{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4RUTLTGJ6WPE2YQQBURKQ3I4KM","short_pith_number":"pith:4RUTLTGJ","schema_version":"1.0","canonical_sha256":"e46935ccc9f59e4d62100d22a86d1c532df6ea779c10cacc994d95169f83db91","source":{"kind":"arxiv","id":"2005.05806","version":2},"attestation_state":"computed","paper":{"title":"Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Daxin Jiang, Haoyang Wen, Ming Zhou, Nan Duan, Ting Liu, Wanxiang Che, Yaobo Liang","submitted_at":"2020-05-12T14:20:09Z","abstract_excerpt":"Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the effectiveness of existing methods on this benchmark, they treat these two sub-tasks individually during training while ignoring their dependencies. To address this issue, we present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature, which are different levels of granularity: documents, paragr"},"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":"2005.05806","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-12T14:20:09Z","cross_cats_sorted":[],"title_canon_sha256":"075f1d1261dd0c041cc2017c8c464b482bcd2827b88aca01fc3508c373dca785","abstract_canon_sha256":"69f927459269e27f080bdd82f98127c509f331b53e575cda2bf657334166b8e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:30.839138Z","signature_b64":"vev8KYSDvO9lbY6WF+a3iIDY1YCDKpnBgOHyzafCev4KmcwCRdVYiGHsx2weTHTtB96vCv8A6u+yNYnCZPPgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e46935ccc9f59e4d62100d22a86d1c532df6ea779c10cacc994d95169f83db91","last_reissued_at":"2026-07-05T01:02:30.838660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:30.838660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Daxin Jiang, Haoyang Wen, Ming Zhou, Nan Duan, Ting Liu, Wanxiang Che, Yaobo Liang","submitted_at":"2020-05-12T14:20:09Z","abstract_excerpt":"Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the effectiveness of existing methods on this benchmark, they treat these two sub-tasks individually during training while ignoring their dependencies. To address this issue, we present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature, which are different levels of granularity: documents, paragr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05806","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/2005.05806/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":"2005.05806","created_at":"2026-07-05T01:02:30.838734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.05806v2","created_at":"2026-07-05T01:02:30.838734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05806","created_at":"2026-07-05T01:02:30.838734+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RUTLTGJ6WPE","created_at":"2026-07-05T01:02:30.838734+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RUTLTGJ6WPE2YQQ","created_at":"2026-07-05T01:02:30.838734+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RUTLTGJ","created_at":"2026-07-05T01:02:30.838734+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/4RUTLTGJ6WPE2YQQBURKQ3I4KM","json":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM.json","graph_json":"https://pith.science/api/pith-number/4RUTLTGJ6WPE2YQQBURKQ3I4KM/graph.json","events_json":"https://pith.science/api/pith-number/4RUTLTGJ6WPE2YQQBURKQ3I4KM/events.json","paper":"https://pith.science/paper/4RUTLTGJ"},"agent_actions":{"view_html":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM","download_json":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM.json","view_paper":"https://pith.science/paper/4RUTLTGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.05806&json=true","fetch_graph":"https://pith.science/api/pith-number/4RUTLTGJ6WPE2YQQBURKQ3I4KM/graph.json","fetch_events":"https://pith.science/api/pith-number/4RUTLTGJ6WPE2YQQBURKQ3I4KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM/action/storage_attestation","attest_author":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM/action/author_attestation","sign_citation":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM/action/citation_signature","submit_replication":"https://pith.science/pith/4RUTLTGJ6WPE2YQQBURKQ3I4KM/action/replication_record"}},"created_at":"2026-07-05T01:02:30.838734+00:00","updated_at":"2026-07-05T01:02:30.838734+00:00"}