{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z7VUJ5FMEJCD3LDHHE6PYK72R5","short_pith_number":"pith:Z7VUJ5FM","canonical_record":{"source":{"id":"2005.09093","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T21:15:39Z","cross_cats_sorted":[],"title_canon_sha256":"195ac804656bd89c16b4c4de15ea98a4ac58e86b7b5b1a02b91a4a79f32917f9","abstract_canon_sha256":"7f002addcf35d32b6143f911a6f02f14be78a2828763473500b511250adb1126"},"schema_version":"1.0"},"canonical_sha256":"cfeb44f4ac22443dac67393cfc2bfa8f42f403bc8e8a2a9940df4edaf8c33f1e","source":{"kind":"arxiv","id":"2005.09093","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09093","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09093v2","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09093","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"pith_short_12","alias_value":"Z7VUJ5FMEJCD","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"pith_short_16","alias_value":"Z7VUJ5FMEJCD3LDH","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"pith_short_8","alias_value":"Z7VUJ5FM","created_at":"2026-07-05T01:39:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z7VUJ5FMEJCD3LDHHE6PYK72R5","target":"record","payload":{"canonical_record":{"source":{"id":"2005.09093","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T21:15:39Z","cross_cats_sorted":[],"title_canon_sha256":"195ac804656bd89c16b4c4de15ea98a4ac58e86b7b5b1a02b91a4a79f32917f9","abstract_canon_sha256":"7f002addcf35d32b6143f911a6f02f14be78a2828763473500b511250adb1126"},"schema_version":"1.0"},"canonical_sha256":"cfeb44f4ac22443dac67393cfc2bfa8f42f403bc8e8a2a9940df4edaf8c33f1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:26.784215Z","signature_b64":"0RiG6ZxS6HUc7fLbwRgLOb05B73jaucNZvekr0Xnz69C91Eog847/WDSXX9PQqfzF9J4uNonhSswjerDoCuyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfeb44f4ac22443dac67393cfc2bfa8f42f403bc8e8a2a9940df4edaf8c33f1e","last_reissued_at":"2026-07-05T01:39:26.783767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:26.783767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.09093","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":"2026-07-05T01:39:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUchxt/Ae5xr7sdkS4/mhlQZ7HjD4oGdr79Ar6LZO2/tcbKJJz5+Ou09wRKBasJA7OHAsmC6NjcT59P7LnSUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:03:14.033980Z"},"content_sha256":"e5f5c8ad2e2d3219c0af046b9d19c790b303e76cc1a4a056bf2d1d67d59eb832","schema_version":"1.0","event_id":"sha256:e5f5c8ad2e2d3219c0af046b9d19c790b303e76cc1a4a056bf2d1d67d59eb832"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z7VUJ5FMEJCD3LDHHE6PYK72R5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are All Languages Created Equal in Multilingual BERT?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mark Dredze, Shijie Wu","submitted_at":"2020-05-18T21:15:39Z","abstract_excerpt":"Multilingual BERT (mBERT) trained on 104 languages has shown surprisingly good cross-lingual performance on several NLP tasks, even without explicit cross-lingual signals. However, these evaluations have focused on cross-lingual transfer with high-resource languages, covering only a third of the languages covered by mBERT. We explore how mBERT performs on a much wider set of languages, focusing on the quality of representation for low-resource languages, measured by within-language performance. We consider three tasks: Named Entity Recognition (99 languages), Part-of-speech Tagging, and Depend"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09093","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/2005.09093/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":"2026-07-05T01:39:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zhg8I8odyY+Fd/283I01tmpSYjMvn3hyUyUMLQ/P7jtNA1Dr+CfNEKYbBf8bDosayeDFKNptT5QTH0Rm6ioEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:03:14.034478Z"},"content_sha256":"ea2826fe4fb328713be8fd3e250c5e3aa4664bb3e50bae356dad1704aa477b45","schema_version":"1.0","event_id":"sha256:ea2826fe4fb328713be8fd3e250c5e3aa4664bb3e50bae356dad1704aa477b45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z7VUJ5FMEJCD3LDHHE6PYK72R5/bundle.json","state_url":"https://pith.science/pith/Z7VUJ5FMEJCD3LDHHE6PYK72R5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z7VUJ5FMEJCD3LDHHE6PYK72R5/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":"2026-08-07T00:03:14Z","links":{"resolver":"https://pith.science/pith/Z7VUJ5FMEJCD3LDHHE6PYK72R5","bundle":"https://pith.science/pith/Z7VUJ5FMEJCD3LDHHE6PYK72R5/bundle.json","state":"https://pith.science/pith/Z7VUJ5FMEJCD3LDHHE6PYK72R5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z7VUJ5FMEJCD3LDHHE6PYK72R5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z7VUJ5FMEJCD3LDHHE6PYK72R5","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":"7f002addcf35d32b6143f911a6f02f14be78a2828763473500b511250adb1126","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T21:15:39Z","title_canon_sha256":"195ac804656bd89c16b4c4de15ea98a4ac58e86b7b5b1a02b91a4a79f32917f9"},"schema_version":"1.0","source":{"id":"2005.09093","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09093","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09093v2","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09093","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"pith_short_12","alias_value":"Z7VUJ5FMEJCD","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"pith_short_16","alias_value":"Z7VUJ5FMEJCD3LDH","created_at":"2026-07-05T01:39:26Z"},{"alias_kind":"pith_short_8","alias_value":"Z7VUJ5FM","created_at":"2026-07-05T01:39:26Z"}],"graph_snapshots":[{"event_id":"sha256:ea2826fe4fb328713be8fd3e250c5e3aa4664bb3e50bae356dad1704aa477b45","target":"graph","created_at":"2026-07-05T01:39:26Z","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/2005.09093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual BERT (mBERT) trained on 104 languages has shown surprisingly good cross-lingual performance on several NLP tasks, even without explicit cross-lingual signals. However, these evaluations have focused on cross-lingual transfer with high-resource languages, covering only a third of the languages covered by mBERT. We explore how mBERT performs on a much wider set of languages, focusing on the quality of representation for low-resource languages, measured by within-language performance. We consider three tasks: Named Entity Recognition (99 languages), Part-of-speech Tagging, and Depend","authors_text":"Mark Dredze, Shijie Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T21:15:39Z","title":"Are All Languages Created Equal in Multilingual BERT?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09093","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:e5f5c8ad2e2d3219c0af046b9d19c790b303e76cc1a4a056bf2d1d67d59eb832","target":"record","created_at":"2026-07-05T01:39:26Z","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":"7f002addcf35d32b6143f911a6f02f14be78a2828763473500b511250adb1126","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-18T21:15:39Z","title_canon_sha256":"195ac804656bd89c16b4c4de15ea98a4ac58e86b7b5b1a02b91a4a79f32917f9"},"schema_version":"1.0","source":{"id":"2005.09093","kind":"arxiv","version":2}},"canonical_sha256":"cfeb44f4ac22443dac67393cfc2bfa8f42f403bc8e8a2a9940df4edaf8c33f1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfeb44f4ac22443dac67393cfc2bfa8f42f403bc8e8a2a9940df4edaf8c33f1e","first_computed_at":"2026-07-05T01:39:26.783767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:26.783767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0RiG6ZxS6HUc7fLbwRgLOb05B73jaucNZvekr0Xnz69C91Eog847/WDSXX9PQqfzF9J4uNonhSswjerDoCuyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:26.784215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.09093","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5f5c8ad2e2d3219c0af046b9d19c790b303e76cc1a4a056bf2d1d67d59eb832","sha256:ea2826fe4fb328713be8fd3e250c5e3aa4664bb3e50bae356dad1704aa477b45"],"state_sha256":"a404edc2761748f162c497db24fb41c117aeab334a08cbac5f85f92698f12024"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIqZAySr+1gxP5GWryFprpOPjbd7iNUUH9zJOIkQbIhF4cTaO24lcngb/q4CmTvzKZSNyWjFHXOCjtZSnUK0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:03:14.038847Z","bundle_sha256":"f9d872f125745d34f3acec0fb57a3d9ac5933575a6e14c86d4488c9177774262"}}