{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WT2T4F3BDUQEWLF2FDAETBWSHT","short_pith_number":"pith:WT2T4F3B","schema_version":"1.0","canonical_sha256":"b4f53e17611d204b2cba28c04986d23cf85c131f43f1a6ccd3b71ed946755eed","source":{"kind":"arxiv","id":"1804.01882","version":3},"attestation_state":"computed","paper":{"title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Octavian-Eugen Ganea, Thomas Hofmann","submitted_at":"2018-04-03T19:25:10Z","abstract_excerpt":"Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a novel method to embed directed acyclic graphs. Following prior work, we first advocate for using hyperbolic spaces which provably model tree-like structures better than Euclidean geometry. Second, we view hierarchical relations as partial orders defined using a family of nested geodesically convex cones. We prove that these entailment cones admit an optimal shape with a closed form expression both in the Euclidean and h"},"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":"1804.01882","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T19:25:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5fa59a0ea5111f74f048d1025b1a75433d5f67338e4721d7a5cd1f58c958c0f6","abstract_canon_sha256":"bed9d20837b15268ad23e7c997bb11fec8a64d95ad98590c215362f86f6c6179"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:00.031095Z","signature_b64":"ypqqRAlPjW/XqVl85psLliFGjqgik3TcO9agK5vV2zM4PidacvS65tZPsUk3nAk8bHSMXOHd/ftdaMLN/jVtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4f53e17611d204b2cba28c04986d23cf85c131f43f1a6ccd3b71ed946755eed","last_reissued_at":"2026-05-18T00:14:00.030310Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:00.030310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Octavian-Eugen Ganea, Thomas Hofmann","submitted_at":"2018-04-03T19:25:10Z","abstract_excerpt":"Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a novel method to embed directed acyclic graphs. Following prior work, we first advocate for using hyperbolic spaces which provably model tree-like structures better than Euclidean geometry. Second, we view hierarchical relations as partial orders defined using a family of nested geodesically convex cones. We prove that these entailment cones admit an optimal shape with a closed form expression both in the Euclidean and h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01882","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":"1804.01882","created_at":"2026-05-18T00:14:00.030441+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.01882v3","created_at":"2026-05-18T00:14:00.030441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01882","created_at":"2026-05-18T00:14:00.030441+00:00"},{"alias_kind":"pith_short_12","alias_value":"WT2T4F3BDUQE","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WT2T4F3BDUQEWLF2","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WT2T4F3B","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT","json":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT.json","graph_json":"https://pith.science/api/pith-number/WT2T4F3BDUQEWLF2FDAETBWSHT/graph.json","events_json":"https://pith.science/api/pith-number/WT2T4F3BDUQEWLF2FDAETBWSHT/events.json","paper":"https://pith.science/paper/WT2T4F3B"},"agent_actions":{"view_html":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT","download_json":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT.json","view_paper":"https://pith.science/paper/WT2T4F3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.01882&json=true","fetch_graph":"https://pith.science/api/pith-number/WT2T4F3BDUQEWLF2FDAETBWSHT/graph.json","fetch_events":"https://pith.science/api/pith-number/WT2T4F3BDUQEWLF2FDAETBWSHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT/action/storage_attestation","attest_author":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT/action/author_attestation","sign_citation":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT/action/citation_signature","submit_replication":"https://pith.science/pith/WT2T4F3BDUQEWLF2FDAETBWSHT/action/replication_record"}},"created_at":"2026-05-18T00:14:00.030441+00:00","updated_at":"2026-05-18T00:14:00.030441+00:00"}