{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R56AKFHIXKBVQTC3RUF4WTFAOV","short_pith_number":"pith:R56AKFHI","schema_version":"1.0","canonical_sha256":"8f7c0514e8ba83584c5b8d0bcb4ca07557ec5c394ab9fca3f9bec322b59ebc36","source":{"kind":"arxiv","id":"1904.03922","version":1},"attestation_state":"computed","paper":{"title":"Crosslingual Document Embedding as Reduced-Rank Ridge Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hristo S. Paskov, Ivan S. Paskov, Martin Jaggi, Martin Josifoski, Robert West","submitted_at":"2019-04-08T10:02:05Z","abstract_excerpt":"There has recently been much interest in extending vector-based word representations to multiple languages, such that words can be compared across languages. In this paper, we shift the focus from words to documents and introduce a method for embedding documents written in any language into a single, language-independent vector space. For training, our approach leverages a multilingual corpus where the same concept is covered in multiple languages (but not necessarily via exact translations), such as Wikipedia. Our method, Cr5 (Crosslingual reduced-rank ridge regression), starts by training a "},"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":"1904.03922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T10:02:05Z","cross_cats_sorted":[],"title_canon_sha256":"b6607356b12c5689629b37130ca9d4de18ef155bf0ca6ee95443e91f77c698c2","abstract_canon_sha256":"e11e6944f5133e69d72c1e94061d79cf25b30d661cb3c9fc230bb082b33e9c66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:07.674054Z","signature_b64":"mDCuWtMBGHdN7pjGJptHXtYfc+FxV32HCCTyTWabhYvU2hNdpfTFgG2MTlFrY2iBeDNH4e9UJ56yW+wDKr/NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f7c0514e8ba83584c5b8d0bcb4ca07557ec5c394ab9fca3f9bec322b59ebc36","last_reissued_at":"2026-05-17T23:49:07.673384Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:07.673384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crosslingual Document Embedding as Reduced-Rank Ridge Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hristo S. Paskov, Ivan S. Paskov, Martin Jaggi, Martin Josifoski, Robert West","submitted_at":"2019-04-08T10:02:05Z","abstract_excerpt":"There has recently been much interest in extending vector-based word representations to multiple languages, such that words can be compared across languages. In this paper, we shift the focus from words to documents and introduce a method for embedding documents written in any language into a single, language-independent vector space. For training, our approach leverages a multilingual corpus where the same concept is covered in multiple languages (but not necessarily via exact translations), such as Wikipedia. Our method, Cr5 (Crosslingual reduced-rank ridge regression), starts by training a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03922","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":"1904.03922","created_at":"2026-05-17T23:49:07.673478+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03922v1","created_at":"2026-05-17T23:49:07.673478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03922","created_at":"2026-05-17T23:49:07.673478+00:00"},{"alias_kind":"pith_short_12","alias_value":"R56AKFHIXKBV","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"R56AKFHIXKBVQTC3","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"R56AKFHI","created_at":"2026-05-18T12:33:27.125529+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/R56AKFHIXKBVQTC3RUF4WTFAOV","json":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV.json","graph_json":"https://pith.science/api/pith-number/R56AKFHIXKBVQTC3RUF4WTFAOV/graph.json","events_json":"https://pith.science/api/pith-number/R56AKFHIXKBVQTC3RUF4WTFAOV/events.json","paper":"https://pith.science/paper/R56AKFHI"},"agent_actions":{"view_html":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV","download_json":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV.json","view_paper":"https://pith.science/paper/R56AKFHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03922&json=true","fetch_graph":"https://pith.science/api/pith-number/R56AKFHIXKBVQTC3RUF4WTFAOV/graph.json","fetch_events":"https://pith.science/api/pith-number/R56AKFHIXKBVQTC3RUF4WTFAOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/action/storage_attestation","attest_author":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/action/author_attestation","sign_citation":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/action/citation_signature","submit_replication":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/action/replication_record"}},"created_at":"2026-05-17T23:49:07.673478+00:00","updated_at":"2026-05-17T23:49:07.673478+00:00"}