{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HZKSSXG3O2QEERZLTPPPIZ5WGV","short_pith_number":"pith:HZKSSXG3","schema_version":"1.0","canonical_sha256":"3e55295cdb76a042472b9bdef467b6355805b0bd9023c3e327f9608adca142bf","source":{"kind":"arxiv","id":"1811.01824","version":4},"attestation_state":"computed","paper":{"title":"Structured Neural Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc Brockschmidt, Miltiadis Allamanis, Patrick Fernandes","submitted_at":"2018-11-05T16:12:04Z","abstract_excerpt":"Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph component that can reason about long-distance relationships in weakly structured data such as text. In an extensive evaluation, we show that the resulting hybrid sequence-graph models outperform both pure sequence models as well as pure graph models on a range of summarization tasks."},"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":"1811.01824","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T16:12:04Z","cross_cats_sorted":["cs.CL","cs.SE","stat.ML"],"title_canon_sha256":"0c9d26ddf501ebe0638f2f45e1ce4a2c67698b808273a1a9d7cc5492c7ec1e4c","abstract_canon_sha256":"c425e0193af8b4f7e0ce36e74751c64d5ce3437b758f92edfaad0eaeb2b2843a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:27.759128Z","signature_b64":"TYyNEwkTsmIg1/KRLgjTXlpXBaBO2iHTltJDAuyPHmOXRqTT/VK1jqEmFwVgudpj3/sGIVs5k9x87Fm83cs6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e55295cdb76a042472b9bdef467b6355805b0bd9023c3e327f9608adca142bf","last_reissued_at":"2026-07-05T02:12:27.758332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:27.758332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Neural Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc Brockschmidt, Miltiadis Allamanis, Patrick Fernandes","submitted_at":"2018-11-05T16:12:04Z","abstract_excerpt":"Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph component that can reason about long-distance relationships in weakly structured data such as text. In an extensive evaluation, we show that the resulting hybrid sequence-graph models outperform both pure sequence models as well as pure graph models on a range of summarization tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01824","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/1811.01824/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":"1811.01824","created_at":"2026-07-05T02:12:27.758710+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01824v4","created_at":"2026-07-05T02:12:27.758710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01824","created_at":"2026-07-05T02:12:27.758710+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZKSSXG3O2QE","created_at":"2026-07-05T02:12:27.758710+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZKSSXG3O2QEERZL","created_at":"2026-07-05T02:12:27.758710+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZKSSXG3","created_at":"2026-07-05T02:12:27.758710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2102.04664","citing_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"1909.09436","citing_title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV","json":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV.json","graph_json":"https://pith.science/api/pith-number/HZKSSXG3O2QEERZLTPPPIZ5WGV/graph.json","events_json":"https://pith.science/api/pith-number/HZKSSXG3O2QEERZLTPPPIZ5WGV/events.json","paper":"https://pith.science/paper/HZKSSXG3"},"agent_actions":{"view_html":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV","download_json":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV.json","view_paper":"https://pith.science/paper/HZKSSXG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01824&json=true","fetch_graph":"https://pith.science/api/pith-number/HZKSSXG3O2QEERZLTPPPIZ5WGV/graph.json","fetch_events":"https://pith.science/api/pith-number/HZKSSXG3O2QEERZLTPPPIZ5WGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV/action/storage_attestation","attest_author":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV/action/author_attestation","sign_citation":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV/action/citation_signature","submit_replication":"https://pith.science/pith/HZKSSXG3O2QEERZLTPPPIZ5WGV/action/replication_record"}},"created_at":"2026-07-05T02:12:27.758710+00:00","updated_at":"2026-07-05T02:12:27.758710+00:00"}