{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WSORK3Q6RDOYR7QR3U22QHM2Y7","short_pith_number":"pith:WSORK3Q6","schema_version":"1.0","canonical_sha256":"b49d156e1e88dd88fe11dd35a81d9ac7d067ff6ab5486d22713b8a5651ba1e0a","source":{"kind":"arxiv","id":"1905.07098","version":2},"attestation_state":"computed","paper":{"title":"Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mo Yu, Shiyu Chang, Wenhan Xiong, William Yang Wang, Xiaoxiao Guo","submitted_at":"2019-05-17T03:00:46Z","abstract_excerpt":"We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the w"},"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":"1905.07098","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-17T03:00:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"62f6f918df2cf3c42b11be0d9f8f9f92b664c5cdfd9d883e2f6dd85cc3bd1789","abstract_canon_sha256":"d61f979f820068e87010de22e9fa268cfe2014b128ca706523084855956d25f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.499272Z","signature_b64":"FV17yz5FVgGn3x+X9GDjKjN8f8MYw8TONUZZ3eZ+oEzlRKeRAr8M1GAkYCXELUDC8BTZz5XxcC75m8JaUWsVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b49d156e1e88dd88fe11dd35a81d9ac7d067ff6ab5486d22713b8a5651ba1e0a","last_reissued_at":"2026-05-17T23:44:37.498843Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.498843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mo Yu, Shiyu Chang, Wenhan Xiong, William Yang Wang, Xiaoxiao Guo","submitted_at":"2019-05-17T03:00:46Z","abstract_excerpt":"We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07098","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":""},"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":"1905.07098","created_at":"2026-05-17T23:44:37.498908+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07098v2","created_at":"2026-05-17T23:44:37.498908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07098","created_at":"2026-05-17T23:44:37.498908+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSORK3Q6RDOY","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSORK3Q6RDOYR7QR","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSORK3Q6","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20283","citing_title":"Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7","json":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7.json","graph_json":"https://pith.science/api/pith-number/WSORK3Q6RDOYR7QR3U22QHM2Y7/graph.json","events_json":"https://pith.science/api/pith-number/WSORK3Q6RDOYR7QR3U22QHM2Y7/events.json","paper":"https://pith.science/paper/WSORK3Q6"},"agent_actions":{"view_html":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7","download_json":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7.json","view_paper":"https://pith.science/paper/WSORK3Q6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07098&json=true","fetch_graph":"https://pith.science/api/pith-number/WSORK3Q6RDOYR7QR3U22QHM2Y7/graph.json","fetch_events":"https://pith.science/api/pith-number/WSORK3Q6RDOYR7QR3U22QHM2Y7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7/action/storage_attestation","attest_author":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7/action/author_attestation","sign_citation":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7/action/citation_signature","submit_replication":"https://pith.science/pith/WSORK3Q6RDOYR7QR3U22QHM2Y7/action/replication_record"}},"created_at":"2026-05-17T23:44:37.498908+00:00","updated_at":"2026-05-17T23:44:37.498908+00:00"}