{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:R56AKFHIXKBVQTC3RUF4WTFAOV","short_pith_number":"pith:R56AKFHI","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"},"canonical_sha256":"8f7c0514e8ba83584c5b8d0bcb4ca07557ec5c394ab9fca3f9bec322b59ebc36","source":{"kind":"arxiv","id":"1904.03922","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03922","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03922v1","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03922","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"R56AKFHIXKBV","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R56AKFHIXKBVQTC3","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R56AKFHI","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:R56AKFHIXKBVQTC3RUF4WTFAOV","target":"record","payload":{"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"},"canonical_sha256":"8f7c0514e8ba83584c5b8d0bcb4ca07557ec5c394ab9fca3f9bec322b59ebc36","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"},"source_kind":"arxiv","source_id":"1904.03922","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":"2026-05-17T23:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDysMbYc45dMUcif6faatOmvIHhfdhAiUfzOzQO3RGOJH5rjVSVNt3D83/jtjk80txveyRvmdAQ38Kusnb0MDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:01:13.200453Z"},"content_sha256":"58de121f3ab6ee1399341959f23577df0fa5683dd7dc8cb4b6cc50c1defdc972","schema_version":"1.0","event_id":"sha256:58de121f3ab6ee1399341959f23577df0fa5683dd7dc8cb4b6cc50c1defdc972"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:R56AKFHIXKBVQTC3RUF4WTFAOV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TD+33d4dvXRMZma1oxPz/D/8A7gQI0/Qr69omOHyP/yRSwDqtviG7D4NdFmyIDFH2dSBb1FK+slHIRqHHR5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:01:13.200799Z"},"content_sha256":"4748a26dcf1f794561278d32e869d3b5da6f1f58475ac25a59a295a97bddce6f","schema_version":"1.0","event_id":"sha256:4748a26dcf1f794561278d32e869d3b5da6f1f58475ac25a59a295a97bddce6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/bundle.json","state_url":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/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":"2026-06-04T18:01:13Z","links":{"resolver":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV","bundle":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/bundle.json","state":"https://pith.science/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R56AKFHIXKBVQTC3RUF4WTFAOV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R56AKFHIXKBVQTC3RUF4WTFAOV","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":"e11e6944f5133e69d72c1e94061d79cf25b30d661cb3c9fc230bb082b33e9c66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T10:02:05Z","title_canon_sha256":"b6607356b12c5689629b37130ca9d4de18ef155bf0ca6ee95443e91f77c698c2"},"schema_version":"1.0","source":{"id":"1904.03922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03922","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03922v1","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03922","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"R56AKFHIXKBV","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R56AKFHIXKBVQTC3","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R56AKFHI","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:4748a26dcf1f794561278d32e869d3b5da6f1f58475ac25a59a295a97bddce6f","target":"graph","created_at":"2026-05-17T23:49:07Z","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":"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 ","authors_text":"Hristo S. Paskov, Ivan S. Paskov, Martin Jaggi, Martin Josifoski, Robert West","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T10:02:05Z","title":"Crosslingual Document Embedding as Reduced-Rank Ridge Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03922","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":"sha256:58de121f3ab6ee1399341959f23577df0fa5683dd7dc8cb4b6cc50c1defdc972","target":"record","created_at":"2026-05-17T23:49:07Z","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":"e11e6944f5133e69d72c1e94061d79cf25b30d661cb3c9fc230bb082b33e9c66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T10:02:05Z","title_canon_sha256":"b6607356b12c5689629b37130ca9d4de18ef155bf0ca6ee95443e91f77c698c2"},"schema_version":"1.0","source":{"id":"1904.03922","kind":"arxiv","version":1}},"canonical_sha256":"8f7c0514e8ba83584c5b8d0bcb4ca07557ec5c394ab9fca3f9bec322b59ebc36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f7c0514e8ba83584c5b8d0bcb4ca07557ec5c394ab9fca3f9bec322b59ebc36","first_computed_at":"2026-05-17T23:49:07.673384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:07.673384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mDCuWtMBGHdN7pjGJptHXtYfc+FxV32HCCTyTWabhYvU2hNdpfTFgG2MTlFrY2iBeDNH4e9UJ56yW+wDKr/NBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:07.674054Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58de121f3ab6ee1399341959f23577df0fa5683dd7dc8cb4b6cc50c1defdc972","sha256:4748a26dcf1f794561278d32e869d3b5da6f1f58475ac25a59a295a97bddce6f"],"state_sha256":"10f67c3615dab8d9f97201c19262c21bf1fe09bf5c5db00ade230682f977a118"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSDHvPFGN5mA6jJfQ5zlMnJnmUGsvxC49OiwiD2tHX3TQ6BdPrXMPeeQ5YwGWPdy6IdWsyb3lRX7xjMVEH4JDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T18:01:13.202714Z","bundle_sha256":"3ac01d9e895bb2866c49e7085a8b771f8a0e8604f563a2d3db13841b0f60aca9"}}