{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:36HPUU7B4HH3CRE7E2SXUNLNHQ","short_pith_number":"pith:36HPUU7B","schema_version":"1.0","canonical_sha256":"df8efa53e1e1cfb1449f26a57a356d3c31c8344f48d54c2326bf544fcd2754d3","source":{"kind":"arxiv","id":"1809.02040","version":1},"attestation_state":"computed","paper":{"title":"Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel Gildea, Linfeng Song, Mo Yu, Radu Florian, Yue Zhang, Zhiguo Wang","submitted_at":"2018-09-06T15:18:14Z","abstract_excerpt":"Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two"},"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":"1809.02040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-06T15:18:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9ae9f71185b9357888d14d7c96faa46997416403d3e5decca4b91029b024ddd","abstract_canon_sha256":"e980d18a4d119fff08472bbe7ae648b87f449d2b01c6c7cde5b8c303e63a2b3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:21.467204Z","signature_b64":"wzaaX3oWIYv6QnCzXdWaUzy561BnLkToCc/qg6BLNHIxSPg2a8aBWKgUP+d69xmXdrACjQ/WWyMK5coboS5kAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df8efa53e1e1cfb1449f26a57a356d3c31c8344f48d54c2326bf544fcd2754d3","last_reissued_at":"2026-05-18T00:06:21.466864Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:21.466864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel Gildea, Linfeng Song, Mo Yu, Radu Florian, Yue Zhang, Zhiguo Wang","submitted_at":"2018-09-06T15:18:14Z","abstract_excerpt":"Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02040","kind":"arxiv","version":1},"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":"1809.02040","created_at":"2026-05-18T00:06:21.466914+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02040v1","created_at":"2026-05-18T00:06:21.466914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02040","created_at":"2026-05-18T00:06:21.466914+00:00"},{"alias_kind":"pith_short_12","alias_value":"36HPUU7B4HH3","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"36HPUU7B4HH3CRE7","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"36HPUU7B","created_at":"2026-05-18T12:32:02.567920+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/36HPUU7B4HH3CRE7E2SXUNLNHQ","json":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ.json","graph_json":"https://pith.science/api/pith-number/36HPUU7B4HH3CRE7E2SXUNLNHQ/graph.json","events_json":"https://pith.science/api/pith-number/36HPUU7B4HH3CRE7E2SXUNLNHQ/events.json","paper":"https://pith.science/paper/36HPUU7B"},"agent_actions":{"view_html":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ","download_json":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ.json","view_paper":"https://pith.science/paper/36HPUU7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02040&json=true","fetch_graph":"https://pith.science/api/pith-number/36HPUU7B4HH3CRE7E2SXUNLNHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/36HPUU7B4HH3CRE7E2SXUNLNHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ/action/storage_attestation","attest_author":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ/action/author_attestation","sign_citation":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ/action/citation_signature","submit_replication":"https://pith.science/pith/36HPUU7B4HH3CRE7E2SXUNLNHQ/action/replication_record"}},"created_at":"2026-05-18T00:06:21.466914+00:00","updated_at":"2026-05-18T00:06:21.466914+00:00"}