{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:62YP7K5BRHQK7RKATHBFA253DP","short_pith_number":"pith:62YP7K5B","canonical_record":{"source":{"id":"1901.07291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-22T13:22:34Z","cross_cats_sorted":[],"title_canon_sha256":"ecd45a10c2652c2080e5a5a4c0ca9c48905281f20a6986f23fb6f8418b7aa49c","abstract_canon_sha256":"7ca1d0916f934a2f19795b8a8487654f0323f59e720cb706792468043bb1a8dc"},"schema_version":"1.0"},"canonical_sha256":"f6b0ffaba189e0afc54099c2506bbb1bdd76bf176693ecd806e56ec5557cfb67","source":{"kind":"arxiv","id":"1901.07291","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07291","created_at":"2026-05-17T23:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07291v1","created_at":"2026-05-17T23:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07291","created_at":"2026-05-17T23:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"62YP7K5BRHQK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"62YP7K5BRHQK7RKA","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"62YP7K5B","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:62YP7K5BRHQK7RKATHBFA253DP","target":"record","payload":{"canonical_record":{"source":{"id":"1901.07291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-22T13:22:34Z","cross_cats_sorted":[],"title_canon_sha256":"ecd45a10c2652c2080e5a5a4c0ca9c48905281f20a6986f23fb6f8418b7aa49c","abstract_canon_sha256":"7ca1d0916f934a2f19795b8a8487654f0323f59e720cb706792468043bb1a8dc"},"schema_version":"1.0"},"canonical_sha256":"f6b0ffaba189e0afc54099c2506bbb1bdd76bf176693ecd806e56ec5557cfb67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:47.460075Z","signature_b64":"9b6DppI8aEZmiSVvy21yV4zXoY8gG0UfEcX2BLt9E63/FpNP+9I96D3h6Hdh988v1UDCPqwFAxs/Ny8ed/NdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6b0ffaba189e0afc54099c2506bbb1bdd76bf176693ecd806e56ec5557cfb67","last_reissued_at":"2026-05-17T23:55:47.459422Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:47.459422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.07291","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":"2026-05-17T23:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVXhThME6mfXfPpLPpfZ6Svygzpv0y/yA0EEwPvlbGAfjdNZwGMOw09rFDjiSvQKJYvuiUc/+5yjxcnJ66m+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:47:46.732098Z"},"content_sha256":"85e48e97a7a6a66c8d60babb57709c1fe3fafcbbcfe00515f0cc717e44b1f4d1","schema_version":"1.0","event_id":"sha256:85e48e97a7a6a66c8d60babb57709c1fe3fafcbbcfe00515f0cc717e44b1f4d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:62YP7K5BRHQK7RKATHBFA253DP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-lingual Language Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Guillaume Lample","submitted_at":"2019-01-22T13:22:34Z","abstract_excerpt":"Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining. We propose two methods to learn cross-lingual language models (XLMs): one unsupervised that only relies on monolingual data, and one supervised that leverages parallel data with a new cross-lingual language model objective. We obtain state-of-the-art results on cross-lingual classification, unsupervised and supervised machine translation. On XNLI, our approach pu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07291","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":"2026-05-17T23:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6fAcQn1W0iWBMbGK6lW5d0qyboO7/kJgUTEJIA1GdIRFstzPC3Vq1DKkZyI19iW3DggQ+ESbpUot99T99EqoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:47:46.732518Z"},"content_sha256":"070fc20ad4c498e24d390b8510d8e8a400b18f7f184b591f4015908947c32cc6","schema_version":"1.0","event_id":"sha256:070fc20ad4c498e24d390b8510d8e8a400b18f7f184b591f4015908947c32cc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62YP7K5BRHQK7RKATHBFA253DP/bundle.json","state_url":"https://pith.science/pith/62YP7K5BRHQK7RKATHBFA253DP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62YP7K5BRHQK7RKATHBFA253DP/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":"2026-05-25T15:47:46Z","links":{"resolver":"https://pith.science/pith/62YP7K5BRHQK7RKATHBFA253DP","bundle":"https://pith.science/pith/62YP7K5BRHQK7RKATHBFA253DP/bundle.json","state":"https://pith.science/pith/62YP7K5BRHQK7RKATHBFA253DP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62YP7K5BRHQK7RKATHBFA253DP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:62YP7K5BRHQK7RKATHBFA253DP","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":"7ca1d0916f934a2f19795b8a8487654f0323f59e720cb706792468043bb1a8dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-22T13:22:34Z","title_canon_sha256":"ecd45a10c2652c2080e5a5a4c0ca9c48905281f20a6986f23fb6f8418b7aa49c"},"schema_version":"1.0","source":{"id":"1901.07291","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07291","created_at":"2026-05-17T23:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07291v1","created_at":"2026-05-17T23:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07291","created_at":"2026-05-17T23:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"62YP7K5BRHQK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"62YP7K5BRHQK7RKA","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"62YP7K5B","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:070fc20ad4c498e24d390b8510d8e8a400b18f7f184b591f4015908947c32cc6","target":"graph","created_at":"2026-05-17T23:55:47Z","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":"Recent studies have demonstrated the efficiency of generative pretraining for English natural language understanding. In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining. We propose two methods to learn cross-lingual language models (XLMs): one unsupervised that only relies on monolingual data, and one supervised that leverages parallel data with a new cross-lingual language model objective. We obtain state-of-the-art results on cross-lingual classification, unsupervised and supervised machine translation. On XNLI, our approach pu","authors_text":"Alexis Conneau, Guillaume Lample","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-22T13:22:34Z","title":"Cross-lingual Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07291","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":"sha256:85e48e97a7a6a66c8d60babb57709c1fe3fafcbbcfe00515f0cc717e44b1f4d1","target":"record","created_at":"2026-05-17T23:55:47Z","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":"7ca1d0916f934a2f19795b8a8487654f0323f59e720cb706792468043bb1a8dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-22T13:22:34Z","title_canon_sha256":"ecd45a10c2652c2080e5a5a4c0ca9c48905281f20a6986f23fb6f8418b7aa49c"},"schema_version":"1.0","source":{"id":"1901.07291","kind":"arxiv","version":1}},"canonical_sha256":"f6b0ffaba189e0afc54099c2506bbb1bdd76bf176693ecd806e56ec5557cfb67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6b0ffaba189e0afc54099c2506bbb1bdd76bf176693ecd806e56ec5557cfb67","first_computed_at":"2026-05-17T23:55:47.459422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:47.459422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9b6DppI8aEZmiSVvy21yV4zXoY8gG0UfEcX2BLt9E63/FpNP+9I96D3h6Hdh988v1UDCPqwFAxs/Ny8ed/NdCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:47.460075Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.07291","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85e48e97a7a6a66c8d60babb57709c1fe3fafcbbcfe00515f0cc717e44b1f4d1","sha256:070fc20ad4c498e24d390b8510d8e8a400b18f7f184b591f4015908947c32cc6"],"state_sha256":"032c975722589f2b6b409b3510a56d991168dd44668ee7d88bc8ca7df85728cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mQBgs0zLZjSiF7vpmSko56a89oVgvlPYqqxQE8F0YmPoMzsXndYPwfGfEW+ztk3/WipopJzlUJ14vldAOF5ECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:47:46.735791Z","bundle_sha256":"f3370e8313d033a30d7b9170df09cf46469931ac91ca82a8d44f205ac5e80de8"}}