{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BY4HQP7OUTBJSKWNIRL37X6IRF","short_pith_number":"pith:BY4HQP7O","schema_version":"1.0","canonical_sha256":"0e38783feea4c2992acd4457bfdfc88945a2769d436189fe61db2c00a33757b6","source":{"kind":"arxiv","id":"2110.14890","version":2},"attestation_state":"computed","paper":{"title":"SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.DC"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Dale Schuurmans, Denny Zhou, Hanjun Dai, Hongyu Ren, Jure Leskovec, Xinyun Chen","submitted_at":"2021-10-28T05:02:33Z","abstract_excerpt":"Knowledge graphs (KGs) capture knowledge in the form of head--relation--tail triples and are a crucial component in many AI systems. There are two important reasoning tasks on KGs: (1) single-hop knowledge graph completion, which involves predicting individual links in the KG; and (2), multi-hop reasoning, where the goal is to predict which KG entities satisfy a given logical query. Embedding-based methods solve both tasks by first computing an embedding for each entity and relation, then using them to form predictions. However, existing scalable KG embedding frameworks only support single-hop"},"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":"2110.14890","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-28T05:02:33Z","cross_cats_sorted":["cs.AI","cs.DB","cs.DC"],"title_canon_sha256":"6ff565df44ada3c1c3810f00ef3b467d751d66e12113a5028d6a8e2a9907d0b0","abstract_canon_sha256":"132471909026d8bacaecbff362b257bf2c861d66ad1c34217d7d3285d0d161ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:59.311024Z","signature_b64":"lW8WfdN4ZKtcDZqU3RzaUX6Bt9Bkg9Px8F5Wq5ye3PkGPUdKAaUdsJyapQU7PUIywVxxRZADusRKwyFA39zzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e38783feea4c2992acd4457bfdfc88945a2769d436189fe61db2c00a33757b6","last_reissued_at":"2026-07-05T03:27:59.310615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:59.310615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.DC"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Dale Schuurmans, Denny Zhou, Hanjun Dai, Hongyu Ren, Jure Leskovec, Xinyun Chen","submitted_at":"2021-10-28T05:02:33Z","abstract_excerpt":"Knowledge graphs (KGs) capture knowledge in the form of head--relation--tail triples and are a crucial component in many AI systems. There are two important reasoning tasks on KGs: (1) single-hop knowledge graph completion, which involves predicting individual links in the KG; and (2), multi-hop reasoning, where the goal is to predict which KG entities satisfy a given logical query. Embedding-based methods solve both tasks by first computing an embedding for each entity and relation, then using them to form predictions. However, existing scalable KG embedding frameworks only support single-hop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14890","kind":"arxiv","version":2},"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/2110.14890/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":"2110.14890","created_at":"2026-07-05T03:27:59.310674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14890v2","created_at":"2026-07-05T03:27:59.310674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14890","created_at":"2026-07-05T03:27:59.310674+00:00"},{"alias_kind":"pith_short_12","alias_value":"BY4HQP7OUTBJ","created_at":"2026-07-05T03:27:59.310674+00:00"},{"alias_kind":"pith_short_16","alias_value":"BY4HQP7OUTBJSKWN","created_at":"2026-07-05T03:27:59.310674+00:00"},{"alias_kind":"pith_short_8","alias_value":"BY4HQP7O","created_at":"2026-07-05T03:27:59.310674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14224","citing_title":"Top Ten Challenges Towards Agentic Neural Graph Databases","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF","json":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF.json","graph_json":"https://pith.science/api/pith-number/BY4HQP7OUTBJSKWNIRL37X6IRF/graph.json","events_json":"https://pith.science/api/pith-number/BY4HQP7OUTBJSKWNIRL37X6IRF/events.json","paper":"https://pith.science/paper/BY4HQP7O"},"agent_actions":{"view_html":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF","download_json":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF.json","view_paper":"https://pith.science/paper/BY4HQP7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14890&json=true","fetch_graph":"https://pith.science/api/pith-number/BY4HQP7OUTBJSKWNIRL37X6IRF/graph.json","fetch_events":"https://pith.science/api/pith-number/BY4HQP7OUTBJSKWNIRL37X6IRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF/action/storage_attestation","attest_author":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF/action/author_attestation","sign_citation":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF/action/citation_signature","submit_replication":"https://pith.science/pith/BY4HQP7OUTBJSKWNIRL37X6IRF/action/replication_record"}},"created_at":"2026-07-05T03:27:59.310674+00:00","updated_at":"2026-07-05T03:27:59.310674+00:00"}