{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BPR3DZQT74D6UK24CXQ4N7YMKY","short_pith_number":"pith:BPR3DZQT","schema_version":"1.0","canonical_sha256":"0be3b1e613ff07ea2b5c15e1c6ff0c5615bc3bf24f6c70f18e786cf2d5d22f04","source":{"kind":"arxiv","id":"1509.01692","version":4},"attestation_state":"computed","paper":{"title":"Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Vylomova, Laura Rimell, Timothy Baldwin, Trevor Cohn","submitted_at":"2015-09-05T11:23:44Z","abstract_excerpt":"Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) super"},"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":"1509.01692","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-05T11:23:44Z","cross_cats_sorted":[],"title_canon_sha256":"2961a9e91c5b84ddc520c7198a5720de4c8c66285521ad8d46fd84572a01ca25","abstract_canon_sha256":"d26d4e5b972ff6c127d6e6b6aaeef28c85fc3a971467c0a19bafa06131458c63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:06.944394Z","signature_b64":"ZoWdVgF96o5q4ZJwLKhomFNUXJcUBwk5VoBbBafXySZpaSLkcR2xXJWcdJpqc+Qx/XlxInhLNEkL3nSb9WqVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0be3b1e613ff07ea2b5c15e1c6ff0c5615bc3bf24f6c70f18e786cf2d5d22f04","last_reissued_at":"2026-05-18T01:09:06.943820Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:06.943820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Vylomova, Laura Rimell, Timothy Baldwin, Trevor Cohn","submitted_at":"2015-09-05T11:23:44Z","abstract_excerpt":"Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) super"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.01692","kind":"arxiv","version":4},"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":"1509.01692","created_at":"2026-05-18T01:09:06.943909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.01692v4","created_at":"2026-05-18T01:09:06.943909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.01692","created_at":"2026-05-18T01:09:06.943909+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPR3DZQT74D6","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPR3DZQT74D6UK24","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPR3DZQT","created_at":"2026-05-18T12:29:14.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05344","citing_title":"Open-SAT: LLM-Guided Query Embedding Refinement for Open-Vocabulary Object Retrieval in Satellite Imagery","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY","json":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY.json","graph_json":"https://pith.science/api/pith-number/BPR3DZQT74D6UK24CXQ4N7YMKY/graph.json","events_json":"https://pith.science/api/pith-number/BPR3DZQT74D6UK24CXQ4N7YMKY/events.json","paper":"https://pith.science/paper/BPR3DZQT"},"agent_actions":{"view_html":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY","download_json":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY.json","view_paper":"https://pith.science/paper/BPR3DZQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.01692&json=true","fetch_graph":"https://pith.science/api/pith-number/BPR3DZQT74D6UK24CXQ4N7YMKY/graph.json","fetch_events":"https://pith.science/api/pith-number/BPR3DZQT74D6UK24CXQ4N7YMKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY/action/storage_attestation","attest_author":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY/action/author_attestation","sign_citation":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY/action/citation_signature","submit_replication":"https://pith.science/pith/BPR3DZQT74D6UK24CXQ4N7YMKY/action/replication_record"}},"created_at":"2026-05-18T01:09:06.943909+00:00","updated_at":"2026-05-18T01:09:06.943909+00:00"}