{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P4BIFC4D7H4DIQGJZRHO4JP6R5","short_pith_number":"pith:P4BIFC4D","schema_version":"1.0","canonical_sha256":"7f02828b83f9f83440c9cc4eee25fe8f62c3e17df3b641934137822379cc9e5c","source":{"kind":"arxiv","id":"2212.00959","version":2},"attestation_state":"computed","paper":{"title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinhao Jiang, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao","submitted_at":"2022-12-02T04:08:09Z","abstract_excerpt":"Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question on a large-scale Knowledge Graph (KG). To cope with the vast search space, existing work usually adopts a two-stage approach: it first retrieves a relatively small subgraph related to the question and then performs the reasoning on the subgraph to find the answer entities accurately. Although these two stages are highly related, previous work employs very different technical solutions for developing the retrieval "},"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":"2212.00959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-02T04:08:09Z","cross_cats_sorted":[],"title_canon_sha256":"158a06536959d929d0acf8762303c85be228a832587695be7de8530af1a02dce","abstract_canon_sha256":"ab38a36c57e2337eca199c39470ddab4ce83a1857626d77a68c9394442230ec2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:04.933491Z","signature_b64":"pNhjWN+d/L6UJYcJMtJvs2LufAaAnj9nOIUoLtxqYHZ/FsjkiRcybPEWg7WvxswiL4PZ/P3bEdT3DxZ+qj1PDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f02828b83f9f83440c9cc4eee25fe8f62c3e17df3b641934137822379cc9e5c","last_reissued_at":"2026-07-05T05:47:04.933058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:04.933058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinhao Jiang, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao","submitted_at":"2022-12-02T04:08:09Z","abstract_excerpt":"Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question on a large-scale Knowledge Graph (KG). To cope with the vast search space, existing work usually adopts a two-stage approach: it first retrieves a relatively small subgraph related to the question and then performs the reasoning on the subgraph to find the answer entities accurately. Although these two stages are highly related, previous work employs very different technical solutions for developing the retrieval "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00959","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/2212.00959/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":"2212.00959","created_at":"2026-07-05T05:47:04.933116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.00959v2","created_at":"2026-07-05T05:47:04.933116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00959","created_at":"2026-07-05T05:47:04.933116+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4BIFC4D7H4D","created_at":"2026-07-05T05:47:04.933116+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4BIFC4D7H4DIQGJ","created_at":"2026-07-05T05:47:04.933116+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4BIFC4D","created_at":"2026-07-05T05:47:04.933116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.15353","citing_title":"NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04449","citing_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5","json":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5.json","graph_json":"https://pith.science/api/pith-number/P4BIFC4D7H4DIQGJZRHO4JP6R5/graph.json","events_json":"https://pith.science/api/pith-number/P4BIFC4D7H4DIQGJZRHO4JP6R5/events.json","paper":"https://pith.science/paper/P4BIFC4D"},"agent_actions":{"view_html":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5","download_json":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5.json","view_paper":"https://pith.science/paper/P4BIFC4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.00959&json=true","fetch_graph":"https://pith.science/api/pith-number/P4BIFC4D7H4DIQGJZRHO4JP6R5/graph.json","fetch_events":"https://pith.science/api/pith-number/P4BIFC4D7H4DIQGJZRHO4JP6R5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5/action/storage_attestation","attest_author":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5/action/author_attestation","sign_citation":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5/action/citation_signature","submit_replication":"https://pith.science/pith/P4BIFC4D7H4DIQGJZRHO4JP6R5/action/replication_record"}},"created_at":"2026-07-05T05:47:04.933116+00:00","updated_at":"2026-07-05T05:47:04.933116+00:00"}