{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YNBYP5ES46Y65C5CTPUMZDOQ5L","short_pith_number":"pith:YNBYP5ES","schema_version":"1.0","canonical_sha256":"c34387f492e7b1ee8ba29be8cc8dd0ead5a2a9ed15b1e4d09e5a153914d4f93a","source":{"kind":"arxiv","id":"2109.08678","version":2},"attestation_state":"computed","paper":{"title":"RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Kazuma Hashimoto, Semih Yavuz, Xi Ye, Yingbo Zhou","submitted_at":"2021-09-17T17:58:28Z","abstract_excerpt":"Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-based approaches have shown some success in generalization, but suffer from the coverage issue. We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability. Our approach first uses a contrastive ranker to rank a set of candidate logical forms obtained by searching over the knowledge graph. It then introduces a ta"},"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":"2109.08678","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-17T17:58:28Z","cross_cats_sorted":[],"title_canon_sha256":"25773e5d18024c75c4a7d46b270ee7630d2a76602a5938c76f40b9426799a086","abstract_canon_sha256":"0698ceacd40d4fdb6a9bad65e9759f76d42fc4788d4d76b2799b0197758911a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:45.101770Z","signature_b64":"lWCiq1uNPAveAIZ+uDnkFXyaGbL05f6R7MWDJ8k7JPWmXxVNczMRqNEGiu86me+goDZNwT25KiSBotXU/I1DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c34387f492e7b1ee8ba29be8cc8dd0ead5a2a9ed15b1e4d09e5a153914d4f93a","last_reissued_at":"2026-07-05T04:06:45.101421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:45.101421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Kazuma Hashimoto, Semih Yavuz, Xi Ye, Yingbo Zhou","submitted_at":"2021-09-17T17:58:28Z","abstract_excerpt":"Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-based approaches have shown some success in generalization, but suffer from the coverage issue. We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability. Our approach first uses a contrastive ranker to rank a set of candidate logical forms obtained by searching over the knowledge graph. It then introduces a ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08678","kind":"arxiv","version":2},"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/2109.08678/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":"2109.08678","created_at":"2026-07-05T04:06:45.101477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08678v2","created_at":"2026-07-05T04:06:45.101477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08678","created_at":"2026-07-05T04:06:45.101477+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNBYP5ES46Y6","created_at":"2026-07-05T04:06:45.101477+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNBYP5ES46Y65C5C","created_at":"2026-07-05T04:06:45.101477+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNBYP5ES","created_at":"2026-07-05T04:06:45.101477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04449","citing_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00845","citing_title":"Graph Query Generation with Constraint-guided Large Language Agents","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L","json":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L.json","graph_json":"https://pith.science/api/pith-number/YNBYP5ES46Y65C5CTPUMZDOQ5L/graph.json","events_json":"https://pith.science/api/pith-number/YNBYP5ES46Y65C5CTPUMZDOQ5L/events.json","paper":"https://pith.science/paper/YNBYP5ES"},"agent_actions":{"view_html":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L","download_json":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L.json","view_paper":"https://pith.science/paper/YNBYP5ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08678&json=true","fetch_graph":"https://pith.science/api/pith-number/YNBYP5ES46Y65C5CTPUMZDOQ5L/graph.json","fetch_events":"https://pith.science/api/pith-number/YNBYP5ES46Y65C5CTPUMZDOQ5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L/action/storage_attestation","attest_author":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L/action/author_attestation","sign_citation":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L/action/citation_signature","submit_replication":"https://pith.science/pith/YNBYP5ES46Y65C5CTPUMZDOQ5L/action/replication_record"}},"created_at":"2026-07-05T04:06:45.101477+00:00","updated_at":"2026-07-05T04:06:45.101477+00:00"}