{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BD2OT4MNJZVEEPVUT2YR5466SM","short_pith_number":"pith:BD2OT4MN","schema_version":"1.0","canonical_sha256":"08f4e9f18d4e6a423eb49eb11ef3de93287cef97490857006180a9333c01a937","source":{"kind":"arxiv","id":"1706.06681","version":3},"attestation_state":"computed","paper":{"title":"Graph-based Neural Multi-Document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ayush Pareek, Dragomir Radev, Krishnan Srinivasan, Kshitijh Meelu, Michihiro Yasunaga, Rui Zhang","submitted_at":"2017-06-20T22:12:14Z","abstract_excerpt":"We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use a greedy heuristic to extract salient sentences while avoiding redundancy. In our experiments on DUC 2004, we consider three types of sentence relation graphs and demonstrate the advantage of combining s"},"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":"1706.06681","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-20T22:12:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"96489796f71fe41e3770df307f99a6f6e27b480281a7cca2bf567904eca03331","abstract_canon_sha256":"65ff3cf4da16cde666bb8db8b8f2100736deaa4a1490fa7e49a37c958250bcd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:49.275367Z","signature_b64":"yyqTQ7IjZV2nPZ7pLCyZxlnFq8sY2d68wFpzhMnYn4x54RubpzkVIutDirCTDH921kFIC0iTfmwkWOGJYiu9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08f4e9f18d4e6a423eb49eb11ef3de93287cef97490857006180a9333c01a937","last_reissued_at":"2026-05-18T00:36:49.274908Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:49.274908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-based Neural Multi-Document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ayush Pareek, Dragomir Radev, Krishnan Srinivasan, Kshitijh Meelu, Michihiro Yasunaga, Rui Zhang","submitted_at":"2017-06-20T22:12:14Z","abstract_excerpt":"We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use a greedy heuristic to extract salient sentences while avoiding redundancy. In our experiments on DUC 2004, we consider three types of sentence relation graphs and demonstrate the advantage of combining s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06681","kind":"arxiv","version":3},"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":"1706.06681","created_at":"2026-05-18T00:36:49.274977+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.06681v3","created_at":"2026-05-18T00:36:49.274977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06681","created_at":"2026-05-18T00:36:49.274977+00:00"},{"alias_kind":"pith_short_12","alias_value":"BD2OT4MNJZVE","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BD2OT4MNJZVEEPVU","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BD2OT4MN","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06330","citing_title":"Ranking sentences from product description & bullets for better search","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM","json":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM.json","graph_json":"https://pith.science/api/pith-number/BD2OT4MNJZVEEPVUT2YR5466SM/graph.json","events_json":"https://pith.science/api/pith-number/BD2OT4MNJZVEEPVUT2YR5466SM/events.json","paper":"https://pith.science/paper/BD2OT4MN"},"agent_actions":{"view_html":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM","download_json":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM.json","view_paper":"https://pith.science/paper/BD2OT4MN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.06681&json=true","fetch_graph":"https://pith.science/api/pith-number/BD2OT4MNJZVEEPVUT2YR5466SM/graph.json","fetch_events":"https://pith.science/api/pith-number/BD2OT4MNJZVEEPVUT2YR5466SM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM/action/storage_attestation","attest_author":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM/action/author_attestation","sign_citation":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM/action/citation_signature","submit_replication":"https://pith.science/pith/BD2OT4MNJZVEEPVUT2YR5466SM/action/replication_record"}},"created_at":"2026-05-18T00:36:49.274977+00:00","updated_at":"2026-05-18T00:36:49.274977+00:00"}