{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VBDVW7P7MB33K5LO5EZ6ZY2QUZ","short_pith_number":"pith:VBDVW7P7","schema_version":"1.0","canonical_sha256":"a8475b7dff6077b5756ee933ece350a64ce298e8d6565696bdb61cd5e6568179","source":{"kind":"arxiv","id":"1811.01713","version":1},"attestation_state":"computed","paper":{"title":"Word Mover's Embedding: From Word2Vec to Document Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Avinash Balakrishnan, Fangli Xu, Ian E.H. Yen, Kun Xu, Lingfei Wu, Michael J. Witbrock, Pin-Yu Chen, Pradeep Ravikumar","submitted_at":"2018-10-30T19:43:17Z","abstract_excerpt":"While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a distance measure between documents called \\emph{Word Mover's Distance} (WMD) that aligns semantically similar words, yields unprecedented KNN classification accuracy. However, WMD is expensive to compute, and it is hard to extend its use beyond a KNN classifier. In this paper, we propose the \\emph{Word Mover's Embedding } (WME), a novel approach t"},"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":"1811.01713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T19:43:17Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"ea4f974ac47ddd3c739dbd6490fec6cbfd9da6ca245ac068c6cec226cbcbd274","abstract_canon_sha256":"b376a912a442ac3a8c7805d57ee625d022378b6cd54104fe1159a170c441b35e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:33.494310Z","signature_b64":"7b893R2/aK+Q3vcwnVY8FxPMQED1z38ClUfiQDfBte4/2GwghyQ2xzqbcf+y9W5rdpvdubzjm5IQPAdGZz2VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8475b7dff6077b5756ee933ece350a64ce298e8d6565696bdb61cd5e6568179","last_reissued_at":"2026-05-18T00:01:33.493793Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:33.493793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Word Mover's Embedding: From Word2Vec to Document Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Avinash Balakrishnan, Fangli Xu, Ian E.H. Yen, Kun Xu, Lingfei Wu, Michael J. Witbrock, Pin-Yu Chen, Pradeep Ravikumar","submitted_at":"2018-10-30T19:43:17Z","abstract_excerpt":"While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a distance measure between documents called \\emph{Word Mover's Distance} (WMD) that aligns semantically similar words, yields unprecedented KNN classification accuracy. However, WMD is expensive to compute, and it is hard to extend its use beyond a KNN classifier. In this paper, we propose the \\emph{Word Mover's Embedding } (WME), a novel approach t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01713","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":""},"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":"1811.01713","created_at":"2026-05-18T00:01:33.493870+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01713v1","created_at":"2026-05-18T00:01:33.493870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01713","created_at":"2026-05-18T00:01:33.493870+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBDVW7P7MB33","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBDVW7P7MB33K5LO","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBDVW7P7","created_at":"2026-05-18T12:32:59.047623+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/VBDVW7P7MB33K5LO5EZ6ZY2QUZ","json":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ.json","graph_json":"https://pith.science/api/pith-number/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/graph.json","events_json":"https://pith.science/api/pith-number/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/events.json","paper":"https://pith.science/paper/VBDVW7P7"},"agent_actions":{"view_html":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ","download_json":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ.json","view_paper":"https://pith.science/paper/VBDVW7P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01713&json=true","fetch_graph":"https://pith.science/api/pith-number/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/action/storage_attestation","attest_author":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/action/author_attestation","sign_citation":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/action/citation_signature","submit_replication":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/action/replication_record"}},"created_at":"2026-05-18T00:01:33.493870+00:00","updated_at":"2026-05-18T00:01:33.493870+00:00"}