{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4BQ7JJHDMFDXOBLPMNFEOATW4L","short_pith_number":"pith:4BQ7JJHD","schema_version":"1.0","canonical_sha256":"e061f4a4e3614777056f634a470276e2c29f096cd3d9d5edbe5c29952d730d9d","source":{"kind":"arxiv","id":"2109.10500","version":1},"attestation_state":"computed","paper":{"title":"HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mingyu Derek Ma, Muhao Chen, Nanyun Peng, Te-Lin Wu","submitted_at":"2021-09-22T03:27:04Z","abstract_excerpt":"Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their coverage by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn "},"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":"2109.10500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-22T03:27:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17083aab981667b042a96ba4e43d9bcdfabbe76796dd9fe8cc011fbee3474d4f","abstract_canon_sha256":"7dae90dd0c5f0816cc04f43a291838d2f7820d8d9c46b7ef7adbe1fc4c7acb7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:37.042541Z","signature_b64":"XLwL8cC/eWIYA7VsQUWkttT94MoIhKVt9oU2hjBN/FA3oQdnsifLto3qeFekp76OODU5PeWazHWSssIpnyfEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e061f4a4e3614777056f634a470276e2c29f096cd3d9d5edbe5c29952d730d9d","last_reissued_at":"2026-07-05T03:16:37.041963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:37.041963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mingyu Derek Ma, Muhao Chen, Nanyun Peng, Te-Lin Wu","submitted_at":"2021-09-22T03:27:04Z","abstract_excerpt":"Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their coverage by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10500","kind":"arxiv","version":1},"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/2109.10500/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":"2109.10500","created_at":"2026-07-05T03:16:37.042061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.10500v1","created_at":"2026-07-05T03:16:37.042061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10500","created_at":"2026-07-05T03:16:37.042061+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BQ7JJHDMFDX","created_at":"2026-07-05T03:16:37.042061+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BQ7JJHDMFDXOBLP","created_at":"2026-07-05T03:16:37.042061+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BQ7JJHD","created_at":"2026-07-05T03:16:37.042061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00265","citing_title":"Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L","json":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L.json","graph_json":"https://pith.science/api/pith-number/4BQ7JJHDMFDXOBLPMNFEOATW4L/graph.json","events_json":"https://pith.science/api/pith-number/4BQ7JJHDMFDXOBLPMNFEOATW4L/events.json","paper":"https://pith.science/paper/4BQ7JJHD"},"agent_actions":{"view_html":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L","download_json":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L.json","view_paper":"https://pith.science/paper/4BQ7JJHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.10500&json=true","fetch_graph":"https://pith.science/api/pith-number/4BQ7JJHDMFDXOBLPMNFEOATW4L/graph.json","fetch_events":"https://pith.science/api/pith-number/4BQ7JJHDMFDXOBLPMNFEOATW4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L/action/storage_attestation","attest_author":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L/action/author_attestation","sign_citation":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L/action/citation_signature","submit_replication":"https://pith.science/pith/4BQ7JJHDMFDXOBLPMNFEOATW4L/action/replication_record"}},"created_at":"2026-07-05T03:16:37.042061+00:00","updated_at":"2026-07-05T03:16:37.042061+00:00"}