{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7QFWEOWUINIYINDUGG2Y4UJC3H","short_pith_number":"pith:7QFWEOWU","schema_version":"1.0","canonical_sha256":"fc0b623ad4435184347431b58e5122d9c49430c677f3230baa7c9a71baf55789","source":{"kind":"arxiv","id":"1905.01852","version":1},"attestation_state":"computed","paper":{"title":"A Large Parallel Corpus of Full-Text Scientific Articles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Felipe Soares, Karin Becker, Viviane Pereira Moreira","submitted_at":"2019-05-06T07:33:00Z","abstract_excerpt":"The Scielo database is an important source of scientific information in Latin America, containing articles from several research domains. A striking characteristic of Scielo is that many of its full-text contents are presented in more than one language, thus being a potential source of parallel corpora. In this article, we present the development of a parallel corpus from Scielo in three languages: English, Portuguese, and Spanish. Sentences were automatically aligned using the Hunalign algorithm for all language pairs, and for a subset of trilingual articles also. We demonstrate the capabilit"},"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":"1905.01852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-06T07:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"124abeefe213eac76e93c5e70f8a8aed262dd060819a624036fabe37b0808bff","abstract_canon_sha256":"f86bbaeabb0a9d87c977ae93f4664ae38ce8d6a46bace740ecbcfe535d142447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:57.232577Z","signature_b64":"PmNKtCJv7qER4RzvSGVknBngi8ChhpP8MM+W4/nru3J9c66si936COOolunUKcHAUz+r82tSVxZ5Vn+vij3oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc0b623ad4435184347431b58e5122d9c49430c677f3230baa7c9a71baf55789","last_reissued_at":"2026-05-17T23:46:57.231785Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:57.231785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large Parallel Corpus of Full-Text Scientific Articles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Felipe Soares, Karin Becker, Viviane Pereira Moreira","submitted_at":"2019-05-06T07:33:00Z","abstract_excerpt":"The Scielo database is an important source of scientific information in Latin America, containing articles from several research domains. A striking characteristic of Scielo is that many of its full-text contents are presented in more than one language, thus being a potential source of parallel corpora. In this article, we present the development of a parallel corpus from Scielo in three languages: English, Portuguese, and Spanish. Sentences were automatically aligned using the Hunalign algorithm for all language pairs, and for a subset of trilingual articles also. We demonstrate the capabilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01852","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":"1905.01852","created_at":"2026-05-17T23:46:57.231913+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.01852v1","created_at":"2026-05-17T23:46:57.231913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01852","created_at":"2026-05-17T23:46:57.231913+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QFWEOWUINIY","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QFWEOWUINIYINDU","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QFWEOWU","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20912","citing_title":"Enhancing Scientific Discourse: Machine Translation for the Scientific Domain","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H","json":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H.json","graph_json":"https://pith.science/api/pith-number/7QFWEOWUINIYINDUGG2Y4UJC3H/graph.json","events_json":"https://pith.science/api/pith-number/7QFWEOWUINIYINDUGG2Y4UJC3H/events.json","paper":"https://pith.science/paper/7QFWEOWU"},"agent_actions":{"view_html":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H","download_json":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H.json","view_paper":"https://pith.science/paper/7QFWEOWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.01852&json=true","fetch_graph":"https://pith.science/api/pith-number/7QFWEOWUINIYINDUGG2Y4UJC3H/graph.json","fetch_events":"https://pith.science/api/pith-number/7QFWEOWUINIYINDUGG2Y4UJC3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/action/storage_attestation","attest_author":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/action/author_attestation","sign_citation":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/action/citation_signature","submit_replication":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/action/replication_record"}},"created_at":"2026-05-17T23:46:57.231913+00:00","updated_at":"2026-05-17T23:46:57.231913+00:00"}