{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WG3XONPUHECZPIYMQQIQQJZN2W","short_pith_number":"pith:WG3XONPU","canonical_record":{"source":{"id":"1906.08401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T00:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad570dda61a05187b960bd068a6792e36992ddd554312c5e240b80b6d6a6a08f","abstract_canon_sha256":"e9a07d445e3c75dc782924a010f84f5a7c98882e0b0d923d71a71d647b2be426"},"schema_version":"1.0"},"canonical_sha256":"b1b77735f4390597a30c841108272dd597e4342c7604bf5842f83c0e0cc66b9e","source":{"kind":"arxiv","id":"1906.08401","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08401","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08401v2","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08401","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"WG3XONPUHECZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WG3XONPUHECZPIYM","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WG3XONPU","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WG3XONPUHECZPIYMQQIQQJZN2W","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T00:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad570dda61a05187b960bd068a6792e36992ddd554312c5e240b80b6d6a6a08f","abstract_canon_sha256":"e9a07d445e3c75dc782924a010f84f5a7c98882e0b0d923d71a71d647b2be426"},"schema_version":"1.0"},"canonical_sha256":"b1b77735f4390597a30c841108272dd597e4342c7604bf5842f83c0e0cc66b9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:52.803214Z","signature_b64":"ZWNztofPcf+9EWIjaoIdYJ/zeQK1REPtbCcktMOMdxscP9EsGnYczULcdVxhNTQJes/CpE7zB8KJDnPk7rgiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1b77735f4390597a30c841108272dd597e4342c7604bf5842f83c0e0cc66b9e","last_reissued_at":"2026-05-17T23:41:52.802652Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:52.802652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08401","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pC2CPQNBeztx/RJZQaQJcf3CjQ7YhY170BFJi/bn9oTieffZaf4CyafFnvVL1EWAmg4MM3e257Y/RUnwHUU0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:58:11.083275Z"},"content_sha256":"4808d3c7ae0b88f902416967302a572660f1b8300550e5ff9a32bafb5c9a3e1b","schema_version":"1.0","event_id":"sha256:4808d3c7ae0b88f902416967302a572660f1b8300550e5ff9a32bafb5c9a3e1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WG3XONPUHECZPIYMQQIQQJZN2W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Document Encoder for Parallel Corpus Mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Strope, Daniel Cer, Heming Ge, Keith Stevens, Mandy Guo, Ray Kurzweil, Yinfei Yang, Yun-hsuan Sung","submitted_at":"2019-06-20T00:59:22Z","abstract_excerpt":"We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings; (ii) a neural bag-of-words (BoW) document encoding model; (iii) a hierarchical multilingual document encoder (HiDE) that builds on our sentence-level model. The results show document embeddings derived from sentence-level averaging are surprisingly effective for clean datasets, but suggest models trained hierarchically at the document-level are more effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08401","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TmT/rOyJ1xd5jFlhkNhGxzj5yPi+wVkPhcwWjKRurYSoYT9WmJmIn5ypcys3AGSopTmvSQI8wFg7/BXtkysmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:58:11.084017Z"},"content_sha256":"71e15719dac45356b1600d3b73d5e672068d27ec977426a8b006129ec1dbfdf4","schema_version":"1.0","event_id":"sha256:71e15719dac45356b1600d3b73d5e672068d27ec977426a8b006129ec1dbfdf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WG3XONPUHECZPIYMQQIQQJZN2W/bundle.json","state_url":"https://pith.science/pith/WG3XONPUHECZPIYMQQIQQJZN2W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WG3XONPUHECZPIYMQQIQQJZN2W/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":"2026-05-26T06:58:11Z","links":{"resolver":"https://pith.science/pith/WG3XONPUHECZPIYMQQIQQJZN2W","bundle":"https://pith.science/pith/WG3XONPUHECZPIYMQQIQQJZN2W/bundle.json","state":"https://pith.science/pith/WG3XONPUHECZPIYMQQIQQJZN2W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WG3XONPUHECZPIYMQQIQQJZN2W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WG3XONPUHECZPIYMQQIQQJZN2W","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":"e9a07d445e3c75dc782924a010f84f5a7c98882e0b0d923d71a71d647b2be426","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T00:59:22Z","title_canon_sha256":"ad570dda61a05187b960bd068a6792e36992ddd554312c5e240b80b6d6a6a08f"},"schema_version":"1.0","source":{"id":"1906.08401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08401","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08401v2","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08401","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"WG3XONPUHECZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WG3XONPUHECZPIYM","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WG3XONPU","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:71e15719dac45356b1600d3b73d5e672068d27ec977426a8b006129ec1dbfdf4","target":"graph","created_at":"2026-05-17T23:41:52Z","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":"We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings; (ii) a neural bag-of-words (BoW) document encoding model; (iii) a hierarchical multilingual document encoder (HiDE) that builds on our sentence-level model. The results show document embeddings derived from sentence-level averaging are surprisingly effective for clean datasets, but suggest models trained hierarchically at the document-level are more effective","authors_text":"Brian Strope, Daniel Cer, Heming Ge, Keith Stevens, Mandy Guo, Ray Kurzweil, Yinfei Yang, Yun-hsuan Sung","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T00:59:22Z","title":"Hierarchical Document Encoder for Parallel Corpus Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08401","kind":"arxiv","version":2},"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":"sha256:4808d3c7ae0b88f902416967302a572660f1b8300550e5ff9a32bafb5c9a3e1b","target":"record","created_at":"2026-05-17T23:41:52Z","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":"e9a07d445e3c75dc782924a010f84f5a7c98882e0b0d923d71a71d647b2be426","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-20T00:59:22Z","title_canon_sha256":"ad570dda61a05187b960bd068a6792e36992ddd554312c5e240b80b6d6a6a08f"},"schema_version":"1.0","source":{"id":"1906.08401","kind":"arxiv","version":2}},"canonical_sha256":"b1b77735f4390597a30c841108272dd597e4342c7604bf5842f83c0e0cc66b9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1b77735f4390597a30c841108272dd597e4342c7604bf5842f83c0e0cc66b9e","first_computed_at":"2026-05-17T23:41:52.802652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:52.802652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZWNztofPcf+9EWIjaoIdYJ/zeQK1REPtbCcktMOMdxscP9EsGnYczULcdVxhNTQJes/CpE7zB8KJDnPk7rgiCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:52.803214Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4808d3c7ae0b88f902416967302a572660f1b8300550e5ff9a32bafb5c9a3e1b","sha256:71e15719dac45356b1600d3b73d5e672068d27ec977426a8b006129ec1dbfdf4"],"state_sha256":"1c5010ee96b539cab496369714c955b22bf129c5649d9482607009477301a80e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"plFXer2fE2yiMyzv5ucYP9w6JiyRNko0Be4ocguPb+theyAzx3xnDylFAqmda3Mp/UyZmvxUZSYlz4hV31iFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:58:11.087880Z","bundle_sha256":"78daba0a63a92cc8c6a2edb568dacd0f32a1da9d2180bec40d5f39ec17991619"}}