{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z4NICC7FKJ6OHLQ7EGF4AQNOQZ","short_pith_number":"pith:Z4NICC7F","canonical_record":{"source":{"id":"2005.00396","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T14:27:14Z","cross_cats_sorted":[],"title_canon_sha256":"4315d4f9ce562bc1561f7c2237538918c9ec965da07a41d9598ec8182a0ea9a5","abstract_canon_sha256":"b2c937565796b9ae3a85576c1dc7fc289db8d555063337a0b529e7dcb3011761"},"schema_version":"1.0"},"canonical_sha256":"cf1a810be5527ce3ae1f218bc041ae86569e33bf609325197413149e1ecc5b15","source":{"kind":"arxiv","id":"2005.00396","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00396","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00396v3","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00396","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z4NICC7FKJ6O","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"Z4NICC7FKJ6OHLQ7","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"Z4NICC7F","created_at":"2026-07-05T02:13:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z4NICC7FKJ6OHLQ7EGF4AQNOQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00396","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T14:27:14Z","cross_cats_sorted":[],"title_canon_sha256":"4315d4f9ce562bc1561f7c2237538918c9ec965da07a41d9598ec8182a0ea9a5","abstract_canon_sha256":"b2c937565796b9ae3a85576c1dc7fc289db8d555063337a0b529e7dcb3011761"},"schema_version":"1.0"},"canonical_sha256":"cf1a810be5527ce3ae1f218bc041ae86569e33bf609325197413149e1ecc5b15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:14.201592Z","signature_b64":"0bswrw9wakupMekICURgtBhr5L5EVD8+fR15A2DEZ92sMPkPwowyuUg2cgseNzfDbBPR/ikX3MfNM5rLF+y8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf1a810be5527ce3ae1f218bc041ae86569e33bf609325197413149e1ecc5b15","last_reissued_at":"2026-07-05T02:13:14.201244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:14.201244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00396","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":"2026-07-05T02:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nX86UKa/pZyio9RsrznRYvBtn9jdndXX2+41n15wQY3GI1V2ScDWeEAbQI93kig82oifXA4elJLGO74kdAvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:35:19.143945Z"},"content_sha256":"f5d0ea145b6f2369071a4003f3e55d1001a42137935e6f1710b0a9cd6cbaa776","schema_version":"1.0","event_id":"sha256:f5d0ea145b6f2369071a4003f3e55d1001a42137935e6f1710b0a9cd6cbaa776"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z4NICC7FKJ6OHLQ7EGF4AQNOQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying Necessary Elements for BERT's Multilinguality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Philipp Dufter","submitted_at":"2020-05-01T14:27:14Z","abstract_excerpt":"It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during training. While recent literature has studied this phenomenon, the reasons for the multilinguality are still somewhat obscure. We aim to identify architectural properties of BERT and linguistic properties of languages that are necessary for BERT to become multilingual. To allow for fast experimentation we propose an efficient setup with small BERT models trained on a mix of syn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00396","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/2005.00396/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":"2026-07-05T02:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kDFCmu7uvaEGrVu2m0+dRoEZnFDuaBQUNdSf8J3V8JHfF8f/xOa4YhiYlFAQ5dIhU/3pNRBWslcY8kf1TY9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:35:19.144827Z"},"content_sha256":"6de5c4ee85fd34c0af78fb6f3ce763659b4235aca547400713012e54db166841","schema_version":"1.0","event_id":"sha256:6de5c4ee85fd34c0af78fb6f3ce763659b4235aca547400713012e54db166841"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4NICC7FKJ6OHLQ7EGF4AQNOQZ/bundle.json","state_url":"https://pith.science/pith/Z4NICC7FKJ6OHLQ7EGF4AQNOQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4NICC7FKJ6OHLQ7EGF4AQNOQZ/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":"2026-08-18T19:35:19Z","links":{"resolver":"https://pith.science/pith/Z4NICC7FKJ6OHLQ7EGF4AQNOQZ","bundle":"https://pith.science/pith/Z4NICC7FKJ6OHLQ7EGF4AQNOQZ/bundle.json","state":"https://pith.science/pith/Z4NICC7FKJ6OHLQ7EGF4AQNOQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4NICC7FKJ6OHLQ7EGF4AQNOQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z4NICC7FKJ6OHLQ7EGF4AQNOQZ","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":"b2c937565796b9ae3a85576c1dc7fc289db8d555063337a0b529e7dcb3011761","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T14:27:14Z","title_canon_sha256":"4315d4f9ce562bc1561f7c2237538918c9ec965da07a41d9598ec8182a0ea9a5"},"schema_version":"1.0","source":{"id":"2005.00396","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00396","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00396v3","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00396","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z4NICC7FKJ6O","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"Z4NICC7FKJ6OHLQ7","created_at":"2026-07-05T02:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"Z4NICC7F","created_at":"2026-07-05T02:13:14Z"}],"graph_snapshots":[{"event_id":"sha256:6de5c4ee85fd34c0af78fb6f3ce763659b4235aca547400713012e54db166841","target":"graph","created_at":"2026-07-05T02:13:14Z","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/2005.00396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during training. While recent literature has studied this phenomenon, the reasons for the multilinguality are still somewhat obscure. We aim to identify architectural properties of BERT and linguistic properties of languages that are necessary for BERT to become multilingual. To allow for fast experimentation we propose an efficient setup with small BERT models trained on a mix of syn","authors_text":"Hinrich Sch\\\"utze, Philipp Dufter","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T14:27:14Z","title":"Identifying Necessary Elements for BERT's Multilinguality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00396","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:f5d0ea145b6f2369071a4003f3e55d1001a42137935e6f1710b0a9cd6cbaa776","target":"record","created_at":"2026-07-05T02:13:14Z","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":"b2c937565796b9ae3a85576c1dc7fc289db8d555063337a0b529e7dcb3011761","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T14:27:14Z","title_canon_sha256":"4315d4f9ce562bc1561f7c2237538918c9ec965da07a41d9598ec8182a0ea9a5"},"schema_version":"1.0","source":{"id":"2005.00396","kind":"arxiv","version":3}},"canonical_sha256":"cf1a810be5527ce3ae1f218bc041ae86569e33bf609325197413149e1ecc5b15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf1a810be5527ce3ae1f218bc041ae86569e33bf609325197413149e1ecc5b15","first_computed_at":"2026-07-05T02:13:14.201244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:14.201244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0bswrw9wakupMekICURgtBhr5L5EVD8+fR15A2DEZ92sMPkPwowyuUg2cgseNzfDbBPR/ikX3MfNM5rLF+y8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:14.201592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00396","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5d0ea145b6f2369071a4003f3e55d1001a42137935e6f1710b0a9cd6cbaa776","sha256:6de5c4ee85fd34c0af78fb6f3ce763659b4235aca547400713012e54db166841"],"state_sha256":"b3f3aff4e34b936a16e6571ed90e12fb3886975c97ad665c19b4b24768ef3777"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ifKnZW3sxcrzhPyyT35HBbNs3wsiblVvoCFRicaE+B1qOGH368kEphPCcLFU8oUUkyGiMjiuIGw7qJafsK0CBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:35:19.148807Z","bundle_sha256":"89c8d096e9e03c8357717d4a88f580f50e2717facd3f5440312eb423e85ebb30"}}