{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5NL7BEX4EMTD4YM5SZHHS2QPEN","short_pith_number":"pith:5NL7BEX4","canonical_record":{"source":{"id":"2006.01538","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-02T11:57:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69f1ec4f8114d6962b25346efe063bc9c1e02d5d65185d9427dc46103d28978e","abstract_canon_sha256":"1f51d560123589b805bb80a7bc7166db94c1a22739e3be72dc11f0537afb726f"},"schema_version":"1.0"},"canonical_sha256":"eb57f092fc23263e619d964e796a0f23588c04342664c56283dd369e3c6820a6","source":{"kind":"arxiv","id":"2006.01538","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01538","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01538v1","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01538","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"pith_short_12","alias_value":"5NL7BEX4EMTD","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"pith_short_16","alias_value":"5NL7BEX4EMTD4YM5","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"pith_short_8","alias_value":"5NL7BEX4","created_at":"2026-07-05T01:07:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5NL7BEX4EMTD4YM5SZHHS2QPEN","target":"record","payload":{"canonical_record":{"source":{"id":"2006.01538","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-02T11:57:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69f1ec4f8114d6962b25346efe063bc9c1e02d5d65185d9427dc46103d28978e","abstract_canon_sha256":"1f51d560123589b805bb80a7bc7166db94c1a22739e3be72dc11f0537afb726f"},"schema_version":"1.0"},"canonical_sha256":"eb57f092fc23263e619d964e796a0f23588c04342664c56283dd369e3c6820a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:18.544110Z","signature_b64":"esPCKak9V+sIvEv4WZxOsJASOEsCw4ZtNerIs608xzSJ43wotI7PMbmTIB47xEJRuZurmh9O/+Sm/h0l+HjsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb57f092fc23263e619d964e796a0f23588c04342664c56283dd369e3c6820a6","last_reissued_at":"2026-07-05T01:07:18.543637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:18.543637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.01538","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":"2026-07-05T01:07:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K1tJeBW4uaB4NKABKDBPzNRXMfNCdcXwy1HEjY2mEgJup2FZxWy4WK68zQHOD0mIemga2G5Z9Z38vtaP0Yv8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:46:22.325857Z"},"content_sha256":"248f9a8b5317f0e7db518dcb7aebf84f6991d416e766b0a42669dcd7b55e8a39","schema_version":"1.0","event_id":"sha256:248f9a8b5317f0e7db518dcb7aebf84f6991d416e766b0a42669dcd7b55e8a39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5NL7BEX4EMTD4YM5SZHHS2QPEN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WikiBERT models: deep transfer learning for many languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Antti Virtanen, Filip Ginter, Jenna Kanerva, Sampo Pyysalo","submitted_at":"2020-06-02T11:57:53Z","abstract_excerpt":"Deep neural language models such as BERT have enabled substantial recent advances in many natural language processing tasks. Due to the effort and computational cost involved in their pre-training, language-specific models are typically introduced only for a small number of high-resource languages such as English. While multilingual models covering large numbers of languages are available, recent work suggests monolingual training can produce better models, and our understanding of the tradeoffs between mono- and multilingual training is incomplete. In this paper, we introduce a simple, fully "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01538","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/2006.01538/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":"2026-07-05T01:07:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PhNmbl3w9hKYLQGYC+zpb0r9S5FZxVu2mUaqUuhIiNSGIBBcC5QBkinKx1JxC/JSECc7liFtDC11Pe2tS/vJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:46:22.326457Z"},"content_sha256":"40c7f852da8c0e2ce6de6cb9e66733dc9ce9e11b02ae1479021c98db9584fb7d","schema_version":"1.0","event_id":"sha256:40c7f852da8c0e2ce6de6cb9e66733dc9ce9e11b02ae1479021c98db9584fb7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NL7BEX4EMTD4YM5SZHHS2QPEN/bundle.json","state_url":"https://pith.science/pith/5NL7BEX4EMTD4YM5SZHHS2QPEN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NL7BEX4EMTD4YM5SZHHS2QPEN/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":"2026-08-12T18:46:22Z","links":{"resolver":"https://pith.science/pith/5NL7BEX4EMTD4YM5SZHHS2QPEN","bundle":"https://pith.science/pith/5NL7BEX4EMTD4YM5SZHHS2QPEN/bundle.json","state":"https://pith.science/pith/5NL7BEX4EMTD4YM5SZHHS2QPEN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NL7BEX4EMTD4YM5SZHHS2QPEN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5NL7BEX4EMTD4YM5SZHHS2QPEN","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":"1f51d560123589b805bb80a7bc7166db94c1a22739e3be72dc11f0537afb726f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-02T11:57:53Z","title_canon_sha256":"69f1ec4f8114d6962b25346efe063bc9c1e02d5d65185d9427dc46103d28978e"},"schema_version":"1.0","source":{"id":"2006.01538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01538","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01538v1","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01538","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"pith_short_12","alias_value":"5NL7BEX4EMTD","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"pith_short_16","alias_value":"5NL7BEX4EMTD4YM5","created_at":"2026-07-05T01:07:18Z"},{"alias_kind":"pith_short_8","alias_value":"5NL7BEX4","created_at":"2026-07-05T01:07:18Z"}],"graph_snapshots":[{"event_id":"sha256:40c7f852da8c0e2ce6de6cb9e66733dc9ce9e11b02ae1479021c98db9584fb7d","target":"graph","created_at":"2026-07-05T01:07:18Z","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/2006.01538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural language models such as BERT have enabled substantial recent advances in many natural language processing tasks. Due to the effort and computational cost involved in their pre-training, language-specific models are typically introduced only for a small number of high-resource languages such as English. While multilingual models covering large numbers of languages are available, recent work suggests monolingual training can produce better models, and our understanding of the tradeoffs between mono- and multilingual training is incomplete. In this paper, we introduce a simple, fully ","authors_text":"Antti Virtanen, Filip Ginter, Jenna Kanerva, Sampo Pyysalo","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-02T11:57:53Z","title":"WikiBERT models: deep transfer learning for many languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01538","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":"sha256:248f9a8b5317f0e7db518dcb7aebf84f6991d416e766b0a42669dcd7b55e8a39","target":"record","created_at":"2026-07-05T01:07:18Z","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":"1f51d560123589b805bb80a7bc7166db94c1a22739e3be72dc11f0537afb726f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-02T11:57:53Z","title_canon_sha256":"69f1ec4f8114d6962b25346efe063bc9c1e02d5d65185d9427dc46103d28978e"},"schema_version":"1.0","source":{"id":"2006.01538","kind":"arxiv","version":1}},"canonical_sha256":"eb57f092fc23263e619d964e796a0f23588c04342664c56283dd369e3c6820a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb57f092fc23263e619d964e796a0f23588c04342664c56283dd369e3c6820a6","first_computed_at":"2026-07-05T01:07:18.543637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:18.543637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"esPCKak9V+sIvEv4WZxOsJASOEsCw4ZtNerIs608xzSJ43wotI7PMbmTIB47xEJRuZurmh9O/+Sm/h0l+HjsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:18.544110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.01538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:248f9a8b5317f0e7db518dcb7aebf84f6991d416e766b0a42669dcd7b55e8a39","sha256:40c7f852da8c0e2ce6de6cb9e66733dc9ce9e11b02ae1479021c98db9584fb7d"],"state_sha256":"813ee070a4a32dfe6acdfae4df6851a9cbc099ee4de8751fb22c2d824061b62b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6r7iYGpLggWbMppN6A0YIFo2UL1xKvDVHOxSEbHjDLzPlddP/jnWWYCR659Wf9vB8QthLPOhXR6j77BbPVRiCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:46:22.331518Z","bundle_sha256":"9b1938b8ce2333f0a2d78077ba835bb097ec6ac80b509457b1de14a56d950bbc"}}