{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:R4VEAUSQRTB4EPE5EW7NVSIG4U","short_pith_number":"pith:R4VEAUSQ","schema_version":"1.0","canonical_sha256":"8f2a4052508cc3c23c9d25bedac906e50a94a6a7e6ee7ca69e745c7f531a2538","source":{"kind":"arxiv","id":"2107.05295","version":1},"attestation_state":"computed","paper":{"title":"DaCy: A Unified Framework for Danish NLP","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kenneth Enevoldsen, Kristoffer Nielbo, Lasse Hansen","submitted_at":"2021-07-12T10:14:31Z","abstract_excerpt":"Danish natural language processing (NLP) has in recent years obtained considerable improvements with the addition of multiple new datasets and models. However, at present, there is no coherent framework for applying state-of-the-art models for Danish. We present DaCy: a unified framework for Danish NLP built on SpaCy. DaCy uses efficient multitask models which obtain state-of-the-art performance on named entity recognition, part-of-speech tagging, and dependency parsing. DaCy contains tools for easy integration of existing models such as for polarity, emotion, or subjectivity detection. In add"},"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":"2107.05295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-12T10:14:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d211818799c6e93cd02a796e0eeadb0c0584c33d9682ba53fbeedd30f60b69f5","abstract_canon_sha256":"18f5f99667c8586458faea073d31a12cb24a96fb9459fed2c0b307f5482a58a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:01.384308Z","signature_b64":"48W31Z/MMCyqPT0Ryz5Wj1pFXV/w2yXgBYNmh2yYA916eAH95Y13QWd7LmDZybOlH486mBWEt+Tapn+BBWe5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f2a4052508cc3c23c9d25bedac906e50a94a6a7e6ee7ca69e745c7f531a2538","last_reissued_at":"2026-07-05T02:57:01.383965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:01.383965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DaCy: A Unified Framework for Danish NLP","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kenneth Enevoldsen, Kristoffer Nielbo, Lasse Hansen","submitted_at":"2021-07-12T10:14:31Z","abstract_excerpt":"Danish natural language processing (NLP) has in recent years obtained considerable improvements with the addition of multiple new datasets and models. However, at present, there is no coherent framework for applying state-of-the-art models for Danish. We present DaCy: a unified framework for Danish NLP built on SpaCy. DaCy uses efficient multitask models which obtain state-of-the-art performance on named entity recognition, part-of-speech tagging, and dependency parsing. DaCy contains tools for easy integration of existing models such as for polarity, emotion, or subjectivity detection. In add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05295","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/2107.05295/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":"2107.05295","created_at":"2026-07-05T02:57:01.384027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.05295v1","created_at":"2026-07-05T02:57:01.384027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05295","created_at":"2026-07-05T02:57:01.384027+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4VEAUSQRTB4","created_at":"2026-07-05T02:57:01.384027+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4VEAUSQRTB4EPE5","created_at":"2026-07-05T02:57:01.384027+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4VEAUSQ","created_at":"2026-07-05T02:57:01.384027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12956","citing_title":"SnakModel: Lessons Learned from Training an Open Danish Large Language Model","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U","json":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U.json","graph_json":"https://pith.science/api/pith-number/R4VEAUSQRTB4EPE5EW7NVSIG4U/graph.json","events_json":"https://pith.science/api/pith-number/R4VEAUSQRTB4EPE5EW7NVSIG4U/events.json","paper":"https://pith.science/paper/R4VEAUSQ"},"agent_actions":{"view_html":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U","download_json":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U.json","view_paper":"https://pith.science/paper/R4VEAUSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.05295&json=true","fetch_graph":"https://pith.science/api/pith-number/R4VEAUSQRTB4EPE5EW7NVSIG4U/graph.json","fetch_events":"https://pith.science/api/pith-number/R4VEAUSQRTB4EPE5EW7NVSIG4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U/action/storage_attestation","attest_author":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U/action/author_attestation","sign_citation":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U/action/citation_signature","submit_replication":"https://pith.science/pith/R4VEAUSQRTB4EPE5EW7NVSIG4U/action/replication_record"}},"created_at":"2026-07-05T02:57:01.384027+00:00","updated_at":"2026-07-05T02:57:01.384027+00:00"}