{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2EQIB4NZ6H4C2VCVRD5X7PFXTJ","short_pith_number":"pith:2EQIB4NZ","schema_version":"1.0","canonical_sha256":"d12080f1b9f1f82d545588fb7fbcb79a7364b7c12d8f6c712a5e2c39107a42d7","source":{"kind":"arxiv","id":"2304.09805","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Corpora for Germanic Low-Resource Languages and Dialects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Hinrich Sch\\\"utze, Verena Blaschke","submitted_at":"2023-04-19T16:45:16Z","abstract_excerpt":"Despite much progress in recent years, the vast majority of work in natural language processing (NLP) is on standard languages with many speakers. In this work, we instead focus on low-resource languages and in particular non-standardized low-resource languages. Even within branches of major language families, often considered well-researched, little is known about the extent and type of available resources and what the major NLP challenges are for these language varieties. The first step to address this situation is a systematic survey of available corpora (most importantly, annotated corpora"},"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":"2304.09805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T16:45:16Z","cross_cats_sorted":[],"title_canon_sha256":"de63a6c5840b5e5ede2a60b6a999c6c97859e6d500321eef787ce3d9b7c29b40","abstract_canon_sha256":"9f34484bee87d25015363ec92553ea727937bd58a5f0e261a7b5d606591f7b05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:42.620879Z","signature_b64":"C32iJXnuqoalD4f36r9b4G399rgy7ZxBOw66SmSxOjretg5V4i+Y/dhsWsqitu9n4fhybD5OqIjcCVgs9bXlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d12080f1b9f1f82d545588fb7fbcb79a7364b7c12d8f6c712a5e2c39107a42d7","last_reissued_at":"2026-07-05T06:02:42.620462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:42.620462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Corpora for Germanic Low-Resource Languages and Dialects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Hinrich Sch\\\"utze, Verena Blaschke","submitted_at":"2023-04-19T16:45:16Z","abstract_excerpt":"Despite much progress in recent years, the vast majority of work in natural language processing (NLP) is on standard languages with many speakers. In this work, we instead focus on low-resource languages and in particular non-standardized low-resource languages. Even within branches of major language families, often considered well-researched, little is known about the extent and type of available resources and what the major NLP challenges are for these language varieties. The first step to address this situation is a systematic survey of available corpora (most importantly, annotated corpora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09805","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/2304.09805/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":"2304.09805","created_at":"2026-07-05T06:02:42.620518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09805v1","created_at":"2026-07-05T06:02:42.620518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09805","created_at":"2026-07-05T06:02:42.620518+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EQIB4NZ6H4C","created_at":"2026-07-05T06:02:42.620518+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EQIB4NZ6H4C2VCV","created_at":"2026-07-05T06:02:42.620518+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EQIB4NZ","created_at":"2026-07-05T06:02:42.620518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09943","citing_title":"Indigenous Languages Spoken in Argentina: A Survey of NLP and Speech Resources","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ","json":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ.json","graph_json":"https://pith.science/api/pith-number/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/graph.json","events_json":"https://pith.science/api/pith-number/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/events.json","paper":"https://pith.science/paper/2EQIB4NZ"},"agent_actions":{"view_html":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ","download_json":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ.json","view_paper":"https://pith.science/paper/2EQIB4NZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09805&json=true","fetch_graph":"https://pith.science/api/pith-number/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/action/storage_attestation","attest_author":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/action/author_attestation","sign_citation":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/action/citation_signature","submit_replication":"https://pith.science/pith/2EQIB4NZ6H4C2VCVRD5X7PFXTJ/action/replication_record"}},"created_at":"2026-07-05T06:02:42.620518+00:00","updated_at":"2026-07-05T06:02:42.620518+00:00"}