{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PO4SGFVWOD73S42LDRHZ5LMLLW","short_pith_number":"pith:PO4SGFVW","schema_version":"1.0","canonical_sha256":"7bb92316b670ffb9734b1c4f9ead8b5db385b29c5f3fdacb46ec43bd384f9ba7","source":{"kind":"arxiv","id":"2404.13207","version":3},"attestation_state":"computed","paper":{"title":"STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"James Zou, Jure Leskovec, Kaidi Cao, Karthik Subbian, Kexin Huang, Michihiro Yasunaga, Qian Huang, Shirley Wu, Shiyu Zhao, Vassilis N. Ioannidis","submitted_at":"2024-04-19T22:54:54Z","abstract_excerpt":"Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g., textual descriptions of products) and structured (e.g., entity relations of products) information. However, many previous works studied textual and relational retrieval tasks as separate topics. To address the gap, we develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Relational Knowledge Bases. Our benchmark covers three domains: product search, academic paper search, and queries in pr"},"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":"2404.13207","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-19T22:54:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"660655f2a62fbec428cf68d1ecc2dc02faa93de8e88e84d2fe920790f4490e0e","abstract_canon_sha256":"cc63d38d82eac15cadabec72467d7e928c1372a94871c73913fe6379d16f63c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:05.048385Z","signature_b64":"JA3Se5GXLcEo5M+vHKvmA049odbpI7WW9T/c0CtSvioU0go4R9m3s95WDyieLbvOVUtASORxMd6mfZK/HtOjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bb92316b670ffb9734b1c4f9ead8b5db385b29c5f3fdacb46ec43bd384f9ba7","last_reissued_at":"2026-07-05T09:23:05.047898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:05.047898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"James Zou, Jure Leskovec, Kaidi Cao, Karthik Subbian, Kexin Huang, Michihiro Yasunaga, Qian Huang, Shirley Wu, Shiyu Zhao, Vassilis N. Ioannidis","submitted_at":"2024-04-19T22:54:54Z","abstract_excerpt":"Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g., textual descriptions of products) and structured (e.g., entity relations of products) information. However, many previous works studied textual and relational retrieval tasks as separate topics. To address the gap, we develop STARK, a large-scale Semi-structure retrieval benchmark on Textual and Relational Knowledge Bases. Our benchmark covers three domains: product search, academic paper search, and queries in pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13207","kind":"arxiv","version":3},"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/2404.13207/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":"2404.13207","created_at":"2026-07-05T09:23:05.047958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13207v3","created_at":"2026-07-05T09:23:05.047958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13207","created_at":"2026-07-05T09:23:05.047958+00:00"},{"alias_kind":"pith_short_12","alias_value":"PO4SGFVWOD73","created_at":"2026-07-05T09:23:05.047958+00:00"},{"alias_kind":"pith_short_16","alias_value":"PO4SGFVWOD73S42L","created_at":"2026-07-05T09:23:05.047958+00:00"},{"alias_kind":"pith_short_8","alias_value":"PO4SGFVW","created_at":"2026-07-05T09:23:05.047958+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/PO4SGFVWOD73S42LDRHZ5LMLLW","json":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW.json","graph_json":"https://pith.science/api/pith-number/PO4SGFVWOD73S42LDRHZ5LMLLW/graph.json","events_json":"https://pith.science/api/pith-number/PO4SGFVWOD73S42LDRHZ5LMLLW/events.json","paper":"https://pith.science/paper/PO4SGFVW"},"agent_actions":{"view_html":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW","download_json":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW.json","view_paper":"https://pith.science/paper/PO4SGFVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13207&json=true","fetch_graph":"https://pith.science/api/pith-number/PO4SGFVWOD73S42LDRHZ5LMLLW/graph.json","fetch_events":"https://pith.science/api/pith-number/PO4SGFVWOD73S42LDRHZ5LMLLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW/action/storage_attestation","attest_author":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW/action/author_attestation","sign_citation":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW/action/citation_signature","submit_replication":"https://pith.science/pith/PO4SGFVWOD73S42LDRHZ5LMLLW/action/replication_record"}},"created_at":"2026-07-05T09:23:05.047958+00:00","updated_at":"2026-07-05T09:23:05.047958+00:00"}