{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DSKC4CKAPMB6TAJDVOUTG2ITTV","short_pith_number":"pith:DSKC4CKA","schema_version":"1.0","canonical_sha256":"1c942e09407b03e98123aba93369139d7945751e143d080fcbabb2c670c4b8ab","source":{"kind":"arxiv","id":"1909.11334","version":3},"attestation_state":"computed","paper":{"title":"Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Wei Feng, Xiaohui Xie, Xiaoran Xu, Yunsheng Jiang, Zhi-Hong Deng, Zhiqing Sun","submitted_at":"2019-09-25T08:15:41Z","abstract_excerpt":"We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning. In contrast to existing models, embedding-based or path-based, we learn an input-dependent subgraph to explicitly model reasoning process. Subgraphs are dynamically constructed and expanded by applying graphical attention mechanism conditioned on input queries. In this way, we not only construct graph-structured explanations but also enable message passing designed in Graph Neural Networks (GNNs) to scale with graph sizes. We take the inspiration from the consciousness prior proposed by an"},"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":"1909.11334","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-09-25T08:15:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"43ad5894464d7a62b330f7c1054e62a732f7410dada20927ccb4340774f7e06f","abstract_canon_sha256":"9691eb9da22d95981251e48ba4e040e8623e721914d395c4f49ec5b56dd2811f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:51.436130Z","signature_b64":"7kpogmDIharCHwu5lnG+JpmTqIw0P+alhio8kCjSmcXGCuBm5Vuv9Cb+C4HsesKtqHt3Q43LAhhh7VPaFvQ8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c942e09407b03e98123aba93369139d7945751e143d080fcbabb2c670c4b8ab","last_reissued_at":"2026-07-05T00:53:51.435628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:51.435628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Wei Feng, Xiaohui Xie, Xiaoran Xu, Yunsheng Jiang, Zhi-Hong Deng, Zhiqing Sun","submitted_at":"2019-09-25T08:15:41Z","abstract_excerpt":"We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning. In contrast to existing models, embedding-based or path-based, we learn an input-dependent subgraph to explicitly model reasoning process. Subgraphs are dynamically constructed and expanded by applying graphical attention mechanism conditioned on input queries. In this way, we not only construct graph-structured explanations but also enable message passing designed in Graph Neural Networks (GNNs) to scale with graph sizes. We take the inspiration from the consciousness prior proposed by an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11334","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.11334/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":"1909.11334","created_at":"2026-07-05T00:53:51.435717+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11334v3","created_at":"2026-07-05T00:53:51.435717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11334","created_at":"2026-07-05T00:53:51.435717+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSKC4CKAPMB6","created_at":"2026-07-05T00:53:51.435717+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSKC4CKAPMB6TAJD","created_at":"2026-07-05T00:53:51.435717+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSKC4CKA","created_at":"2026-07-05T00:53:51.435717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14468","citing_title":"BioGraphFusion: Graph Knowledge Embedding for Biological Completion and Reasoning","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV","json":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV.json","graph_json":"https://pith.science/api/pith-number/DSKC4CKAPMB6TAJDVOUTG2ITTV/graph.json","events_json":"https://pith.science/api/pith-number/DSKC4CKAPMB6TAJDVOUTG2ITTV/events.json","paper":"https://pith.science/paper/DSKC4CKA"},"agent_actions":{"view_html":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV","download_json":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV.json","view_paper":"https://pith.science/paper/DSKC4CKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11334&json=true","fetch_graph":"https://pith.science/api/pith-number/DSKC4CKAPMB6TAJDVOUTG2ITTV/graph.json","fetch_events":"https://pith.science/api/pith-number/DSKC4CKAPMB6TAJDVOUTG2ITTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV/action/storage_attestation","attest_author":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV/action/author_attestation","sign_citation":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV/action/citation_signature","submit_replication":"https://pith.science/pith/DSKC4CKAPMB6TAJDVOUTG2ITTV/action/replication_record"}},"created_at":"2026-07-05T00:53:51.435717+00:00","updated_at":"2026-07-05T00:53:51.435717+00:00"}