{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LGKHQCE6XSMOYQ55IWXJQG5B2N","short_pith_number":"pith:LGKHQCE6","canonical_record":{"source":{"id":"2203.08430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:09:35Z","cross_cats_sorted":[],"title_canon_sha256":"2391cec94bbf0cf19a64e5e8a429740f5c4bbd6559b2d9d0d200bf78bf3c3377","abstract_canon_sha256":"bd08f82666d930b9968e3551913ca179d96beeee607749d026b9059500413d71"},"schema_version":"1.0"},"canonical_sha256":"599478089ebc98ec43bd45ae981ba1d37c89b08f154f8bc2eac1924ad9e5db4f","source":{"kind":"arxiv","id":"2203.08430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08430","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08430v1","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08430","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"LGKHQCE6XSMO","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"LGKHQCE6XSMOYQ55","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"LGKHQCE6","created_at":"2026-07-05T04:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LGKHQCE6XSMOYQ55IWXJQG5B2N","target":"record","payload":{"canonical_record":{"source":{"id":"2203.08430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:09:35Z","cross_cats_sorted":[],"title_canon_sha256":"2391cec94bbf0cf19a64e5e8a429740f5c4bbd6559b2d9d0d200bf78bf3c3377","abstract_canon_sha256":"bd08f82666d930b9968e3551913ca179d96beeee607749d026b9059500413d71"},"schema_version":"1.0"},"canonical_sha256":"599478089ebc98ec43bd45ae981ba1d37c89b08f154f8bc2eac1924ad9e5db4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:44.591377Z","signature_b64":"+OjXGh7u/0HQIQ63AGy5Udzc+7AJFMgkZmGR0wlsBcCIXfCjRnredoN9J7OlIjXRH3RqUvNb2nzq9M9G220sBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599478089ebc98ec43bd45ae981ba1d37c89b08f154f8bc2eac1924ad9e5db4f","last_reissued_at":"2026-07-05T04:05:44.590938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:44.590938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.08430","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":"2026-07-05T04:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUhEXatznD4NN16uXdS4d2U/mL/Uuh9q9QzuQnPSO50MKGnhcJJ9CVPWN4VGgO406zh0+mSeS4gYW59g+UUoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:44:54.548649Z"},"content_sha256":"fd406cb44a511cfe4f9663a545cd01c8fa40c3eda34bbcb3ee32f5cb838e56e9","schema_version":"1.0","event_id":"sha256:fd406cb44a511cfe4f9663a545cd01c8fa40c3eda34bbcb3ee32f5cb838e56e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LGKHQCE6XSMOYQ55IWXJQG5B2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nan Duan, Yaobo Liang, Yuan Chai","submitted_at":"2022-03-16T07:09:35Z","abstract_excerpt":"Multilingual pre-trained language models, such as mBERT and XLM-R, have shown impressive cross-lingual ability. Surprisingly, both of them use multilingual masked language model (MLM) without any cross-lingual supervision or aligned data. Despite the encouraging results, we still lack a clear understanding of why cross-lingual ability could emerge from multilingual MLM. In our work, we argue that cross-language ability comes from the commonality between languages. Specifically, we study three language properties: constituent order, composition and word co-occurrence. First, we create an artifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08430","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/2203.08430/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":"2026-07-05T04:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3+VuMeJf0Hb58mPSXjSb/XUT5WhvV1lcpXPwXDcbS3LJUd8DvqseGGuZbivw4tUuTZX4eZo7duLnxolv2rnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:44:54.549176Z"},"content_sha256":"af7107b41616ba3c3582ebae6cc4178444b5c28faa6418d48b57e7a10ee7286f","schema_version":"1.0","event_id":"sha256:af7107b41616ba3c3582ebae6cc4178444b5c28faa6418d48b57e7a10ee7286f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGKHQCE6XSMOYQ55IWXJQG5B2N/bundle.json","state_url":"https://pith.science/pith/LGKHQCE6XSMOYQ55IWXJQG5B2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGKHQCE6XSMOYQ55IWXJQG5B2N/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":"2026-08-21T11:44:54Z","links":{"resolver":"https://pith.science/pith/LGKHQCE6XSMOYQ55IWXJQG5B2N","bundle":"https://pith.science/pith/LGKHQCE6XSMOYQ55IWXJQG5B2N/bundle.json","state":"https://pith.science/pith/LGKHQCE6XSMOYQ55IWXJQG5B2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGKHQCE6XSMOYQ55IWXJQG5B2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LGKHQCE6XSMOYQ55IWXJQG5B2N","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":"bd08f82666d930b9968e3551913ca179d96beeee607749d026b9059500413d71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:09:35Z","title_canon_sha256":"2391cec94bbf0cf19a64e5e8a429740f5c4bbd6559b2d9d0d200bf78bf3c3377"},"schema_version":"1.0","source":{"id":"2203.08430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08430","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08430v1","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08430","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"LGKHQCE6XSMO","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"LGKHQCE6XSMOYQ55","created_at":"2026-07-05T04:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"LGKHQCE6","created_at":"2026-07-05T04:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:af7107b41616ba3c3582ebae6cc4178444b5c28faa6418d48b57e7a10ee7286f","target":"graph","created_at":"2026-07-05T04:05:44Z","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/2203.08430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual pre-trained language models, such as mBERT and XLM-R, have shown impressive cross-lingual ability. Surprisingly, both of them use multilingual masked language model (MLM) without any cross-lingual supervision or aligned data. Despite the encouraging results, we still lack a clear understanding of why cross-lingual ability could emerge from multilingual MLM. In our work, we argue that cross-language ability comes from the commonality between languages. Specifically, we study three language properties: constituent order, composition and word co-occurrence. First, we create an artifi","authors_text":"Nan Duan, Yaobo Liang, Yuan Chai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:09:35Z","title":"Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08430","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:fd406cb44a511cfe4f9663a545cd01c8fa40c3eda34bbcb3ee32f5cb838e56e9","target":"record","created_at":"2026-07-05T04:05:44Z","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":"bd08f82666d930b9968e3551913ca179d96beeee607749d026b9059500413d71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T07:09:35Z","title_canon_sha256":"2391cec94bbf0cf19a64e5e8a429740f5c4bbd6559b2d9d0d200bf78bf3c3377"},"schema_version":"1.0","source":{"id":"2203.08430","kind":"arxiv","version":1}},"canonical_sha256":"599478089ebc98ec43bd45ae981ba1d37c89b08f154f8bc2eac1924ad9e5db4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"599478089ebc98ec43bd45ae981ba1d37c89b08f154f8bc2eac1924ad9e5db4f","first_computed_at":"2026-07-05T04:05:44.590938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:44.590938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+OjXGh7u/0HQIQ63AGy5Udzc+7AJFMgkZmGR0wlsBcCIXfCjRnredoN9J7OlIjXRH3RqUvNb2nzq9M9G220sBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:44.591377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd406cb44a511cfe4f9663a545cd01c8fa40c3eda34bbcb3ee32f5cb838e56e9","sha256:af7107b41616ba3c3582ebae6cc4178444b5c28faa6418d48b57e7a10ee7286f"],"state_sha256":"5c042d78e1376a8307951b0c7cd13671fb14fb80da7fccaf5ed1dc7f2813cdc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CQ+oNC7GeBMCpoAbWjhFgtp0VbZAaHbGN9MpeWpOYntftXplR4LFQ8XfwsJ0EE+DlTMDLzvDhVJ7E6DagWeDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T11:44:54.554569Z","bundle_sha256":"cee835e0a0b3e4ca54c75fe92a2fdd564ff7c36bb938f103e3b0eda697485df7"}}