{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GM6SF3VZKGHAPS3DNAZJMZS3BH","short_pith_number":"pith:GM6SF3VZ","schema_version":"1.0","canonical_sha256":"333d22eeb9518e07cb63683296665b09dd93c6a79ec69512403a11893929b13e","source":{"kind":"arxiv","id":"2110.04330","version":2},"attestation_state":"computed","paper":{"title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Donghan Yu, Michael Zeng, Shuohang Wang, Wenhao Yu, Xiang Ren, Yichong Xu, Yiming Yang, Yuwei Fang","submitted_at":"2021-10-08T18:39:59Z","abstract_excerpt":"Current Open-Domain Question Answering (ODQA) model paradigm often contains a retrieving module and a reading module. Given an input question, the reading module predicts the answer from the relevant passages which are retrieved by the retriever. The recent proposed Fusion-in-Decoder (FiD), which is built on top of the pretrained generative model T5, achieves the state-of-the-art performance in the reading module. Although being effective, it remains constrained by inefficient attention on all retrieved passages which contain a lot of noise. In this work, we propose a novel method KG-FiD, whic"},"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":"2110.04330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-08T18:39:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6bb09610ac63dd258758247a1a2f3a3aea3d9b9b90d1b26f7e43e735f7349872","abstract_canon_sha256":"d1bd8ed3d49622b1bee96b9de7bcea2cc9813aae7b9d2f3f73b6bf56f0d636b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:09.846873Z","signature_b64":"+j6CBJEHemYcw1nI3WV7IdZO6IpT4Hudr1k6Z8Y84FYtOLOfJ7NDQe5g4YaXrr072Zj/ugwzrstOBECrhs/IAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"333d22eeb9518e07cb63683296665b09dd93c6a79ec69512403a11893929b13e","last_reissued_at":"2026-07-05T04:29:09.846336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:09.846336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Donghan Yu, Michael Zeng, Shuohang Wang, Wenhao Yu, Xiang Ren, Yichong Xu, Yiming Yang, Yuwei Fang","submitted_at":"2021-10-08T18:39:59Z","abstract_excerpt":"Current Open-Domain Question Answering (ODQA) model paradigm often contains a retrieving module and a reading module. Given an input question, the reading module predicts the answer from the relevant passages which are retrieved by the retriever. The recent proposed Fusion-in-Decoder (FiD), which is built on top of the pretrained generative model T5, achieves the state-of-the-art performance in the reading module. Although being effective, it remains constrained by inefficient attention on all retrieved passages which contain a lot of noise. In this work, we propose a novel method KG-FiD, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04330","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/2110.04330/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":"2110.04330","created_at":"2026-07-05T04:29:09.846389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04330v2","created_at":"2026-07-05T04:29:09.846389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04330","created_at":"2026-07-05T04:29:09.846389+00:00"},{"alias_kind":"pith_short_12","alias_value":"GM6SF3VZKGHA","created_at":"2026-07-05T04:29:09.846389+00:00"},{"alias_kind":"pith_short_16","alias_value":"GM6SF3VZKGHAPS3D","created_at":"2026-07-05T04:29:09.846389+00:00"},{"alias_kind":"pith_short_8","alias_value":"GM6SF3VZ","created_at":"2026-07-05T04:29:09.846389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04413","citing_title":"MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot","ref_index":71,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH","json":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH.json","graph_json":"https://pith.science/api/pith-number/GM6SF3VZKGHAPS3DNAZJMZS3BH/graph.json","events_json":"https://pith.science/api/pith-number/GM6SF3VZKGHAPS3DNAZJMZS3BH/events.json","paper":"https://pith.science/paper/GM6SF3VZ"},"agent_actions":{"view_html":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH","download_json":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH.json","view_paper":"https://pith.science/paper/GM6SF3VZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04330&json=true","fetch_graph":"https://pith.science/api/pith-number/GM6SF3VZKGHAPS3DNAZJMZS3BH/graph.json","fetch_events":"https://pith.science/api/pith-number/GM6SF3VZKGHAPS3DNAZJMZS3BH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH/action/storage_attestation","attest_author":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH/action/author_attestation","sign_citation":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH/action/citation_signature","submit_replication":"https://pith.science/pith/GM6SF3VZKGHAPS3DNAZJMZS3BH/action/replication_record"}},"created_at":"2026-07-05T04:29:09.846389+00:00","updated_at":"2026-07-05T04:29:09.846389+00:00"}