{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VL56FHZXQHCGNPVE7M6ISW2775","short_pith_number":"pith:VL56FHZX","schema_version":"1.0","canonical_sha256":"aafbe29f3781c466bea4fb3c895b5fff5358b7022ff292bf67370fcb51a03ee0","source":{"kind":"arxiv","id":"1912.00991","version":1},"attestation_state":"computed","paper":{"title":"Morphological Tagging and Lemmatization of Albanian: A Manually Annotated Corpus and Neural Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ginter, Jenna Kanerva, Marenglen Biba, Nelda Kote, Samuel R\\\"onnqvist","submitted_at":"2019-12-02T18:50:37Z","abstract_excerpt":"In this paper, we present the first publicly available part-of-speech and morphologically tagged corpus for the Albanian language, as well as a neural morphological tagger and lemmatizer trained on it. There is currently a lack of available NLP resources for Albanian, and its complex grammar and morphology present challenges to their development. We have created an Albanian part-of-speech corpus based on the Universal Dependencies schema for morphological annotation, containing about 118,000 tokens of naturally occuring text collected from different text sources, with an addition of 67,000 tok"},"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":"1912.00991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-12-02T18:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"62452dff575cdb8b32e5964ee5c6bb413ebde7192d19a827ee6ff5b7715c7c18","abstract_canon_sha256":"51fda91bcd37fcfad2c8cf228ca6f79cfc4c0cef1b915e9da18c48e931c144d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:18.626982Z","signature_b64":"5Lh97bYXG1Qopm0ke3xZCGjrpO+x8r2gN+YUR8x6oOayB3oN4ycIu9rsgLsnLCD0BGpWvmOfCZRaIYSYdtdtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aafbe29f3781c466bea4fb3c895b5fff5358b7022ff292bf67370fcb51a03ee0","last_reissued_at":"2026-07-05T00:23:18.626538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:18.626538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Morphological Tagging and Lemmatization of Albanian: A Manually Annotated Corpus and Neural Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ginter, Jenna Kanerva, Marenglen Biba, Nelda Kote, Samuel R\\\"onnqvist","submitted_at":"2019-12-02T18:50:37Z","abstract_excerpt":"In this paper, we present the first publicly available part-of-speech and morphologically tagged corpus for the Albanian language, as well as a neural morphological tagger and lemmatizer trained on it. There is currently a lack of available NLP resources for Albanian, and its complex grammar and morphology present challenges to their development. We have created an Albanian part-of-speech corpus based on the Universal Dependencies schema for morphological annotation, containing about 118,000 tokens of naturally occuring text collected from different text sources, with an addition of 67,000 tok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00991","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/1912.00991/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":"1912.00991","created_at":"2026-07-05T00:23:18.626597+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00991v1","created_at":"2026-07-05T00:23:18.626597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00991","created_at":"2026-07-05T00:23:18.626597+00:00"},{"alias_kind":"pith_short_12","alias_value":"VL56FHZXQHCG","created_at":"2026-07-05T00:23:18.626597+00:00"},{"alias_kind":"pith_short_16","alias_value":"VL56FHZXQHCGNPVE","created_at":"2026-07-05T00:23:18.626597+00:00"},{"alias_kind":"pith_short_8","alias_value":"VL56FHZX","created_at":"2026-07-05T00:23:18.626597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775","json":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775.json","graph_json":"https://pith.science/api/pith-number/VL56FHZXQHCGNPVE7M6ISW2775/graph.json","events_json":"https://pith.science/api/pith-number/VL56FHZXQHCGNPVE7M6ISW2775/events.json","paper":"https://pith.science/paper/VL56FHZX"},"agent_actions":{"view_html":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775","download_json":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775.json","view_paper":"https://pith.science/paper/VL56FHZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00991&json=true","fetch_graph":"https://pith.science/api/pith-number/VL56FHZXQHCGNPVE7M6ISW2775/graph.json","fetch_events":"https://pith.science/api/pith-number/VL56FHZXQHCGNPVE7M6ISW2775/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775/action/storage_attestation","attest_author":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775/action/author_attestation","sign_citation":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775/action/citation_signature","submit_replication":"https://pith.science/pith/VL56FHZXQHCGNPVE7M6ISW2775/action/replication_record"}},"created_at":"2026-07-05T00:23:18.626597+00:00","updated_at":"2026-07-05T00:23:18.626597+00:00"}