{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ROKB2YFQQOCFMEUEVG2A7KSYQF","short_pith_number":"pith:ROKB2YFQ","schema_version":"1.0","canonical_sha256":"8b941d60b08384561284a9b40faa58815b61525aeadb99765151142e8f47f49a","source":{"kind":"arxiv","id":"2508.04266","version":4},"attestation_state":"computed","paper":{"title":"ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huaipeng Zhao, Jian Dong Zhang, Jiangyuan Wang, Kejun Xiao, Qi Sun, Tao Luo, Xiaoyi Zeng","submitted_at":"2025-08-06T09:51:30Z","abstract_excerpt":"Existing benchmarks in e-commerce primarily focus on basic user intents, such as finding or purchasing products. However, real-world users often pursue more complex goals, such as applying vouchers, managing budgets, and finding multi-products seller. To bridge this gap, we propose ShoppingBench, a novel end-to-end shopping benchmark designed to encompass increasingly challenging levels of grounded intent. Specifically, we propose a scalable framework to simulate user instructions based on various intents derived from sampled real-world products. To facilitate consistent and reliable evaluatio"},"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":"2508.04266","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-06T09:51:30Z","cross_cats_sorted":[],"title_canon_sha256":"1d066b2fc399e6706edb5bce7e574a5eb34d5f66d4937d115b271e51c802c488","abstract_canon_sha256":"626de3152150a606d8a60c0f11196e3c670b437639f0ead885deed3d607e5b4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:47.129454Z","signature_b64":"2sdVS1Qy2wGZR6wdXdyB1JPjtlAubpra9ObRLiGLtRWf60vdVhcbCaCrz8SzEJk/QoedZxbDFRquuottNWg3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b941d60b08384561284a9b40faa58815b61525aeadb99765151142e8f47f49a","last_reissued_at":"2026-06-19T16:12:47.128968Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:47.128968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huaipeng Zhao, Jian Dong Zhang, Jiangyuan Wang, Kejun Xiao, Qi Sun, Tao Luo, Xiaoyi Zeng","submitted_at":"2025-08-06T09:51:30Z","abstract_excerpt":"Existing benchmarks in e-commerce primarily focus on basic user intents, such as finding or purchasing products. However, real-world users often pursue more complex goals, such as applying vouchers, managing budgets, and finding multi-products seller. To bridge this gap, we propose ShoppingBench, a novel end-to-end shopping benchmark designed to encompass increasingly challenging levels of grounded intent. Specifically, we propose a scalable framework to simulate user instructions based on various intents derived from sampled real-world products. To facilitate consistent and reliable evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04266","kind":"arxiv","version":4},"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/2508.04266/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":"2508.04266","created_at":"2026-06-19T16:12:47.129025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04266v4","created_at":"2026-06-19T16:12:47.129025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04266","created_at":"2026-06-19T16:12:47.129025+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROKB2YFQQOCF","created_at":"2026-06-19T16:12:47.129025+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROKB2YFQQOCFMEUE","created_at":"2026-06-19T16:12:47.129025+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROKB2YFQ","created_at":"2026-06-19T16:12:47.129025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.18805","citing_title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2508.13024","citing_title":"WebMall -- A Multi-Shop Benchmark for Evaluating Web Agents","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2511.23281","citing_title":"MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report)","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF","json":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF.json","graph_json":"https://pith.science/api/pith-number/ROKB2YFQQOCFMEUEVG2A7KSYQF/graph.json","events_json":"https://pith.science/api/pith-number/ROKB2YFQQOCFMEUEVG2A7KSYQF/events.json","paper":"https://pith.science/paper/ROKB2YFQ"},"agent_actions":{"view_html":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF","download_json":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF.json","view_paper":"https://pith.science/paper/ROKB2YFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04266&json=true","fetch_graph":"https://pith.science/api/pith-number/ROKB2YFQQOCFMEUEVG2A7KSYQF/graph.json","fetch_events":"https://pith.science/api/pith-number/ROKB2YFQQOCFMEUEVG2A7KSYQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF/action/storage_attestation","attest_author":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF/action/author_attestation","sign_citation":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF/action/citation_signature","submit_replication":"https://pith.science/pith/ROKB2YFQQOCFMEUEVG2A7KSYQF/action/replication_record"}},"created_at":"2026-06-19T16:12:47.129025+00:00","updated_at":"2026-06-19T16:12:47.129025+00:00"}