{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BUKG234NU5C2FBFIHEGHEGXV74","short_pith_number":"pith:BUKG234N","canonical_record":{"source":{"id":"1911.01464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-04T19:41:13Z","cross_cats_sorted":[],"title_canon_sha256":"ffa57ba40dc815754fe31ea283da4940a056e9e1a547c83be195cbd747667c6e","abstract_canon_sha256":"9593d9ee21a7827d516b0b6943d8434cb75dd7377fdc226767f4e6b903cfb272"},"schema_version":"1.0"},"canonical_sha256":"0d146d6f8da745a284a8390c721af5ff107dc5e564258a04d412715a64af69a1","source":{"kind":"arxiv","id":"1911.01464","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.01464","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"1911.01464v3","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.01464","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"BUKG234NU5C2","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"pith_short_16","alias_value":"BUKG234NU5C2FBFI","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"pith_short_8","alias_value":"BUKG234N","created_at":"2026-07-05T01:01:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BUKG234NU5C2FBFIHEGHEGXV74","target":"record","payload":{"canonical_record":{"source":{"id":"1911.01464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-04T19:41:13Z","cross_cats_sorted":[],"title_canon_sha256":"ffa57ba40dc815754fe31ea283da4940a056e9e1a547c83be195cbd747667c6e","abstract_canon_sha256":"9593d9ee21a7827d516b0b6943d8434cb75dd7377fdc226767f4e6b903cfb272"},"schema_version":"1.0"},"canonical_sha256":"0d146d6f8da745a284a8390c721af5ff107dc5e564258a04d412715a64af69a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:21.426978Z","signature_b64":"62AQymTJXmQ3t3pufnOnVUlOvgsHilaQWIjitARmMXZ/uuUyvnS3fh4gGZz4LETI429jXDqS376B6tI8hhFUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d146d6f8da745a284a8390c721af5ff107dc5e564258a04d412715a64af69a1","last_reissued_at":"2026-07-05T01:01:21.426564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:21.426564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.01464","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":"2026-07-05T01:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3O1tW2r5cFhFooXNpFMkjuw8pMtv/JLjePi49Tj276Xqee56idlp4+UFbR03VOPGxLfUkiVNptGujU7fenJEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:16:42.536045Z"},"content_sha256":"92fa00e5b6a86940dde45a9f723b9746dc60e1f63e6083b78906ea036f7e6fd0","schema_version":"1.0","event_id":"sha256:92fa00e5b6a86940dde45a9f723b9746dc60e1f63e6083b78906ea036f7e6fd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BUKG234NU5C2FBFIHEGHEGXV74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emerging Cross-lingual Structure in Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Haoran Li, Luke Zettlemoyer, Shijie Wu, Veselin Stoyanov","submitted_at":"2019-11-04T19:41:13Z","abstract_excerpt":"We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so effective for cross-lingual transfer. We show, contrary to what was previously hypothesized, that transfer is possible even when there is no shared vocabulary across the monolingual corpora and also when the text comes from very different domains. The only requirement is that there are some shared parameters in the top layers of the multi-lingual encoder. To better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.01464","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/1911.01464/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":"2026-07-05T01:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XafJOL2rCHrphsQZRGbgI55g8gE6gETRHpTWQBG5C9fVX+5Vk/aZE1hYaDa4Icob3evaPuLWWuharxq5cKJYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:16:42.536940Z"},"content_sha256":"3de4e11f9115a8b04f59552ee2f021efc56b1841698d4bd30a98cb1f09ef5ae2","schema_version":"1.0","event_id":"sha256:3de4e11f9115a8b04f59552ee2f021efc56b1841698d4bd30a98cb1f09ef5ae2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUKG234NU5C2FBFIHEGHEGXV74/bundle.json","state_url":"https://pith.science/pith/BUKG234NU5C2FBFIHEGHEGXV74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUKG234NU5C2FBFIHEGHEGXV74/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":"2026-08-18T12:16:42Z","links":{"resolver":"https://pith.science/pith/BUKG234NU5C2FBFIHEGHEGXV74","bundle":"https://pith.science/pith/BUKG234NU5C2FBFIHEGHEGXV74/bundle.json","state":"https://pith.science/pith/BUKG234NU5C2FBFIHEGHEGXV74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUKG234NU5C2FBFIHEGHEGXV74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BUKG234NU5C2FBFIHEGHEGXV74","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":"9593d9ee21a7827d516b0b6943d8434cb75dd7377fdc226767f4e6b903cfb272","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-04T19:41:13Z","title_canon_sha256":"ffa57ba40dc815754fe31ea283da4940a056e9e1a547c83be195cbd747667c6e"},"schema_version":"1.0","source":{"id":"1911.01464","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.01464","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"1911.01464v3","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.01464","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"BUKG234NU5C2","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"pith_short_16","alias_value":"BUKG234NU5C2FBFI","created_at":"2026-07-05T01:01:21Z"},{"alias_kind":"pith_short_8","alias_value":"BUKG234N","created_at":"2026-07-05T01:01:21Z"}],"graph_snapshots":[{"event_id":"sha256:3de4e11f9115a8b04f59552ee2f021efc56b1841698d4bd30a98cb1f09ef5ae2","target":"graph","created_at":"2026-07-05T01:01:21Z","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/1911.01464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so effective for cross-lingual transfer. We show, contrary to what was previously hypothesized, that transfer is possible even when there is no shared vocabulary across the monolingual corpora and also when the text comes from very different domains. The only requirement is that there are some shared parameters in the top layers of the multi-lingual encoder. To better ","authors_text":"Alexis Conneau, Haoran Li, Luke Zettlemoyer, Shijie Wu, Veselin Stoyanov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-04T19:41:13Z","title":"Emerging Cross-lingual Structure in Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.01464","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":"sha256:92fa00e5b6a86940dde45a9f723b9746dc60e1f63e6083b78906ea036f7e6fd0","target":"record","created_at":"2026-07-05T01:01:21Z","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":"9593d9ee21a7827d516b0b6943d8434cb75dd7377fdc226767f4e6b903cfb272","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-04T19:41:13Z","title_canon_sha256":"ffa57ba40dc815754fe31ea283da4940a056e9e1a547c83be195cbd747667c6e"},"schema_version":"1.0","source":{"id":"1911.01464","kind":"arxiv","version":3}},"canonical_sha256":"0d146d6f8da745a284a8390c721af5ff107dc5e564258a04d412715a64af69a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d146d6f8da745a284a8390c721af5ff107dc5e564258a04d412715a64af69a1","first_computed_at":"2026-07-05T01:01:21.426564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:01:21.426564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"62AQymTJXmQ3t3pufnOnVUlOvgsHilaQWIjitARmMXZ/uuUyvnS3fh4gGZz4LETI429jXDqS376B6tI8hhFUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:01:21.426978Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.01464","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92fa00e5b6a86940dde45a9f723b9746dc60e1f63e6083b78906ea036f7e6fd0","sha256:3de4e11f9115a8b04f59552ee2f021efc56b1841698d4bd30a98cb1f09ef5ae2"],"state_sha256":"31e2fb0fa4bc710d9facc81edeb23e913143321ef2175ac559abcc7f9dbfdaa8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RK4mKIDVydNhUXrsgHaiL2FCBbB566CobpdZm0TWrW/0I0RH6PmjNA7Y6fyeysmd1AGk9fqs+/BqciQxDtPAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:16:42.543264Z","bundle_sha256":"73bb8a84e7175975079c3366e4df789ea7393cde779dc306e6254a1e0e4093f3"}}