{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CNXCIK3QHERX4IMHUNGEZ6WL7T","short_pith_number":"pith:CNXCIK3Q","schema_version":"1.0","canonical_sha256":"136e242b7039237e2187a34c4cfacbfccbee9f3083dd030e26184fbc5273dc63","source":{"kind":"arxiv","id":"1904.05953","version":1},"attestation_state":"computed","paper":{"title":"Strong Baselines for Complex Word Identification across Multiple Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alison Sneyd, Andreas Vlachos, Aneeq Ur Rehman, Daniel King, Elisabeth Fritzsch, Fernando Alva-Manchego, Pierre Finnimore","submitted_at":"2019-04-11T20:50:18Z","abstract_excerpt":"Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test in the same language) and cross-lingual (i.e. test in a language not seen during training). The best monolingual models relied on language-dependent features, which do not generalise in the cross-lingual setting, while the best cross-lingual model used neural networks with multi-task learning. In this paper, we present monolingual and cross-lingual CWI model"},"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":"1904.05953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-11T20:50:18Z","cross_cats_sorted":[],"title_canon_sha256":"71e5adeb641f844fd53848c97cbd18e0fa995f8164e2e3cc85ddf17fdd25458f","abstract_canon_sha256":"d70e6dbe23d8d5bc21efe048dfe6e427d565f3f68c5ac99374a7fa814f7a5f06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:44.657958Z","signature_b64":"d/HxYTJIS9za+GBBYQAWGkDa6Oq15kyaEetzTiBlRgalZYHE60jexe+fdw1MeLcQxxByp3ZbeUQ32l/K27YwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"136e242b7039237e2187a34c4cfacbfccbee9f3083dd030e26184fbc5273dc63","last_reissued_at":"2026-05-17T23:48:44.657192Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:44.657192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strong Baselines for Complex Word Identification across Multiple Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alison Sneyd, Andreas Vlachos, Aneeq Ur Rehman, Daniel King, Elisabeth Fritzsch, Fernando Alva-Manchego, Pierre Finnimore","submitted_at":"2019-04-11T20:50:18Z","abstract_excerpt":"Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test in the same language) and cross-lingual (i.e. test in a language not seen during training). The best monolingual models relied on language-dependent features, which do not generalise in the cross-lingual setting, while the best cross-lingual model used neural networks with multi-task learning. In this paper, we present monolingual and cross-lingual CWI model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05953","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":""},"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":"1904.05953","created_at":"2026-05-17T23:48:44.657259+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05953v1","created_at":"2026-05-17T23:48:44.657259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05953","created_at":"2026-05-17T23:48:44.657259+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNXCIK3QHERX","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNXCIK3QHERX4IMH","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNXCIK3Q","created_at":"2026-05-18T12:33:15.570797+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/CNXCIK3QHERX4IMHUNGEZ6WL7T","json":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T.json","graph_json":"https://pith.science/api/pith-number/CNXCIK3QHERX4IMHUNGEZ6WL7T/graph.json","events_json":"https://pith.science/api/pith-number/CNXCIK3QHERX4IMHUNGEZ6WL7T/events.json","paper":"https://pith.science/paper/CNXCIK3Q"},"agent_actions":{"view_html":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T","download_json":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T.json","view_paper":"https://pith.science/paper/CNXCIK3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05953&json=true","fetch_graph":"https://pith.science/api/pith-number/CNXCIK3QHERX4IMHUNGEZ6WL7T/graph.json","fetch_events":"https://pith.science/api/pith-number/CNXCIK3QHERX4IMHUNGEZ6WL7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T/action/storage_attestation","attest_author":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T/action/author_attestation","sign_citation":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T/action/citation_signature","submit_replication":"https://pith.science/pith/CNXCIK3QHERX4IMHUNGEZ6WL7T/action/replication_record"}},"created_at":"2026-05-17T23:48:44.657259+00:00","updated_at":"2026-05-17T23:48:44.657259+00:00"}