{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VBDVW7P7MB33K5LO5EZ6ZY2QUZ","short_pith_number":"pith:VBDVW7P7","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"},"canonical_sha256":"a8475b7dff6077b5756ee933ece350a64ce298e8d6565696bdb61cd5e6568179","source":{"kind":"arxiv","id":"1811.01713","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01713","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01713v1","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01713","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"VBDVW7P7MB33","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VBDVW7P7MB33K5LO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VBDVW7P7","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VBDVW7P7MB33K5LO5EZ6ZY2QUZ","target":"record","payload":{"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"},"canonical_sha256":"a8475b7dff6077b5756ee933ece350a64ce298e8d6565696bdb61cd5e6568179","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"},"source_kind":"arxiv","source_id":"1811.01713","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bufllrb1KkO6dvNO/QYwKfYAQyQ2dHKVmnZFvGnDyeABaQ4RCWD/5ytuM/6W+6ZeBfX51tsJnKfu7W7sHhzzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:35:08.656652Z"},"content_sha256":"f848f33caf9d0edd4a0b9b748280a61e30cadd05f0feee2d32bd0704c89a1464","schema_version":"1.0","event_id":"sha256:f848f33caf9d0edd4a0b9b748280a61e30cadd05f0feee2d32bd0704c89a1464"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VBDVW7P7MB33K5LO5EZ6ZY2QUZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P27Fck2Gz/VtZr55jJwXuLghnky4Snk2MhYHXHrkELoGxJxbl+euFZpCMldGYQR8UyLIyJl7j1koF9TT4GjWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T00:35:08.657012Z"},"content_sha256":"79d75b81bba8fe8d7cdff3db2fe71043def15a392bef73815963838ee854f2fd","schema_version":"1.0","event_id":"sha256:79d75b81bba8fe8d7cdff3db2fe71043def15a392bef73815963838ee854f2fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/bundle.json","state_url":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T00:35:08Z","links":{"resolver":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ","bundle":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/bundle.json","state":"https://pith.science/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBDVW7P7MB33K5LO5EZ6ZY2QUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VBDVW7P7MB33K5LO5EZ6ZY2QUZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b376a912a442ac3a8c7805d57ee625d022378b6cd54104fe1159a170c441b35e","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T19:43:17Z","title_canon_sha256":"ea4f974ac47ddd3c739dbd6490fec6cbfd9da6ca245ac068c6cec226cbcbd274"},"schema_version":"1.0","source":{"id":"1811.01713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01713","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01713v1","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01713","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"VBDVW7P7MB33","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VBDVW7P7MB33K5LO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VBDVW7P7","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:79d75b81bba8fe8d7cdff3db2fe71043def15a392bef73815963838ee854f2fd","target":"graph","created_at":"2026-05-18T00:01:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Avinash Balakrishnan, Fangli Xu, Ian E.H. Yen, Kun Xu, Lingfei Wu, Michael J. Witbrock, Pin-Yu Chen, Pradeep Ravikumar","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T19:43:17Z","title":"Word Mover's Embedding: From Word2Vec to Document Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01713","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f848f33caf9d0edd4a0b9b748280a61e30cadd05f0feee2d32bd0704c89a1464","target":"record","created_at":"2026-05-18T00:01:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b376a912a442ac3a8c7805d57ee625d022378b6cd54104fe1159a170c441b35e","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T19:43:17Z","title_canon_sha256":"ea4f974ac47ddd3c739dbd6490fec6cbfd9da6ca245ac068c6cec226cbcbd274"},"schema_version":"1.0","source":{"id":"1811.01713","kind":"arxiv","version":1}},"canonical_sha256":"a8475b7dff6077b5756ee933ece350a64ce298e8d6565696bdb61cd5e6568179","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8475b7dff6077b5756ee933ece350a64ce298e8d6565696bdb61cd5e6568179","first_computed_at":"2026-05-18T00:01:33.493793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:33.493793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7b893R2/aK+Q3vcwnVY8FxPMQED1z38ClUfiQDfBte4/2GwghyQ2xzqbcf+y9W5rdpvdubzjm5IQPAdGZz2VAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:33.494310Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.01713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f848f33caf9d0edd4a0b9b748280a61e30cadd05f0feee2d32bd0704c89a1464","sha256:79d75b81bba8fe8d7cdff3db2fe71043def15a392bef73815963838ee854f2fd"],"state_sha256":"35e833515de0afaf03398b19fe6dd0ac482f6c2594fe74f52595452a5dddba50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FchoGfgibkQnUD6Q/bQeZVslbT82Mh/fDvEVkJC2lZ64DlX7xulvU1W+mkr/7Nnuw225z35lri4shZoYzrk/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T00:35:08.658882Z","bundle_sha256":"715b58bb6d856b86f1bbf9ce60fa50fb2bd09075863c1043616eb54a089af72a"}}