{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:POLFLWVMZLMCDEJPOXG3SDLCYE","short_pith_number":"pith:POLFLWVM","schema_version":"1.0","canonical_sha256":"7b9655daaccad821912f75cdb90d62c110fdc28fc48caca8d6442f9a7d1f911d","source":{"kind":"arxiv","id":"2506.02839","version":1},"attestation_state":"computed","paper":{"title":"DeepShop: A Benchmark for Deep Research Shopping Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lingyong Yan, Maarten de Rijke, Xiaoyu Zhang, Xiuying Chen, Yougang Lyu, Zhaochun Ren","submitted_at":"2025-06-03T13:08:17Z","abstract_excerpt":"Web agents for online shopping have shown great promise in automating user interactions across e-commerce platforms. Benchmarks for assessing such agents do not reflect the complexity of real-world shopping scenarios, as they often consist of overly simple queries with deterministic paths, such as \"Find iPhone 15.\" Real shopping scenarios are inherently more layered, involving multi-dimensional product attributes, search filters, and user-specific sorting preferences. To address this gap, we introduce DeepShop, a benchmark designed to evaluate web agents in complex and realistic online shoppin"},"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":"2506.02839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-03T13:08:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e57c99ffb5ae6a652963ee02e67bdbd676f73513a8c248111cb18dab6623ffbb","abstract_canon_sha256":"24136785fd8dfb566e98d44498729ad7947f26865df247cc2fbf20886b59ab18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:10.179631Z","signature_b64":"OLzU+3BygdCzwZb4KP+HY592VU23mco7obvRqPRiklJSb1IiQKGvkD/h3rYhgDGByxEkap/truAL80jAmTPsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b9655daaccad821912f75cdb90d62c110fdc28fc48caca8d6442f9a7d1f911d","last_reissued_at":"2026-07-05T11:15:10.179093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:10.179093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepShop: A Benchmark for Deep Research Shopping Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lingyong Yan, Maarten de Rijke, Xiaoyu Zhang, Xiuying Chen, Yougang Lyu, Zhaochun Ren","submitted_at":"2025-06-03T13:08:17Z","abstract_excerpt":"Web agents for online shopping have shown great promise in automating user interactions across e-commerce platforms. Benchmarks for assessing such agents do not reflect the complexity of real-world shopping scenarios, as they often consist of overly simple queries with deterministic paths, such as \"Find iPhone 15.\" Real shopping scenarios are inherently more layered, involving multi-dimensional product attributes, search filters, and user-specific sorting preferences. To address this gap, we introduce DeepShop, a benchmark designed to evaluate web agents in complex and realistic online shoppin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02839","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/2506.02839/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":"2506.02839","created_at":"2026-07-05T11:15:10.179155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02839v1","created_at":"2026-07-05T11:15:10.179155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02839","created_at":"2026-07-05T11:15:10.179155+00:00"},{"alias_kind":"pith_short_12","alias_value":"POLFLWVMZLMC","created_at":"2026-07-05T11:15:10.179155+00:00"},{"alias_kind":"pith_short_16","alias_value":"POLFLWVMZLMCDEJP","created_at":"2026-07-05T11:15:10.179155+00:00"},{"alias_kind":"pith_short_8","alias_value":"POLFLWVM","created_at":"2026-07-05T11:15:10.179155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13385","citing_title":"Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02031","citing_title":"OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14786","citing_title":"Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18805","citing_title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16116","citing_title":"ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13024","citing_title":"WebMall -- A Multi-Shop Benchmark for Evaluating Web Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15832","citing_title":"A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains","ref_index":12,"is_internal_anchor":false},{"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":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25562","citing_title":"SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08516","citing_title":"MolmoWeb: Open Visual Web Agent and Open Data for the Open Web","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06761","citing_title":"Weblica: Scalable and Reproducible Training Environments for Visual Web Agents","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE","json":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE.json","graph_json":"https://pith.science/api/pith-number/POLFLWVMZLMCDEJPOXG3SDLCYE/graph.json","events_json":"https://pith.science/api/pith-number/POLFLWVMZLMCDEJPOXG3SDLCYE/events.json","paper":"https://pith.science/paper/POLFLWVM"},"agent_actions":{"view_html":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE","download_json":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE.json","view_paper":"https://pith.science/paper/POLFLWVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02839&json=true","fetch_graph":"https://pith.science/api/pith-number/POLFLWVMZLMCDEJPOXG3SDLCYE/graph.json","fetch_events":"https://pith.science/api/pith-number/POLFLWVMZLMCDEJPOXG3SDLCYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE/action/storage_attestation","attest_author":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE/action/author_attestation","sign_citation":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE/action/citation_signature","submit_replication":"https://pith.science/pith/POLFLWVMZLMCDEJPOXG3SDLCYE/action/replication_record"}},"created_at":"2026-07-05T11:15:10.179155+00:00","updated_at":"2026-07-05T11:15:10.179155+00:00"}