{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2EQCR52DMTCEACBVF4YA5ILILQ","short_pith_number":"pith:2EQCR52D","canonical_record":{"source":{"id":"2012.15547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T11:16:51Z","cross_cats_sorted":[],"title_canon_sha256":"a0b97b36312534ae3518c7b16c3efc861afa4af6bdb30b5836f3cbcaf470d6d3","abstract_canon_sha256":"15c2e0568b9614d37015f96374cc4b19a7864e2a1203046a5ea8a6166c45b61d"},"schema_version":"1.0"},"canonical_sha256":"d12028f74364c44008352f300ea1685c1af77c039fe73cfc31b81d408cedb9a3","source":{"kind":"arxiv","id":"2012.15547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15547","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15547v1","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15547","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"2EQCR52DMTCE","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"2EQCR52DMTCEACBV","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"2EQCR52D","created_at":"2026-07-05T02:03:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2EQCR52DMTCEACBVF4YA5ILILQ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T11:16:51Z","cross_cats_sorted":[],"title_canon_sha256":"a0b97b36312534ae3518c7b16c3efc861afa4af6bdb30b5836f3cbcaf470d6d3","abstract_canon_sha256":"15c2e0568b9614d37015f96374cc4b19a7864e2a1203046a5ea8a6166c45b61d"},"schema_version":"1.0"},"canonical_sha256":"d12028f74364c44008352f300ea1685c1af77c039fe73cfc31b81d408cedb9a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:03:19.631210Z","signature_b64":"5vE28p6YgdPA/HjDHjdSKAIfAkOcfsE39iM20OYIXH8+wkdY6jxyaX0Bs6FjzioldO6jcurpOUxEeRJUKu3mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d12028f74364c44008352f300ea1685c1af77c039fe73cfc31b81d408cedb9a3","last_reissued_at":"2026-07-05T02:03:19.630851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:03:19.630851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15547","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":"2026-07-05T02:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6TjRIcFwoncCSs0sg4lUSNrVfXb4vMFqYmg7O04zl7KNaYE1k+Yv+L0IhrO9mvdP0so+fstZXJ2UIMJ+ReDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:37:24.228701Z"},"content_sha256":"2665e289c2126af2cf0b6158fc1719beb062b4ffd10851256235dd258da63c8f","schema_version":"1.0","event_id":"sha256:2665e289c2126af2cf0b6158fc1719beb062b4ffd10851256235dd258da63c8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2EQCR52DMTCEACBVF4YA5ILILQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Eriguchi, Alexandre Muzio, Arul Menezes, Dongdong Zhang, Furu Wei, Hany Hassan Awadalla, Haoyang Huang, Jian Yang, Li Dong, Saksham Singhal, Shuming Ma, Xia Song, Zewen Chi","submitted_at":"2020-12-31T11:16:51Z","abstract_excerpt":"Multilingual machine translation enables a single model to translate between different languages. Most existing multilingual machine translation systems adopt a randomly initialized Transformer backbone. In this work, inspired by the recent success of language model pre-training, we present XLM-T, which initializes the model with an off-the-shelf pretrained cross-lingual Transformer encoder and fine-tunes it with multilingual parallel data. This simple method achieves significant improvements on a WMT dataset with 10 language pairs and the OPUS-100 corpus with 94 pairs. Surprisingly, the metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15547","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.15547/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":"2026-07-05T02:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tuOdt7rkPrxyixL7PahZBZOk8wSD8JbczvbfIN5+Z4FJrUBViINFe36C7YL1MRPhF3CEyO4jeXVjdxv8L7ZQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:37:24.229078Z"},"content_sha256":"4325d73bb31f1ba250517feef0869f2eccb1f2f6de8985d45f15beaf5be873b1","schema_version":"1.0","event_id":"sha256:4325d73bb31f1ba250517feef0869f2eccb1f2f6de8985d45f15beaf5be873b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2EQCR52DMTCEACBVF4YA5ILILQ/bundle.json","state_url":"https://pith.science/pith/2EQCR52DMTCEACBVF4YA5ILILQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2EQCR52DMTCEACBVF4YA5ILILQ/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":"2026-07-05T15:37:24Z","links":{"resolver":"https://pith.science/pith/2EQCR52DMTCEACBVF4YA5ILILQ","bundle":"https://pith.science/pith/2EQCR52DMTCEACBVF4YA5ILILQ/bundle.json","state":"https://pith.science/pith/2EQCR52DMTCEACBVF4YA5ILILQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2EQCR52DMTCEACBVF4YA5ILILQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2EQCR52DMTCEACBVF4YA5ILILQ","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":"15c2e0568b9614d37015f96374cc4b19a7864e2a1203046a5ea8a6166c45b61d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T11:16:51Z","title_canon_sha256":"a0b97b36312534ae3518c7b16c3efc861afa4af6bdb30b5836f3cbcaf470d6d3"},"schema_version":"1.0","source":{"id":"2012.15547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15547","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15547v1","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15547","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"2EQCR52DMTCE","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"2EQCR52DMTCEACBV","created_at":"2026-07-05T02:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"2EQCR52D","created_at":"2026-07-05T02:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:4325d73bb31f1ba250517feef0869f2eccb1f2f6de8985d45f15beaf5be873b1","target":"graph","created_at":"2026-07-05T02:03:19Z","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/2012.15547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual machine translation enables a single model to translate between different languages. Most existing multilingual machine translation systems adopt a randomly initialized Transformer backbone. In this work, inspired by the recent success of language model pre-training, we present XLM-T, which initializes the model with an off-the-shelf pretrained cross-lingual Transformer encoder and fine-tunes it with multilingual parallel data. This simple method achieves significant improvements on a WMT dataset with 10 language pairs and the OPUS-100 corpus with 94 pairs. Surprisingly, the metho","authors_text":"Akiko Eriguchi, Alexandre Muzio, Arul Menezes, Dongdong Zhang, Furu Wei, Hany Hassan Awadalla, Haoyang Huang, Jian Yang, Li Dong, Saksham Singhal, Shuming Ma, Xia Song, Zewen Chi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T11:16:51Z","title":"XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15547","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":"sha256:2665e289c2126af2cf0b6158fc1719beb062b4ffd10851256235dd258da63c8f","target":"record","created_at":"2026-07-05T02:03:19Z","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":"15c2e0568b9614d37015f96374cc4b19a7864e2a1203046a5ea8a6166c45b61d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T11:16:51Z","title_canon_sha256":"a0b97b36312534ae3518c7b16c3efc861afa4af6bdb30b5836f3cbcaf470d6d3"},"schema_version":"1.0","source":{"id":"2012.15547","kind":"arxiv","version":1}},"canonical_sha256":"d12028f74364c44008352f300ea1685c1af77c039fe73cfc31b81d408cedb9a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d12028f74364c44008352f300ea1685c1af77c039fe73cfc31b81d408cedb9a3","first_computed_at":"2026-07-05T02:03:19.630851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:03:19.630851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5vE28p6YgdPA/HjDHjdSKAIfAkOcfsE39iM20OYIXH8+wkdY6jxyaX0Bs6FjzioldO6jcurpOUxEeRJUKu3mCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:03:19.631210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2665e289c2126af2cf0b6158fc1719beb062b4ffd10851256235dd258da63c8f","sha256:4325d73bb31f1ba250517feef0869f2eccb1f2f6de8985d45f15beaf5be873b1"],"state_sha256":"7e233a05703f46f4cd03a55d78ede1b058321e70f9529665037cad6ec1c9fc44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RlxX8xGut74Oe2iYM+gkZzcqjei8IxdsGV+bF4zw0ONyiRfKyoHuTqP2zMOEQaEHOJMio+rudd6ZLW7Now59Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:37:24.231892Z","bundle_sha256":"8ed926bd65a2decf25bae48aaa901c9a8b75500a083b8ac32eff398052bd7709"}}