{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EKJLKDVDPT5XXIN55WJHBBYAPP","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":"247a984ab8f94a75c9ff1d439d82e604e2520b61a050dabdf330fbc85c81edc8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T09:46:51Z","title_canon_sha256":"ce809e5f3153452c4a4a09f04411189656ebbe8645feac7096f9479a73d982fc"},"schema_version":"1.0","source":{"id":"2203.16169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16169","created_at":"2026-07-05T04:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16169v1","created_at":"2026-07-05T04:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16169","created_at":"2026-07-05T04:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"EKJLKDVDPT5X","created_at":"2026-07-05T04:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"EKJLKDVDPT5XXIN5","created_at":"2026-07-05T04:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"EKJLKDVD","created_at":"2026-07-05T04:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:4b77e3cee468ad5003562cad3c25964e683881f7e7486baf34bbde14baca409c","target":"graph","created_at":"2026-07-05T04:10:08Z","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/2203.16169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Constantine Lignos, Elena \\'Alvarez-Mellado","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T09:46:51Z","title":"Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16169","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:d1a2485385ba20f6099500d1a221da60943c61fbc94aee717af70cabed192479","target":"record","created_at":"2026-07-05T04:10:08Z","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":"247a984ab8f94a75c9ff1d439d82e604e2520b61a050dabdf330fbc85c81edc8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T09:46:51Z","title_canon_sha256":"ce809e5f3153452c4a4a09f04411189656ebbe8645feac7096f9479a73d982fc"},"schema_version":"1.0","source":{"id":"2203.16169","kind":"arxiv","version":1}},"canonical_sha256":"2292b50ea37cfb7ba1bded927087007bc14f511026d7279f3af41fb326f491a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2292b50ea37cfb7ba1bded927087007bc14f511026d7279f3af41fb326f491a8","first_computed_at":"2026-07-05T04:10:08.200035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:08.200035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FiJ35QOi0SKjhuq3qnD/XrxzM+nXOgWN2aX6EDa/l+OMdZxbDzCtJ8o+wvi2cUw8MBLocsXwrxCws2avnlOaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:08.200408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1a2485385ba20f6099500d1a221da60943c61fbc94aee717af70cabed192479","sha256:4b77e3cee468ad5003562cad3c25964e683881f7e7486baf34bbde14baca409c"],"state_sha256":"d8601702f6fd58ce96864ee4918ea14e3413380731483e6b977bd23b9de1f52e"}