{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J5E3HVVON4YEHHIU7CXCG5VLIX","short_pith_number":"pith:J5E3HVVO","schema_version":"1.0","canonical_sha256":"4f49b3d6ae6f30439d14f8ae2376ab45d3d66f42ebfdd18000b88e9def9f7fec","source":{"kind":"arxiv","id":"2608.09282","version":1},"attestation_state":"computed","paper":{"title":"ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Adrian Li, Heming Xia, Jace Wong, Kelong Mao, Lirui Luo, Pu Yao, Simiu Gu, Sulong Xu, Xinwei Yang, Yudong Guo","submitted_at":"2026-08-10T08:37:54Z","abstract_excerpt":"Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product. Such combo-shopping tasks arise in device setup, meal preparation, event planning, and group takeout ordering, requiring joint reasoning about item compatibility, availability, store-level requirements, delivery fees, coupons, and budgets. Evaluation is challenging because multiple baskets may satisfy the same request, making exact-match metrics unsuitable, whereas semantic evaluation alone cannot detect infeasible orders, invalid coupon combinations, or incorrect payments. "},"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":"2608.09282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T08:37:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"15049c41625c55a6bbdd7f8ce461a0e8fbcd2fdbcd80c766a0cee71130a2a449","abstract_canon_sha256":"575be2699ec836c05b6ef0674c99843b270af7df1707f35436ea1ebca1bee6d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:22:14.846056Z","signature_b64":"w+BzYE5w4pqw9ChrX0DA1HIoIC+n8ns7bVeELayCx4ILB471aRpE9CM1mg7bBOz2Av3IkDWkMrIaL+ELIPHCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f49b3d6ae6f30439d14f8ae2376ab45d3d66f42ebfdd18000b88e9def9f7fec","last_reissued_at":"2026-08-11T02:22:14.844352Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:22:14.844352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Adrian Li, Heming Xia, Jace Wong, Kelong Mao, Lirui Luo, Pu Yao, Simiu Gu, Sulong Xu, Xinwei Yang, Yudong Guo","submitted_at":"2026-08-10T08:37:54Z","abstract_excerpt":"Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product. Such combo-shopping tasks arise in device setup, meal preparation, event planning, and group takeout ordering, requiring joint reasoning about item compatibility, availability, store-level requirements, delivery fees, coupons, and budgets. Evaluation is challenging because multiple baskets may satisfy the same request, making exact-match metrics unsuitable, whereas semantic evaluation alone cannot detect infeasible orders, invalid coupon combinations, or incorrect payments. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09282","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/2608.09282/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":"2608.09282","created_at":"2026-08-11T02:22:14.845014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09282v1","created_at":"2026-08-11T02:22:14.845014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09282","created_at":"2026-08-11T02:22:14.845014+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5E3HVVON4YE","created_at":"2026-08-11T02:22:14.845014+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5E3HVVON4YEHHIU","created_at":"2026-08-11T02:22:14.845014+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5E3HVVO","created_at":"2026-08-11T02:22:14.845014+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/J5E3HVVON4YEHHIU7CXCG5VLIX","json":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX.json","graph_json":"https://pith.science/api/pith-number/J5E3HVVON4YEHHIU7CXCG5VLIX/graph.json","events_json":"https://pith.science/api/pith-number/J5E3HVVON4YEHHIU7CXCG5VLIX/events.json","paper":"https://pith.science/paper/J5E3HVVO"},"agent_actions":{"view_html":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX","download_json":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX.json","view_paper":"https://pith.science/paper/J5E3HVVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09282&json=true","fetch_graph":"https://pith.science/api/pith-number/J5E3HVVON4YEHHIU7CXCG5VLIX/graph.json","fetch_events":"https://pith.science/api/pith-number/J5E3HVVON4YEHHIU7CXCG5VLIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX/action/storage_attestation","attest_author":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX/action/author_attestation","sign_citation":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX/action/citation_signature","submit_replication":"https://pith.science/pith/J5E3HVVON4YEHHIU7CXCG5VLIX/action/replication_record"}},"created_at":"2026-08-11T02:22:14.845014+00:00","updated_at":"2026-08-11T02:22:14.845014+00:00"}