{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GA2FTDXOZZORUTUK4F2MWZWEP3","short_pith_number":"pith:GA2FTDXO","canonical_record":{"source":{"id":"2006.07890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T12:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"790336e336e2c34158d74b6377360b54dffb2480fcc88101a485d96444d64893","abstract_canon_sha256":"9289c3625a8979141fa9278fc7ff49bc4806d36739aa23e25a6fe6f5a0b203e2"},"schema_version":"1.0"},"canonical_sha256":"3034598eeece5d1a4e8ae174cb66c47efdd87ea98d5fb8a8144fe2a26a16a492","source":{"kind":"arxiv","id":"2006.07890","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07890","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07890v1","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07890","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"GA2FTDXOZZOR","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"GA2FTDXOZZORUTUK","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"GA2FTDXO","created_at":"2026-07-05T04:27:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GA2FTDXOZZORUTUK4F2MWZWEP3","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T12:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"790336e336e2c34158d74b6377360b54dffb2480fcc88101a485d96444d64893","abstract_canon_sha256":"9289c3625a8979141fa9278fc7ff49bc4806d36739aa23e25a6fe6f5a0b203e2"},"schema_version":"1.0"},"canonical_sha256":"3034598eeece5d1a4e8ae174cb66c47efdd87ea98d5fb8a8144fe2a26a16a492","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:41.185585Z","signature_b64":"JlzT9goMcPLP7SOmn9O+svBytkug6kgXTvUqPZM+HS8gPJ+QQImLUPdXjQyOrfyJ7pfOHeqdRhTi4H/jElY8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3034598eeece5d1a4e8ae174cb66c47efdd87ea98d5fb8a8144fe2a26a16a492","last_reissued_at":"2026-07-05T04:27:41.185109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:41.185109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07890","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":"2026-07-05T04:27:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTizsycsJNd9R2B5XeGzGJxEIcNDsBb/GPjGJNnAuWSwaih8q7T4PySPGfJhjVWYbjy+vc+W12Qhr2qj51SBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:03:52.477987Z"},"content_sha256":"73d8c462bf114dc80fa57ef9ea0aa2b020c0111baf6db0c4c7db2fa7615bfc75","schema_version":"1.0","event_id":"sha256:73d8c462bf114dc80fa57ef9ea0aa2b020c0111baf6db0c4c7db2fa7615bfc75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GA2FTDXOZZORUTUK4F2MWZWEP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FinEst BERT and CroSloEngual BERT: less is more in multilingual models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marko Robnik-\\v{S}ikonja, Matej Ul\\v{c}ar","submitted_at":"2020-06-14T12:54:01Z","abstract_excerpt":"Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. The research has been mostly focused on English language, though. While massively multilingual models exist, studies have shown that monolingual models produce much better results. We train two trilingual BERT-like models, one for Finnish, Estonian, and English, the other for Croatian, Slovenian, and English. We evaluate their performance on several downstream tasks, NER, POS-tagging, and dependency parsing, using the multilingual BERT and XLM-R as baselines. The newly created FinEst BERT and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07890","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/2006.07890/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":"2026-07-05T04:27:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EK1h6LZ4KfCd18ZhmjXANMBd1IQDuxtqmnle6YEHx8poTGryfWqbZRXie6/+YV2zvkdOdCxJzVGLEfht1aF+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T09:03:52.478365Z"},"content_sha256":"ce62ae0c6adeff0baa444fcc70392ce82e2b1cddd22f1d34fc87f2a6b4fda1c5","schema_version":"1.0","event_id":"sha256:ce62ae0c6adeff0baa444fcc70392ce82e2b1cddd22f1d34fc87f2a6b4fda1c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GA2FTDXOZZORUTUK4F2MWZWEP3/bundle.json","state_url":"https://pith.science/pith/GA2FTDXOZZORUTUK4F2MWZWEP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GA2FTDXOZZORUTUK4F2MWZWEP3/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":"2026-07-05T09:03:52Z","links":{"resolver":"https://pith.science/pith/GA2FTDXOZZORUTUK4F2MWZWEP3","bundle":"https://pith.science/pith/GA2FTDXOZZORUTUK4F2MWZWEP3/bundle.json","state":"https://pith.science/pith/GA2FTDXOZZORUTUK4F2MWZWEP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GA2FTDXOZZORUTUK4F2MWZWEP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GA2FTDXOZZORUTUK4F2MWZWEP3","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":"9289c3625a8979141fa9278fc7ff49bc4806d36739aa23e25a6fe6f5a0b203e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T12:54:01Z","title_canon_sha256":"790336e336e2c34158d74b6377360b54dffb2480fcc88101a485d96444d64893"},"schema_version":"1.0","source":{"id":"2006.07890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07890","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07890v1","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07890","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"GA2FTDXOZZOR","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"GA2FTDXOZZORUTUK","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"GA2FTDXO","created_at":"2026-07-05T04:27:41Z"}],"graph_snapshots":[{"event_id":"sha256:ce62ae0c6adeff0baa444fcc70392ce82e2b1cddd22f1d34fc87f2a6b4fda1c5","target":"graph","created_at":"2026-07-05T04:27:41Z","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/2006.07890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. The research has been mostly focused on English language, though. While massively multilingual models exist, studies have shown that monolingual models produce much better results. We train two trilingual BERT-like models, one for Finnish, Estonian, and English, the other for Croatian, Slovenian, and English. We evaluate their performance on several downstream tasks, NER, POS-tagging, and dependency parsing, using the multilingual BERT and XLM-R as baselines. The newly created FinEst BERT and ","authors_text":"Marko Robnik-\\v{S}ikonja, Matej Ul\\v{c}ar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T12:54:01Z","title":"FinEst BERT and CroSloEngual BERT: less is more in multilingual models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07890","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":"sha256:73d8c462bf114dc80fa57ef9ea0aa2b020c0111baf6db0c4c7db2fa7615bfc75","target":"record","created_at":"2026-07-05T04:27:41Z","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":"9289c3625a8979141fa9278fc7ff49bc4806d36739aa23e25a6fe6f5a0b203e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-14T12:54:01Z","title_canon_sha256":"790336e336e2c34158d74b6377360b54dffb2480fcc88101a485d96444d64893"},"schema_version":"1.0","source":{"id":"2006.07890","kind":"arxiv","version":1}},"canonical_sha256":"3034598eeece5d1a4e8ae174cb66c47efdd87ea98d5fb8a8144fe2a26a16a492","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3034598eeece5d1a4e8ae174cb66c47efdd87ea98d5fb8a8144fe2a26a16a492","first_computed_at":"2026-07-05T04:27:41.185109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:41.185109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JlzT9goMcPLP7SOmn9O+svBytkug6kgXTvUqPZM+HS8gPJ+QQImLUPdXjQyOrfyJ7pfOHeqdRhTi4H/jElY8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:41.185585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d8c462bf114dc80fa57ef9ea0aa2b020c0111baf6db0c4c7db2fa7615bfc75","sha256:ce62ae0c6adeff0baa444fcc70392ce82e2b1cddd22f1d34fc87f2a6b4fda1c5"],"state_sha256":"0cc6fd9090f2476427a32f996e43ae2cc6b30142c2891e60bb909507d197305b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zy5aOAYDwL+e1WovyDMWaKZ3A2ggg+MPKQXCMpbXfsuYT8ARDrOuaFwlEVSuB41/bbmOrg7c0gcXEiC/VEsyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T09:03:52.480237Z","bundle_sha256":"eac7e66c18a3f21d052e4f010959d0bae7e61ab98e61f97c75b1a6a391bc2008"}}