{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:POLFLWVMZLMCDEJPOXG3SDLCYE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"24136785fd8dfb566e98d44498729ad7947f26865df247cc2fbf20886b59ab18","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-03T13:08:17Z","title_canon_sha256":"e57c99ffb5ae6a652963ee02e67bdbd676f73513a8c248111cb18dab6623ffbb"},"schema_version":"1.0","source":{"id":"2506.02839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02839","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02839v1","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02839","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"POLFLWVMZLMC","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"pith_short_16","alias_value":"POLFLWVMZLMCDEJP","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"pith_short_8","alias_value":"POLFLWVM","created_at":"2026-07-05T11:15:10Z"}],"graph_snapshots":[{"event_id":"sha256:fc26a8f2647366ffec69416188574c15b720bc13de3e815107a3728e265c7855","target":"graph","created_at":"2026-07-05T11:15:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.02839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lingyong Yan, Maarten de Rijke, Xiaoyu Zhang, Xiuying Chen, Yougang Lyu, Zhaochun Ren","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-03T13:08:17Z","title":"DeepShop: A Benchmark for Deep Research Shopping Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02839","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bfae256383c28c9e36a8d9187bc05aee958f5fa48ae11212ac5a14f78bf0f165","target":"record","created_at":"2026-07-05T11:15:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"24136785fd8dfb566e98d44498729ad7947f26865df247cc2fbf20886b59ab18","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-03T13:08:17Z","title_canon_sha256":"e57c99ffb5ae6a652963ee02e67bdbd676f73513a8c248111cb18dab6623ffbb"},"schema_version":"1.0","source":{"id":"2506.02839","kind":"arxiv","version":1}},"canonical_sha256":"7b9655daaccad821912f75cdb90d62c110fdc28fc48caca8d6442f9a7d1f911d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b9655daaccad821912f75cdb90d62c110fdc28fc48caca8d6442f9a7d1f911d","first_computed_at":"2026-07-05T11:15:10.179093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:10.179093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OLzU+3BygdCzwZb4KP+HY592VU23mco7obvRqPRiklJSb1IiQKGvkD/h3rYhgDGByxEkap/truAL80jAmTPsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:10.179631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfae256383c28c9e36a8d9187bc05aee958f5fa48ae11212ac5a14f78bf0f165","sha256:fc26a8f2647366ffec69416188574c15b720bc13de3e815107a3728e265c7855"],"state_sha256":"40ff00209f4b210d812a26389ff86851aad116dc3aba961fdf0291c2a7c1c8e1"}