{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:D3R5PKPF2SKL6MXD4J4QKVSDVR","short_pith_number":"pith:D3R5PKPF","schema_version":"1.0","canonical_sha256":"1ee3d7a9e5d494bf32e3e279055643ac4cb6abe4d7ac408970e2b1c6ddb5120b","source":{"kind":"arxiv","id":"2005.10043","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Graph to Improve Abstractive Multi-Document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hua Wu, Jiachen Liu, Junping Du, Wei Li, Xinyan Xiao","submitted_at":"2020-05-20T13:39:47Z","abstract_excerpt":"Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents such as similarity graph and discourse graph, to more effectively process multiple input documents and produce abstractive summaries. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. "},"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":"2005.10043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T13:39:47Z","cross_cats_sorted":[],"title_canon_sha256":"37e969b821310bd4661821d5d5dddb0c7d611927d869aca656eec2f4d8c248d0","abstract_canon_sha256":"e834908e3ef8e6d56c1e6bdcd3de52753daede5e677d70e919b6c855b8678b25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:04:36.467122Z","signature_b64":"Cyj6XsVUIXDh+Bebn8bkFfod1voq2kHWXijMOAu8SHBT7nzjdnlSgFq68tOx0qEkRJUfDjUtZ9gFZ/KqIMOsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ee3d7a9e5d494bf32e3e279055643ac4cb6abe4d7ac408970e2b1c6ddb5120b","last_reissued_at":"2026-07-05T01:04:36.466591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:04:36.466591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Graph to Improve Abstractive Multi-Document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hua Wu, Jiachen Liu, Junping Du, Wei Li, Xinyan Xiao","submitted_at":"2020-05-20T13:39:47Z","abstract_excerpt":"Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents such as similarity graph and discourse graph, to more effectively process multiple input documents and produce abstractive summaries. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10043","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.10043/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":"2005.10043","created_at":"2026-07-05T01:04:36.466651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.10043v1","created_at":"2026-07-05T01:04:36.466651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10043","created_at":"2026-07-05T01:04:36.466651+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3R5PKPF2SKL","created_at":"2026-07-05T01:04:36.466651+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3R5PKPF2SKL6MXD","created_at":"2026-07-05T01:04:36.466651+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3R5PKPF","created_at":"2026-07-05T01:04:36.466651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19591","citing_title":"A BART-based approach with hierarchical strategy for Vietnamese abstractive multi-document summarization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":237,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR","json":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR.json","graph_json":"https://pith.science/api/pith-number/D3R5PKPF2SKL6MXD4J4QKVSDVR/graph.json","events_json":"https://pith.science/api/pith-number/D3R5PKPF2SKL6MXD4J4QKVSDVR/events.json","paper":"https://pith.science/paper/D3R5PKPF"},"agent_actions":{"view_html":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR","download_json":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR.json","view_paper":"https://pith.science/paper/D3R5PKPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.10043&json=true","fetch_graph":"https://pith.science/api/pith-number/D3R5PKPF2SKL6MXD4J4QKVSDVR/graph.json","fetch_events":"https://pith.science/api/pith-number/D3R5PKPF2SKL6MXD4J4QKVSDVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR/action/storage_attestation","attest_author":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR/action/author_attestation","sign_citation":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR/action/citation_signature","submit_replication":"https://pith.science/pith/D3R5PKPF2SKL6MXD4J4QKVSDVR/action/replication_record"}},"created_at":"2026-07-05T01:04:36.466651+00:00","updated_at":"2026-07-05T01:04:36.466651+00:00"}