{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DE4H7N7DPDW2XF5LRYJMS2NOH5","short_pith_number":"pith:DE4H7N7D","schema_version":"1.0","canonical_sha256":"19387fb7e378edab97ab8e12c969ae3f682ad6eb16677058787d5b7d638450ce","source":{"kind":"arxiv","id":"1808.09920","version":4},"attestation_state":"computed","paper":{"title":"Question Answering by Reasoning Across Documents with Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Ivan Titov, Nicola De Cao, Wilker Aziz","submitted_at":"2018-08-29T16:44:51Z","abstract_excerpt":"Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentions of entities are nodes of this graph while edges encode relations between different mentions (e.g., within- and cross-document co-reference). Graph convolutional networks (GCNs) are applied to these graphs and trained to perform multi-step reasoning. Our Entity-GCN method is sc"},"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":"1808.09920","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-29T16:44:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2caaa87a273c1f02c9f04608c6b4f268d0a5cfa1513599b8f5412d0753e49b0","abstract_canon_sha256":"b7cf3811199569b917ea03e4d318329b28a0712cace7a950fe519239c80d92d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:14.423173Z","signature_b64":"JuFrlLdb4ruBV5V1k+UK7w4gnVt1Jn/VIiR5q1sd/+JUqIJ6WoLwPN7XiQBKH0rpv8AF5LNneTr+Dr8DO9dPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19387fb7e378edab97ab8e12c969ae3f682ad6eb16677058787d5b7d638450ce","last_reissued_at":"2026-07-05T05:01:14.422694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:14.422694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Question Answering by Reasoning Across Documents with Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Ivan Titov, Nicola De Cao, Wilker Aziz","submitted_at":"2018-08-29T16:44:51Z","abstract_excerpt":"Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentions of entities are nodes of this graph while edges encode relations between different mentions (e.g., within- and cross-document co-reference). Graph convolutional networks (GCNs) are applied to these graphs and trained to perform multi-step reasoning. Our Entity-GCN method is sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09920","kind":"arxiv","version":4},"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/1808.09920/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":"1808.09920","created_at":"2026-07-05T05:01:14.422752+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09920v4","created_at":"2026-07-05T05:01:14.422752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09920","created_at":"2026-07-05T05:01:14.422752+00:00"},{"alias_kind":"pith_short_12","alias_value":"DE4H7N7DPDW2","created_at":"2026-07-05T05:01:14.422752+00:00"},{"alias_kind":"pith_short_16","alias_value":"DE4H7N7DPDW2XF5L","created_at":"2026-07-05T05:01:14.422752+00:00"},{"alias_kind":"pith_short_8","alias_value":"DE4H7N7D","created_at":"2026-07-05T05:01:14.422752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.15717","citing_title":"The False Promise of Imitating Proprietary LLMs","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5","json":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5.json","graph_json":"https://pith.science/api/pith-number/DE4H7N7DPDW2XF5LRYJMS2NOH5/graph.json","events_json":"https://pith.science/api/pith-number/DE4H7N7DPDW2XF5LRYJMS2NOH5/events.json","paper":"https://pith.science/paper/DE4H7N7D"},"agent_actions":{"view_html":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5","download_json":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5.json","view_paper":"https://pith.science/paper/DE4H7N7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09920&json=true","fetch_graph":"https://pith.science/api/pith-number/DE4H7N7DPDW2XF5LRYJMS2NOH5/graph.json","fetch_events":"https://pith.science/api/pith-number/DE4H7N7DPDW2XF5LRYJMS2NOH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5/action/storage_attestation","attest_author":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5/action/author_attestation","sign_citation":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5/action/citation_signature","submit_replication":"https://pith.science/pith/DE4H7N7DPDW2XF5LRYJMS2NOH5/action/replication_record"}},"created_at":"2026-07-05T05:01:14.422752+00:00","updated_at":"2026-07-05T05:01:14.422752+00:00"}