{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:J5HIGFTERURRO6CKMPC5PGTUCZ","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":"da30d98c64a9feb2925f768dd4d2810a0c520104ce4d5859565a28141fea21e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T13:13:37Z","title_canon_sha256":"8b196ba1bc78e0645b70fdd48ced54d7f289a82290448618a111c300746a050a"},"schema_version":"1.0","source":{"id":"2608.04808","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04808","created_at":"2026-08-06T01:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04808v1","created_at":"2026-08-06T01:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04808","created_at":"2026-08-06T01:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"J5HIGFTERURR","created_at":"2026-08-06T01:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"J5HIGFTERURRO6CK","created_at":"2026-08-06T01:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"J5HIGFTE","created_at":"2026-08-06T01:47:16Z"}],"graph_snapshots":[{"event_id":"sha256:cf4e7c863638b6806ac2aa6cdd298b0104d35c0d288c7054c80c246936700fe6","target":"graph","created_at":"2026-08-06T01:47:16Z","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/2608.04808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Alistair Lawson, Peter J Barclay, Peter Stefan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T13:13:37Z","title":"A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04808","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":"sha256:0f5a466db11ca0bdd87529115d96612799fc624a72b4d5c05f40b2df97774b1b","target":"record","created_at":"2026-08-06T01:47:16Z","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":"da30d98c64a9feb2925f768dd4d2810a0c520104ce4d5859565a28141fea21e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T13:13:37Z","title_canon_sha256":"8b196ba1bc78e0645b70fdd48ced54d7f289a82290448618a111c300746a050a"},"schema_version":"1.0","source":{"id":"2608.04808","kind":"arxiv","version":1}},"canonical_sha256":"4f4e8316648d2317784a63c5d79a74166c232e28ed8a3df52d31df76ae3b4b30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f4e8316648d2317784a63c5d79a74166c232e28ed8a3df52d31df76ae3b4b30","first_computed_at":"2026-08-06T01:47:16.187737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:47:16.187737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bVVbe/Hd1F4WVU7C+SdlA7rQKE/N+ljxJZwpITkhjReqdFBzFO2hEfae33e8fleo80mLQBIGQW9ZJ/DnEkjdBw==","signature_status":"signed_v1","signed_at":"2026-08-06T01:47:16.189277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04808","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f5a466db11ca0bdd87529115d96612799fc624a72b4d5c05f40b2df97774b1b","sha256:cf4e7c863638b6806ac2aa6cdd298b0104d35c0d288c7054c80c246936700fe6"],"state_sha256":"547e993844ff9998de67ca5279fe0bd8d327a5bed669fbb4bf62f2cd9214be0b"}