{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EKJLKDVDPT5XXIN55WJHBBYAPP","short_pith_number":"pith:EKJLKDVD","schema_version":"1.0","canonical_sha256":"2292b50ea37cfb7ba1bded927087007bc14f511026d7279f3af41fb326f491a8","source":{"kind":"arxiv","id":"2203.16169","version":1},"attestation_state":"computed","paper":{"title":"Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Elena \\'Alvarez-Mellado","submitted_at":"2022-03-30T09:46:51Z","abstract_excerpt":"This work presents a new resource for borrowing identification and analyzes the performance and errors of several models on this task. We introduce a new annotated corpus of Spanish newswire rich in unassimilated lexical borrowings -- words from one language that are introduced into another without orthographic adaptation -- and use it to evaluate how several sequence labeling models (CRF, BiLSTM-CRF, and Transformer-based models) perform. The corpus contains 370,000 tokens and is larger, more borrowing-dense, OOV-rich, and topic-varied than previous corpora available for this task. Our result"},"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":"2203.16169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T09:46:51Z","cross_cats_sorted":[],"title_canon_sha256":"ce809e5f3153452c4a4a09f04411189656ebbe8645feac7096f9479a73d982fc","abstract_canon_sha256":"247a984ab8f94a75c9ff1d439d82e604e2520b61a050dabdf330fbc85c81edc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:08.200408Z","signature_b64":"FiJ35QOi0SKjhuq3qnD/XrxzM+nXOgWN2aX6EDa/l+OMdZxbDzCtJ8o+wvi2cUw8MBLocsXwrxCws2avnlOaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2292b50ea37cfb7ba1bded927087007bc14f511026d7279f3af41fb326f491a8","last_reissued_at":"2026-07-05T04:10:08.200035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:08.200035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Elena \\'Alvarez-Mellado","submitted_at":"2022-03-30T09:46:51Z","abstract_excerpt":"This work presents a new resource for borrowing identification and analyzes the performance and errors of several models on this task. We introduce a new annotated corpus of Spanish newswire rich in unassimilated lexical borrowings -- words from one language that are introduced into another without orthographic adaptation -- and use it to evaluate how several sequence labeling models (CRF, BiLSTM-CRF, and Transformer-based models) perform. The corpus contains 370,000 tokens and is larger, more borrowing-dense, OOV-rich, and topic-varied than previous corpora available for this task. Our result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16169","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/2203.16169/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":"2203.16169","created_at":"2026-07-05T04:10:08.200096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16169v1","created_at":"2026-07-05T04:10:08.200096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16169","created_at":"2026-07-05T04:10:08.200096+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKJLKDVDPT5X","created_at":"2026-07-05T04:10:08.200096+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKJLKDVDPT5XXIN5","created_at":"2026-07-05T04:10:08.200096+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKJLKDVD","created_at":"2026-07-05T04:10:08.200096+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/EKJLKDVDPT5XXIN55WJHBBYAPP","json":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP.json","graph_json":"https://pith.science/api/pith-number/EKJLKDVDPT5XXIN55WJHBBYAPP/graph.json","events_json":"https://pith.science/api/pith-number/EKJLKDVDPT5XXIN55WJHBBYAPP/events.json","paper":"https://pith.science/paper/EKJLKDVD"},"agent_actions":{"view_html":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP","download_json":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP.json","view_paper":"https://pith.science/paper/EKJLKDVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16169&json=true","fetch_graph":"https://pith.science/api/pith-number/EKJLKDVDPT5XXIN55WJHBBYAPP/graph.json","fetch_events":"https://pith.science/api/pith-number/EKJLKDVDPT5XXIN55WJHBBYAPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP/action/storage_attestation","attest_author":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP/action/author_attestation","sign_citation":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP/action/citation_signature","submit_replication":"https://pith.science/pith/EKJLKDVDPT5XXIN55WJHBBYAPP/action/replication_record"}},"created_at":"2026-07-05T04:10:08.200096+00:00","updated_at":"2026-07-05T04:10:08.200096+00:00"}