{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FB2OO7LGKZRUHYM5DY4NKGZ3LO","short_pith_number":"pith:FB2OO7LG","schema_version":"1.0","canonical_sha256":"2874e77d66566343e19d1e38d51b3b5bb49444f326376b553b7bf2e534066d58","source":{"kind":"arxiv","id":"1810.06546","version":2},"attestation_state":"computed","paper":{"title":"Poincar\\'e GloVe: Hyperbolic Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandru Tifrea, Gary B\\'ecigneul, Octavian-Eugen Ganea","submitted_at":"2018-10-15T17:54:36Z","abstract_excerpt":"Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical structure that the next generation of unsupervised learned word embeddings should reveal. In this paper, justified by the notion of delta-hyperbolicity or tree-likeliness of a space, we propose to embed words in a Cartesian product of hyperbolic spaces which we theoretically connect to the Gaussian word embeddings and their Fisher geometry. This connection allows us to introduce a novel principled hypernymy score for word embeddings. Moreover, we adapt the well-known Glove algorithm to learn unsupe"},"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":"1810.06546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-15T17:54:36Z","cross_cats_sorted":[],"title_canon_sha256":"800416ffb482fcca9f47d6eac552876d96e6cb8e6131fb72f02fbb6cb638605e","abstract_canon_sha256":"51a89bf3a1397c9ca3f7078c9f585361321ee1ed1477741ef351c9231802afad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:07.915950Z","signature_b64":"WHuMWfwV4uF0+yEg57ipTf5QSUiWgX23HBv3Wcc8MjQm8hwsFgE9z6v5lfmXzccdQ4aPzp33SPz89sM07AHqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2874e77d66566343e19d1e38d51b3b5bb49444f326376b553b7bf2e534066d58","last_reissued_at":"2026-05-18T00:00:07.915405Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:07.915405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Poincar\\'e GloVe: Hyperbolic Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandru Tifrea, Gary B\\'ecigneul, Octavian-Eugen Ganea","submitted_at":"2018-10-15T17:54:36Z","abstract_excerpt":"Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical structure that the next generation of unsupervised learned word embeddings should reveal. In this paper, justified by the notion of delta-hyperbolicity or tree-likeliness of a space, we propose to embed words in a Cartesian product of hyperbolic spaces which we theoretically connect to the Gaussian word embeddings and their Fisher geometry. This connection allows us to introduce a novel principled hypernymy score for word embeddings. Moreover, we adapt the well-known Glove algorithm to learn unsupe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06546","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":""},"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":"1810.06546","created_at":"2026-05-18T00:00:07.915494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.06546v2","created_at":"2026-05-18T00:00:07.915494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06546","created_at":"2026-05-18T00:00:07.915494+00:00"},{"alias_kind":"pith_short_12","alias_value":"FB2OO7LGKZRU","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FB2OO7LGKZRUHYM5","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FB2OO7LG","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.00656","citing_title":"DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06752","citing_title":"Busemann energy-based attention for emotion analysis in Poincar\\'e discs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17174","citing_title":"Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO","json":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO.json","graph_json":"https://pith.science/api/pith-number/FB2OO7LGKZRUHYM5DY4NKGZ3LO/graph.json","events_json":"https://pith.science/api/pith-number/FB2OO7LGKZRUHYM5DY4NKGZ3LO/events.json","paper":"https://pith.science/paper/FB2OO7LG"},"agent_actions":{"view_html":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO","download_json":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO.json","view_paper":"https://pith.science/paper/FB2OO7LG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.06546&json=true","fetch_graph":"https://pith.science/api/pith-number/FB2OO7LGKZRUHYM5DY4NKGZ3LO/graph.json","fetch_events":"https://pith.science/api/pith-number/FB2OO7LGKZRUHYM5DY4NKGZ3LO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO/action/storage_attestation","attest_author":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO/action/author_attestation","sign_citation":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO/action/citation_signature","submit_replication":"https://pith.science/pith/FB2OO7LGKZRUHYM5DY4NKGZ3LO/action/replication_record"}},"created_at":"2026-05-18T00:00:07.915494+00:00","updated_at":"2026-05-18T00:00:07.915494+00:00"}