27T01:05:46.647355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14864v2","created_at":"2026-05-27T01:05:46.647355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14864","created_at":"2026-05-27T01:05:46.647355+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6C4LIYUVVRM","created_at":"2026-05-27T01:05:46.647355+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6C4LIYUVVRMUD47","created_at":"2026-05-27T01:05:46.647355+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6C4LIYU","created_at":"2026-05-27T01:05:46.647355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16116","citing_title":"ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC","json":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC.json","graph_json":"https://pith.science/api/pith-number/L6C4LIYUVVRMUD47ZVBPW4O4IC/graph.json","events_json":"https://pith.science/api/pith-number/L6C4LIYUVVRMUD47ZVBPW4O4IC/events.json","paper":"https://pith.science/paper/L6C4LIYU"},"agent_actions":{"view_html":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC","download_json":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC.json","view_paper":"https://pith.science/paper/L6C4LIYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14864&json=true","fetch_graph":"https://pith.science/api/pith-number/L6C4LIYUVVRMUD47ZVBPW4O4IC/graph.json","fetch_events":"https://pith.science/api/pith-number/L6C4LIYUVVRMUD47ZVBPW4O4IC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC/action/storage_attestation","attest_author":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC/action/author_attestation","sign_citation":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC/action/citation_signature","submit_replication":"https://pith.science/pith/L6C4LIYUVVRMUD47ZVBPW4O4IC/action/replication_record"}},"created_at":"2026-05-27T01:05:46.647355+00:00","updated_at":"2026-05-27T01:05:46.647355+00:00"}