{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6BBKVEH7BR42CTVJSMFGWOUPSG","short_pith_number":"pith:6BBKVEH7","canonical_record":{"source":{"id":"1909.00964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T06:11:44Z","cross_cats_sorted":[],"title_canon_sha256":"419d0fc4881f3af69eebfcb6b84f8f3b466a7c71c83759188bbd39aea7d9f9b1","abstract_canon_sha256":"ff65fc9515a8bf579c2fca92f3b1c67bb377d180b637910dde8b1a7b5f1385c7"},"schema_version":"1.0"},"canonical_sha256":"f042aa90ff0c79a14ea9930a6b3a8f91bfd2204a06d65f586159fdc5973ffc41","source":{"kind":"arxiv","id":"1909.00964","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00964","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00964v2","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00964","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"6BBKVEH7BR42","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"6BBKVEH7BR42CTVJ","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"6BBKVEH7","created_at":"2026-07-05T00:02:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6BBKVEH7BR42CTVJSMFGWOUPSG","target":"record","payload":{"canonical_record":{"source":{"id":"1909.00964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T06:11:44Z","cross_cats_sorted":[],"title_canon_sha256":"419d0fc4881f3af69eebfcb6b84f8f3b466a7c71c83759188bbd39aea7d9f9b1","abstract_canon_sha256":"ff65fc9515a8bf579c2fca92f3b1c67bb377d180b637910dde8b1a7b5f1385c7"},"schema_version":"1.0"},"canonical_sha256":"f042aa90ff0c79a14ea9930a6b3a8f91bfd2204a06d65f586159fdc5973ffc41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:15.238487Z","signature_b64":"RxPn2F1S63hcZjbzhqLLVmVeCafGErMuQPTgKKKwuvZmEQBr6dn3gAASNdW64B1iB+AHuLIPFDhrZeguBmcfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f042aa90ff0c79a14ea9930a6b3a8f91bfd2204a06d65f586159fdc5973ffc41","last_reissued_at":"2026-07-05T00:02:15.238067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:15.238067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.00964","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":"2026-07-05T00:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0l3BKm7mGstBxWeqiuj/w4ch439txCNSleLXACme7HM7s5uxajplY4HADKKDvq8//8Z9MRu+63I+pPzGMFssBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T07:22:23.118128Z"},"content_sha256":"c60aeeadc9c4d013f6294b8522bbb5f5349ea8d676e74a1030027ea371958842","schema_version":"1.0","event_id":"sha256:c60aeeadc9c4d013f6294b8522bbb5f5349ea8d676e74a1030027ea371958842"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6BBKVEH7BR42CTVJSMFGWOUPSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Haoyang Huang, Linjun Shou, Ming Gong, Ming Zhou, Nan Duan, Yaobo Liang","submitted_at":"2019-09-03T06:11:44Z","abstract_excerpt":"We present Unicoder, a universal language encoder that is insensitive to different languages. Given an arbitrary NLP task, a model can be trained with Unicoder using training data in one language and directly applied to inputs of the same task in other languages. Comparing to similar efforts such as Multilingual BERT and XLM, three new cross-lingual pre-training tasks are proposed, including cross-lingual word recovery, cross-lingual paraphrase classification and cross-lingual masked language model. These tasks help Unicoder learn the mappings among different languages from more perspectives. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00964","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.00964/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GPyGBdwyXl3UXo2R4jNu6LE0eQ9K9o0/hCWbp3bGwB3Cl1j/cK5+u+QIdKaz9cc81IWFhg5qLkQBQQRSBDTUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T07:22:23.118528Z"},"content_sha256":"c6a285c86d07c6b044cb4ae31330d51f00dcd89ee7404083de29819a26e8495d","schema_version":"1.0","event_id":"sha256:c6a285c86d07c6b044cb4ae31330d51f00dcd89ee7404083de29819a26e8495d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6BBKVEH7BR42CTVJSMFGWOUPSG/bundle.json","state_url":"https://pith.science/pith/6BBKVEH7BR42CTVJSMFGWOUPSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6BBKVEH7BR42CTVJSMFGWOUPSG/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":"2026-07-26T07:22:23Z","links":{"resolver":"https://pith.science/pith/6BBKVEH7BR42CTVJSMFGWOUPSG","bundle":"https://pith.science/pith/6BBKVEH7BR42CTVJSMFGWOUPSG/bundle.json","state":"https://pith.science/pith/6BBKVEH7BR42CTVJSMFGWOUPSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6BBKVEH7BR42CTVJSMFGWOUPSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6BBKVEH7BR42CTVJSMFGWOUPSG","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":"ff65fc9515a8bf579c2fca92f3b1c67bb377d180b637910dde8b1a7b5f1385c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T06:11:44Z","title_canon_sha256":"419d0fc4881f3af69eebfcb6b84f8f3b466a7c71c83759188bbd39aea7d9f9b1"},"schema_version":"1.0","source":{"id":"1909.00964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00964","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00964v2","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00964","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"6BBKVEH7BR42","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"6BBKVEH7BR42CTVJ","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"6BBKVEH7","created_at":"2026-07-05T00:02:15Z"}],"graph_snapshots":[{"event_id":"sha256:c6a285c86d07c6b044cb4ae31330d51f00dcd89ee7404083de29819a26e8495d","target":"graph","created_at":"2026-07-05T00:02:15Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.00964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Unicoder, a universal language encoder that is insensitive to different languages. Given an arbitrary NLP task, a model can be trained with Unicoder using training data in one language and directly applied to inputs of the same task in other languages. Comparing to similar efforts such as Multilingual BERT and XLM, three new cross-lingual pre-training tasks are proposed, including cross-lingual word recovery, cross-lingual paraphrase classification and cross-lingual masked language model. These tasks help Unicoder learn the mappings among different languages from more perspectives. ","authors_text":"Daxin Jiang, Haoyang Huang, Linjun Shou, Ming Gong, Ming Zhou, Nan Duan, Yaobo Liang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T06:11:44Z","title":"Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00964","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:c60aeeadc9c4d013f6294b8522bbb5f5349ea8d676e74a1030027ea371958842","target":"record","created_at":"2026-07-05T00:02:15Z","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":"ff65fc9515a8bf579c2fca92f3b1c67bb377d180b637910dde8b1a7b5f1385c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-03T06:11:44Z","title_canon_sha256":"419d0fc4881f3af69eebfcb6b84f8f3b466a7c71c83759188bbd39aea7d9f9b1"},"schema_version":"1.0","source":{"id":"1909.00964","kind":"arxiv","version":2}},"canonical_sha256":"f042aa90ff0c79a14ea9930a6b3a8f91bfd2204a06d65f586159fdc5973ffc41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f042aa90ff0c79a14ea9930a6b3a8f91bfd2204a06d65f586159fdc5973ffc41","first_computed_at":"2026-07-05T00:02:15.238067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:15.238067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RxPn2F1S63hcZjbzhqLLVmVeCafGErMuQPTgKKKwuvZmEQBr6dn3gAASNdW64B1iB+AHuLIPFDhrZeguBmcfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:15.238487Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.00964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c60aeeadc9c4d013f6294b8522bbb5f5349ea8d676e74a1030027ea371958842","sha256:c6a285c86d07c6b044cb4ae31330d51f00dcd89ee7404083de29819a26e8495d"],"state_sha256":"379c616359bc9302f1d142ab2fcfd2e50fb524026a3c66ee8b1ba05b0fb56b8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oPYp5L6oa+fn8tBL/zWHRC7VSMReEyd6nr/e3GcIJ7O6ncJFaWMzvAsQX7TyrvthH6DEH3f0aVJYjKc/XOcEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T07:22:23.122012Z","bundle_sha256":"a93a95f950312b059971203ad498d58b7d9eca233ae1540b5bf62e096e1c3e16"}}