{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NON6BKWC7EPNXHRL26H7YCENXX","short_pith_number":"pith:NON6BKWC","canonical_record":{"source":{"id":"2106.16138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T15:45:07Z","cross_cats_sorted":[],"title_canon_sha256":"029a0adbd68a96080551e2d61048ef32b72abce1db8eb9a299c4790a25b831c5","abstract_canon_sha256":"5a35486b3f5426d6ab057531a5a7fd4ace6c60868c80e1fd1d345d66e775b41b"},"schema_version":"1.0"},"canonical_sha256":"6b9be0aac2f91edb9e2bd78ffc088dbdd6cb08af932907f09ea3fb3b41d4cc60","source":{"kind":"arxiv","id":"2106.16138","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.16138","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2106.16138v2","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.16138","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"NON6BKWC7EPN","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"NON6BKWC7EPNXHRL","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"NON6BKWC","created_at":"2026-07-05T04:15:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NON6BKWC7EPNXHRL26H7YCENXX","target":"record","payload":{"canonical_record":{"source":{"id":"2106.16138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T15:45:07Z","cross_cats_sorted":[],"title_canon_sha256":"029a0adbd68a96080551e2d61048ef32b72abce1db8eb9a299c4790a25b831c5","abstract_canon_sha256":"5a35486b3f5426d6ab057531a5a7fd4ace6c60868c80e1fd1d345d66e775b41b"},"schema_version":"1.0"},"canonical_sha256":"6b9be0aac2f91edb9e2bd78ffc088dbdd6cb08af932907f09ea3fb3b41d4cc60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:43.503663Z","signature_b64":"d4TxgmkSecaL3m03MjFuRpoOEzPY40yzaTbExqKUu/eyquos81DMBnvswLwyagvQEddvsJBTnlsgq6I9CGSVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b9be0aac2f91edb9e2bd78ffc088dbdd6cb08af932907f09ea3fb3b41d4cc60","last_reissued_at":"2026-07-05T04:15:43.503171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:43.503171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.16138","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":"2026-07-05T04:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uj2gAD69cj7QL49YlIleAximQTHbZbnZhRLDvyKkh5Hxb/Iho+r5M+CtFIA/dtyhdUEqhe64QJerpltVaAMHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:07:41.616477Z"},"content_sha256":"3a1c6bdbbb0c9de0700e9731243dbb12b3d1d84640996e38a9806241fe48461c","schema_version":"1.0","event_id":"sha256:3a1c6bdbbb0c9de0700e9731243dbb12b3d1d84640996e38a9806241fe48461c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NON6BKWC7EPNXHRL26H7YCENXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Furu Wei, Heyan Huang, Li Dong, Payal Bajaj, Saksham Singhal, Shaohan Huang, Shuming Ma, Xian-Ling Mao, Xia Song, Zewen Chi","submitted_at":"2021-06-30T15:45:07Z","abstract_excerpt":"In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides, we pretrain the model, named as XLM-E, on both multilingual and parallel corpora. Our model outperforms the baseline models on various cross-lingual understanding tasks with much less computation cost. Moreover, analysis shows that XLM-E tends to obtain better cross-lingual transferability."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.16138","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/2106.16138/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":"2026-07-05T04:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ONskBtesqfNG4IK9LN69YjT5ERIBQtGWKMXBD5nts6Mn8r7NP9AfpOc+xlCoyiIySSPiIIV0uMsg7G64T1vxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:07:41.617009Z"},"content_sha256":"606f8f7708ac5d9c76a4ec5dc6978cc74434ec1afe4980011a2dffbe0cd21759","schema_version":"1.0","event_id":"sha256:606f8f7708ac5d9c76a4ec5dc6978cc74434ec1afe4980011a2dffbe0cd21759"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NON6BKWC7EPNXHRL26H7YCENXX/bundle.json","state_url":"https://pith.science/pith/NON6BKWC7EPNXHRL26H7YCENXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NON6BKWC7EPNXHRL26H7YCENXX/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":"2026-08-21T11:07:41Z","links":{"resolver":"https://pith.science/pith/NON6BKWC7EPNXHRL26H7YCENXX","bundle":"https://pith.science/pith/NON6BKWC7EPNXHRL26H7YCENXX/bundle.json","state":"https://pith.science/pith/NON6BKWC7EPNXHRL26H7YCENXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NON6BKWC7EPNXHRL26H7YCENXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NON6BKWC7EPNXHRL26H7YCENXX","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":"5a35486b3f5426d6ab057531a5a7fd4ace6c60868c80e1fd1d345d66e775b41b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T15:45:07Z","title_canon_sha256":"029a0adbd68a96080551e2d61048ef32b72abce1db8eb9a299c4790a25b831c5"},"schema_version":"1.0","source":{"id":"2106.16138","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.16138","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2106.16138v2","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.16138","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"NON6BKWC7EPN","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"NON6BKWC7EPNXHRL","created_at":"2026-07-05T04:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"NON6BKWC","created_at":"2026-07-05T04:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:606f8f7708ac5d9c76a4ec5dc6978cc74434ec1afe4980011a2dffbe0cd21759","target":"graph","created_at":"2026-07-05T04:15:43Z","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/2106.16138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides, we pretrain the model, named as XLM-E, on both multilingual and parallel corpora. Our model outperforms the baseline models on various cross-lingual understanding tasks with much less computation cost. Moreover, analysis shows that XLM-E tends to obtain better cross-lingual transferability.","authors_text":"Bo Zheng, Furu Wei, Heyan Huang, Li Dong, Payal Bajaj, Saksham Singhal, Shaohan Huang, Shuming Ma, Xian-Ling Mao, Xia Song, Zewen Chi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T15:45:07Z","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.16138","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":"sha256:3a1c6bdbbb0c9de0700e9731243dbb12b3d1d84640996e38a9806241fe48461c","target":"record","created_at":"2026-07-05T04:15:43Z","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":"5a35486b3f5426d6ab057531a5a7fd4ace6c60868c80e1fd1d345d66e775b41b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T15:45:07Z","title_canon_sha256":"029a0adbd68a96080551e2d61048ef32b72abce1db8eb9a299c4790a25b831c5"},"schema_version":"1.0","source":{"id":"2106.16138","kind":"arxiv","version":2}},"canonical_sha256":"6b9be0aac2f91edb9e2bd78ffc088dbdd6cb08af932907f09ea3fb3b41d4cc60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b9be0aac2f91edb9e2bd78ffc088dbdd6cb08af932907f09ea3fb3b41d4cc60","first_computed_at":"2026-07-05T04:15:43.503171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:43.503171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d4TxgmkSecaL3m03MjFuRpoOEzPY40yzaTbExqKUu/eyquos81DMBnvswLwyagvQEddvsJBTnlsgq6I9CGSVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:43.503663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.16138","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a1c6bdbbb0c9de0700e9731243dbb12b3d1d84640996e38a9806241fe48461c","sha256:606f8f7708ac5d9c76a4ec5dc6978cc74434ec1afe4980011a2dffbe0cd21759"],"state_sha256":"698c7b8f858576cb89294bac0db72f127f85d0408e3d2fd8907aa6f66cf20a06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQ6b8iVZAIvlYzZUFBmHDs5PPllIErj2pnhg2OD9ZMY7Q0iCFOZ9yubixA85gy0Ar6Ly2eJBHMqdh/4FjPFYDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T11:07:41.621544Z","bundle_sha256":"86aae7abc4f5ce072d8538a0af3819222a1d6c7c07819c2ed43fdbd73f310b84"}}