{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KG5MZKKQYD4VX2WBWSFDPNQ4Q6","short_pith_number":"pith:KG5MZKKQ","canonical_record":{"source":{"id":"2012.15674","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:52:27Z","cross_cats_sorted":[],"title_canon_sha256":"4089e4af85282ad530ae0cee09995a9d4808ba188b90c5b141f1306b5f6b2ec2","abstract_canon_sha256":"ebf3af1944a52f98cb8fe15033c3cda3a1bdb6b23ec3cd943b816eb229111f26"},"schema_version":"1.0"},"canonical_sha256":"51bacca950c0f95beac1b48a37b61c87b84c740161aa1a5b75a2c06486494246","source":{"kind":"arxiv","id":"2012.15674","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15674","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15674v4","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15674","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"KG5MZKKQYD4V","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"KG5MZKKQYD4VX2WB","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"KG5MZKKQ","created_at":"2026-07-05T03:15:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KG5MZKKQYD4VX2WBWSFDPNQ4Q6","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15674","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:52:27Z","cross_cats_sorted":[],"title_canon_sha256":"4089e4af85282ad530ae0cee09995a9d4808ba188b90c5b141f1306b5f6b2ec2","abstract_canon_sha256":"ebf3af1944a52f98cb8fe15033c3cda3a1bdb6b23ec3cd943b816eb229111f26"},"schema_version":"1.0"},"canonical_sha256":"51bacca950c0f95beac1b48a37b61c87b84c740161aa1a5b75a2c06486494246","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:08.609482Z","signature_b64":"W0SSjEM62NscV7YkhE+/UY3gSM+wWq9/u9kfwXYKdHHXhcix6I1vZS7jvOv418MGRnp2WstTv9eU9EtslZtKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51bacca950c0f95beac1b48a37b61c87b84c740161aa1a5b75a2c06486494246","last_reissued_at":"2026-07-05T03:15:08.609070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:08.609070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15674","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6eSdpR5QigVtt4CGU5ry/TaUC9WWhIkj4EdeWSjSWSWI7I5X+bFqiIytBtbkgNC3UWL1ABRDfn7obJsIalhOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:32:54.028061Z"},"content_sha256":"55e0eb465e6159aac4c011b7199c6c071455bce3be0f52b8d9f18d69da1e1078","schema_version":"1.0","event_id":"sha256:55e0eb465e6159aac4c011b7199c6c071455bce3be0f52b8d9f18d69da1e1078"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KG5MZKKQYD4VX2WBWSFDPNQ4Q6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Pang, HaiFeng Wang, Hao Tian, Hua Wu, Shuohuan Wang, Xuan Ouyang, Yu Sun","submitted_at":"2020-12-31T15:52:27Z","abstract_excerpt":"Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is generally acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose ERNIE-M, a new training method that encourages the model to align the representation of multiple languages with monolingual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15674","kind":"arxiv","version":4},"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/2012.15674/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":"2026-07-05T03:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgbWv02lr85RZ2ocOYpLB4h8TJKtAuTJJHBFR4O4ynaZv0Xrpzf4uFnFR3fCg7bg4g7i+Ki71Wp6OtUHfx4tBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:32:54.028610Z"},"content_sha256":"8d38c59668a639922d9bd563a92fc799ef2403c30e662155ae3417d321c9ca78","schema_version":"1.0","event_id":"sha256:8d38c59668a639922d9bd563a92fc799ef2403c30e662155ae3417d321c9ca78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KG5MZKKQYD4VX2WBWSFDPNQ4Q6/bundle.json","state_url":"https://pith.science/pith/KG5MZKKQYD4VX2WBWSFDPNQ4Q6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KG5MZKKQYD4VX2WBWSFDPNQ4Q6/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":"2026-08-19T16:32:54Z","links":{"resolver":"https://pith.science/pith/KG5MZKKQYD4VX2WBWSFDPNQ4Q6","bundle":"https://pith.science/pith/KG5MZKKQYD4VX2WBWSFDPNQ4Q6/bundle.json","state":"https://pith.science/pith/KG5MZKKQYD4VX2WBWSFDPNQ4Q6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KG5MZKKQYD4VX2WBWSFDPNQ4Q6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KG5MZKKQYD4VX2WBWSFDPNQ4Q6","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":"ebf3af1944a52f98cb8fe15033c3cda3a1bdb6b23ec3cd943b816eb229111f26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:52:27Z","title_canon_sha256":"4089e4af85282ad530ae0cee09995a9d4808ba188b90c5b141f1306b5f6b2ec2"},"schema_version":"1.0","source":{"id":"2012.15674","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15674","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15674v4","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15674","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"KG5MZKKQYD4V","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"KG5MZKKQYD4VX2WB","created_at":"2026-07-05T03:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"KG5MZKKQ","created_at":"2026-07-05T03:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:8d38c59668a639922d9bd563a92fc799ef2403c30e662155ae3417d321c9ca78","target":"graph","created_at":"2026-07-05T03:15:08Z","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/2012.15674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is generally acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose ERNIE-M, a new training method that encourages the model to align the representation of multiple languages with monolingual ","authors_text":"Chao Pang, HaiFeng Wang, Hao Tian, Hua Wu, Shuohuan Wang, Xuan Ouyang, Yu Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:52:27Z","title":"ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15674","kind":"arxiv","version":4},"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":"sha256:55e0eb465e6159aac4c011b7199c6c071455bce3be0f52b8d9f18d69da1e1078","target":"record","created_at":"2026-07-05T03:15:08Z","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":"ebf3af1944a52f98cb8fe15033c3cda3a1bdb6b23ec3cd943b816eb229111f26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:52:27Z","title_canon_sha256":"4089e4af85282ad530ae0cee09995a9d4808ba188b90c5b141f1306b5f6b2ec2"},"schema_version":"1.0","source":{"id":"2012.15674","kind":"arxiv","version":4}},"canonical_sha256":"51bacca950c0f95beac1b48a37b61c87b84c740161aa1a5b75a2c06486494246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51bacca950c0f95beac1b48a37b61c87b84c740161aa1a5b75a2c06486494246","first_computed_at":"2026-07-05T03:15:08.609070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:08.609070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W0SSjEM62NscV7YkhE+/UY3gSM+wWq9/u9kfwXYKdHHXhcix6I1vZS7jvOv418MGRnp2WstTv9eU9EtslZtKBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:08.609482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15674","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55e0eb465e6159aac4c011b7199c6c071455bce3be0f52b8d9f18d69da1e1078","sha256:8d38c59668a639922d9bd563a92fc799ef2403c30e662155ae3417d321c9ca78"],"state_sha256":"f2c7d0e7ca4845a5584ae8879c80d64be59d38f7fabe7156583b2212d0b46f0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CaW0AOzIE+LMSq3eB6+AXp7KAAYJUP3SSnyaHjSE0JtnOd1EozalbVptOGepQkSYgpz0xbYnhBxw0KXDTh4LBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:32:54.032084Z","bundle_sha256":"b896d31d1d6cf46c8a1c3f94c12e6cb2a84ee7bfdcfd9759504205e97d0e665f"}}