{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J5HIGFTERURRO6CKMPC5PGTUCZ","short_pith_number":"pith:J5HIGFTE","schema_version":"1.0","canonical_sha256":"4f4e8316648d2317784a63c5d79a74166c232e28ed8a3df52d31df76ae3b4b30","source":{"kind":"arxiv","id":"2608.04808","version":1},"attestation_state":"computed","paper":{"title":"A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alistair Lawson, Peter J Barclay, Peter Stefan","submitted_at":"2026-08-05T13:13:37Z","abstract_excerpt":"Part-of-speech tagging for low-resource languages remains challenging due to limited annotated data, especially for linguistically complex languages. Gaidhlig (Scottish Gaelic) is a morphologically rich and endangered language with limited digital resources, making it suitable for examining a lightweight language processing approach. This paper describes using the modular spaCy Natural Language Processing framework to build part-of-speech taggers for Gaidhlig using the Annotated Reference Corpus of Scottish Gaelic. We train two models with minimal pre-processing and configuration: one using a "},"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":"2608.04808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T13:13:37Z","cross_cats_sorted":[],"title_canon_sha256":"8b196ba1bc78e0645b70fdd48ced54d7f289a82290448618a111c300746a050a","abstract_canon_sha256":"da30d98c64a9feb2925f768dd4d2810a0c520104ce4d5859565a28141fea21e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:47:16.189277Z","signature_b64":"bVVbe/Hd1F4WVU7C+SdlA7rQKE/N+ljxJZwpITkhjReqdFBzFO2hEfae33e8fleo80mLQBIGQW9ZJ/DnEkjdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f4e8316648d2317784a63c5d79a74166c232e28ed8a3df52d31df76ae3b4b30","last_reissued_at":"2026-08-06T01:47:16.187737Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:47:16.187737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alistair Lawson, Peter J Barclay, Peter Stefan","submitted_at":"2026-08-05T13:13:37Z","abstract_excerpt":"Part-of-speech tagging for low-resource languages remains challenging due to limited annotated data, especially for linguistically complex languages. Gaidhlig (Scottish Gaelic) is a morphologically rich and endangered language with limited digital resources, making it suitable for examining a lightweight language processing approach. This paper describes using the modular spaCy Natural Language Processing framework to build part-of-speech taggers for Gaidhlig using the Annotated Reference Corpus of Scottish Gaelic. We train two models with minimal pre-processing and configuration: one using a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04808","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/2608.04808/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":"2608.04808","created_at":"2026-08-06T01:47:16.189639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04808v1","created_at":"2026-08-06T01:47:16.189639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04808","created_at":"2026-08-06T01:47:16.189639+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5HIGFTERURR","created_at":"2026-08-06T01:47:16.189639+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5HIGFTERURRO6CK","created_at":"2026-08-06T01:47:16.189639+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5HIGFTE","created_at":"2026-08-06T01:47:16.189639+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/J5HIGFTERURRO6CKMPC5PGTUCZ","json":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ.json","graph_json":"https://pith.science/api/pith-number/J5HIGFTERURRO6CKMPC5PGTUCZ/graph.json","events_json":"https://pith.science/api/pith-number/J5HIGFTERURRO6CKMPC5PGTUCZ/events.json","paper":"https://pith.science/paper/J5HIGFTE"},"agent_actions":{"view_html":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ","download_json":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ.json","view_paper":"https://pith.science/paper/J5HIGFTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04808&json=true","fetch_graph":"https://pith.science/api/pith-number/J5HIGFTERURRO6CKMPC5PGTUCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/J5HIGFTERURRO6CKMPC5PGTUCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ/action/storage_attestation","attest_author":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ/action/author_attestation","sign_citation":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ/action/citation_signature","submit_replication":"https://pith.science/pith/J5HIGFTERURRO6CKMPC5PGTUCZ/action/replication_record"}},"created_at":"2026-08-06T01:47:16.189639+00:00","updated_at":"2026-08-06T01:47:16.189639+00:00"}