{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JT4S4YL35A573LKASW3HWC44QD","short_pith_number":"pith:JT4S4YL3","canonical_record":{"source":{"id":"2010.03142","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T03:57:54Z","cross_cats_sorted":[],"title_canon_sha256":"f8fade25f57edf23538260516ad8b62901e81bed3614619567923c4b57b95c38","abstract_canon_sha256":"87508d61af8272316182b6caaaeef462b767f8c9a8c2f39fe93bd06dce5a1823"},"schema_version":"1.0"},"canonical_sha256":"4cf92e617be83bfdad4095b67b0b9c80eea5364bb82274b180117e41e1589da5","source":{"kind":"arxiv","id":"2010.03142","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03142","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03142v3","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03142","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"pith_short_12","alias_value":"JT4S4YL35A57","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"pith_short_16","alias_value":"JT4S4YL35A573LKA","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"pith_short_8","alias_value":"JT4S4YL3","created_at":"2026-07-05T02:08:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JT4S4YL35A573LKASW3HWC44QD","target":"record","payload":{"canonical_record":{"source":{"id":"2010.03142","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T03:57:54Z","cross_cats_sorted":[],"title_canon_sha256":"f8fade25f57edf23538260516ad8b62901e81bed3614619567923c4b57b95c38","abstract_canon_sha256":"87508d61af8272316182b6caaaeef462b767f8c9a8c2f39fe93bd06dce5a1823"},"schema_version":"1.0"},"canonical_sha256":"4cf92e617be83bfdad4095b67b0b9c80eea5364bb82274b180117e41e1589da5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:50.725693Z","signature_b64":"PJiQWpabra8gH2S9LpXLS3xpsNEDdRJu1dB/FK97ZGbA57uYacdP7bMUIl2UuhO6IyU1lWV6noftPL34fy5dBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cf92e617be83bfdad4095b67b0b9c80eea5364bb82274b180117e41e1589da5","last_reissued_at":"2026-07-05T02:08:50.725188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:50.725188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.03142","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:08:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q2A7uzyi/qarRwwWr3iltCDXijqJtcvGhIvgbbdPDGKLXferKMPf1ZzunCQAoSxT0szOQHpKH5q7f0eauRLaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:17:09.157127Z"},"content_sha256":"3fe77d5d22654db5a58934fad0ea7592e90dcb7064ab1fc6b7a0eab2802ac5d4","schema_version":"1.0","event_id":"sha256:3fe77d5d22654db5a58934fad0ea7592e90dcb7064ab1fc6b7a0eab2802ac5d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JT4S4YL35A573LKASW3HWC44QD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Jiangtao Feng, Lei Li, Mingxuan Wang, Xiao Pan, Xipeng Qiu, Zehui Lin","submitted_at":"2020-10-07T03:57:54Z","abstract_excerpt":"We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach to pre-train a universal multilingual neural machine translation model. Our key idea in mRASP is its novel technique of random aligned substitution, which brings words and phrases with similar meanings across multiple languages closer in the representation space. We pre-train a mRASP model on 32 language pairs jointly with only public datasets. The model is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03142","kind":"arxiv","version":3},"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/2010.03142/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":"2026-07-05T02:08:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u41FD4oPdJEjtQoLP55+hrFyLesFIVgs7WlTZhVXS4NW4D8Mtqvq/FUF/1duru9lAkf3MUBouTZCRv3cma+YBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:17:09.157626Z"},"content_sha256":"3db3e57a0085e000e83b9920a8bc4043d74bf13c4ef3ef0c8bcb4cfd68ef6e21","schema_version":"1.0","event_id":"sha256:3db3e57a0085e000e83b9920a8bc4043d74bf13c4ef3ef0c8bcb4cfd68ef6e21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JT4S4YL35A573LKASW3HWC44QD/bundle.json","state_url":"https://pith.science/pith/JT4S4YL35A573LKASW3HWC44QD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JT4S4YL35A573LKASW3HWC44QD/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":"2026-08-03T19:17:09Z","links":{"resolver":"https://pith.science/pith/JT4S4YL35A573LKASW3HWC44QD","bundle":"https://pith.science/pith/JT4S4YL35A573LKASW3HWC44QD/bundle.json","state":"https://pith.science/pith/JT4S4YL35A573LKASW3HWC44QD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JT4S4YL35A573LKASW3HWC44QD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JT4S4YL35A573LKASW3HWC44QD","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":"87508d61af8272316182b6caaaeef462b767f8c9a8c2f39fe93bd06dce5a1823","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T03:57:54Z","title_canon_sha256":"f8fade25f57edf23538260516ad8b62901e81bed3614619567923c4b57b95c38"},"schema_version":"1.0","source":{"id":"2010.03142","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03142","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03142v3","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03142","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"pith_short_12","alias_value":"JT4S4YL35A57","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"pith_short_16","alias_value":"JT4S4YL35A573LKA","created_at":"2026-07-05T02:08:50Z"},{"alias_kind":"pith_short_8","alias_value":"JT4S4YL3","created_at":"2026-07-05T02:08:50Z"}],"graph_snapshots":[{"event_id":"sha256:3db3e57a0085e000e83b9920a8bc4043d74bf13c4ef3ef0c8bcb4cfd68ef6e21","target":"graph","created_at":"2026-07-05T02:08:50Z","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/2010.03142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach to pre-train a universal multilingual neural machine translation model. Our key idea in mRASP is its novel technique of random aligned substitution, which brings words and phrases with similar meanings across multiple languages closer in the representation space. We pre-train a mRASP model on 32 language pairs jointly with only public datasets. The model is ","authors_text":"Hao Zhou, Jiangtao Feng, Lei Li, Mingxuan Wang, Xiao Pan, Xipeng Qiu, Zehui Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T03:57:54Z","title":"Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03142","kind":"arxiv","version":3},"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":"sha256:3fe77d5d22654db5a58934fad0ea7592e90dcb7064ab1fc6b7a0eab2802ac5d4","target":"record","created_at":"2026-07-05T02:08:50Z","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":"87508d61af8272316182b6caaaeef462b767f8c9a8c2f39fe93bd06dce5a1823","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T03:57:54Z","title_canon_sha256":"f8fade25f57edf23538260516ad8b62901e81bed3614619567923c4b57b95c38"},"schema_version":"1.0","source":{"id":"2010.03142","kind":"arxiv","version":3}},"canonical_sha256":"4cf92e617be83bfdad4095b67b0b9c80eea5364bb82274b180117e41e1589da5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cf92e617be83bfdad4095b67b0b9c80eea5364bb82274b180117e41e1589da5","first_computed_at":"2026-07-05T02:08:50.725188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:08:50.725188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PJiQWpabra8gH2S9LpXLS3xpsNEDdRJu1dB/FK97ZGbA57uYacdP7bMUIl2UuhO6IyU1lWV6noftPL34fy5dBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:08:50.725693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03142","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fe77d5d22654db5a58934fad0ea7592e90dcb7064ab1fc6b7a0eab2802ac5d4","sha256:3db3e57a0085e000e83b9920a8bc4043d74bf13c4ef3ef0c8bcb4cfd68ef6e21"],"state_sha256":"a8a58c242b3ffbc50a116401ed7af74ede6e559bf46f7f277c6d20dfc4651f73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8u8EJYlPIIkx0To9jOoxqQV8f/QzPLu+yU5B5bhtcyE/WXPP2Vd0jcvk5/eJpoa80PCCfSraTDG0jTHPycBGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:17:09.162749Z","bundle_sha256":"5084960ec0d48415b15c1f8b8a3669ff8f4fb9a89579f1703338678242b57f0a"}}