{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JPLFITXZK7OXPQZNUPUVU266QG","short_pith_number":"pith:JPLFITXZ","schema_version":"1.0","canonical_sha256":"4bd6544ef957dd77c32da3e95a6bde81b27965b0a7ab8ad8d0f09d94af70e541","source":{"kind":"arxiv","id":"1912.07076","version":1},"attestation_state":"computed","paper":{"title":"Multilingual is not enough: BERT for Finnish","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antti Virtanen, Filip Ginter, Jenna Kanerva, Jouni Luoma, Juhani Luotolahti, Rami Ilo, Sampo Pyysalo, Tapio Salakoski","submitted_at":"2019-12-15T17:50:56Z","abstract_excerpt":"Deep learning-based language models pretrained on large unannotated text corpora have been demonstrated to allow efficient transfer learning for natural language processing, with recent approaches such as the transformer-based BERT model advancing the state of the art across a variety of tasks. While most work on these models has focused on high-resource languages, in particular English, a number of recent efforts have introduced multilingual models that can be fine-tuned to address tasks in a large number of different languages. However, we still lack a thorough understanding of the capabilit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.07076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-15T17:50:56Z","cross_cats_sorted":[],"title_canon_sha256":"2bca4b76beaec98b6220a56266066024e9125c6bbdc3c5ec9a957e2952c1d7aa","abstract_canon_sha256":"5467ad095bae79f164fea29f2b5719c113f1fb980a955723d1400f81279521e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:18.244812Z","signature_b64":"cLq/HdgTFtXeNYrovTK7zKba4oxM38eYYz3zBirr7sfMlcHBGaKA2ZilUAFArfs1tXZpfSGYTUFaM/F0mlJfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd6544ef957dd77c32da3e95a6bde81b27965b0a7ab8ad8d0f09d94af70e541","last_reissued_at":"2026-07-05T00:26:18.244339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:18.244339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual is not enough: BERT for Finnish","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antti Virtanen, Filip Ginter, Jenna Kanerva, Jouni Luoma, Juhani Luotolahti, Rami Ilo, Sampo Pyysalo, Tapio Salakoski","submitted_at":"2019-12-15T17:50:56Z","abstract_excerpt":"Deep learning-based language models pretrained on large unannotated text corpora have been demonstrated to allow efficient transfer learning for natural language processing, with recent approaches such as the transformer-based BERT model advancing the state of the art across a variety of tasks. While most work on these models has focused on high-resource languages, in particular English, a number of recent efforts have introduced multilingual models that can be fine-tuned to address tasks in a large number of different languages. However, we still lack a thorough understanding of the capabilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07076","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/1912.07076/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.07076","created_at":"2026-07-05T00:26:18.244399+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07076v1","created_at":"2026-07-05T00:26:18.244399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07076","created_at":"2026-07-05T00:26:18.244399+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPLFITXZK7OX","created_at":"2026-07-05T00:26:18.244399+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPLFITXZK7OXPQZN","created_at":"2026-07-05T00:26:18.244399+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPLFITXZ","created_at":"2026-07-05T00:26:18.244399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06738","citing_title":"Modular Monolingual Adaptation using Pretrained Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02100","citing_title":"PortBERT: Navigating the Depths of Portuguese Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14815","citing_title":"Domain Fine-Tuning FinBERT on Finnish Histopathological Reports: Train-Time Signals and Downstream Correlations","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG","json":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG.json","graph_json":"https://pith.science/api/pith-number/JPLFITXZK7OXPQZNUPUVU266QG/graph.json","events_json":"https://pith.science/api/pith-number/JPLFITXZK7OXPQZNUPUVU266QG/events.json","paper":"https://pith.science/paper/JPLFITXZ"},"agent_actions":{"view_html":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG","download_json":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG.json","view_paper":"https://pith.science/paper/JPLFITXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07076&json=true","fetch_graph":"https://pith.science/api/pith-number/JPLFITXZK7OXPQZNUPUVU266QG/graph.json","fetch_events":"https://pith.science/api/pith-number/JPLFITXZK7OXPQZNUPUVU266QG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG/action/storage_attestation","attest_author":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG/action/author_attestation","sign_citation":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG/action/citation_signature","submit_replication":"https://pith.science/pith/JPLFITXZK7OXPQZNUPUVU266QG/action/replication_record"}},"created_at":"2026-07-05T00:26:18.244399+00:00","updated_at":"2026-07-05T00:26:18.244399+00:00"}