{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7QFWEOWUINIYINDUGG2Y4UJC3H","short_pith_number":"pith:7QFWEOWU","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"},"canonical_sha256":"fc0b623ad4435184347431b58e5122d9c49430c677f3230baa7c9a71baf55789","source":{"kind":"arxiv","id":"1905.01852","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01852","created_at":"2026-05-17T23:46:57Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01852v1","created_at":"2026-05-17T23:46:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01852","created_at":"2026-05-17T23:46:57Z"},{"alias_kind":"pith_short_12","alias_value":"7QFWEOWUINIY","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7QFWEOWUINIYINDU","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7QFWEOWU","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7QFWEOWUINIYINDUGG2Y4UJC3H","target":"record","payload":{"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"},"canonical_sha256":"fc0b623ad4435184347431b58e5122d9c49430c677f3230baa7c9a71baf55789","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"},"source_kind":"arxiv","source_id":"1905.01852","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jeFuTvCePexo3mIVH6lkxQlCd5P3AIpGJL/+KCAcsoTSyVjzE28fuf49Zfh2Hz7jxbBnMcDFomh5I+4SE8nDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:26:29.210328Z"},"content_sha256":"5503bfa33d3cb9f3a53ba56e837c68d971f47cd9477aab5fb334d7ea2235f89c","schema_version":"1.0","event_id":"sha256:5503bfa33d3cb9f3a53ba56e837c68d971f47cd9477aab5fb334d7ea2235f89c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7QFWEOWUINIYINDUGG2Y4UJC3H","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+oJRfxFgbpnofRkOgJSoU5migr0B5BynuXVpxdXCM5Fbfg9xzb8a0co6bZVotuZZNA4xn7cxH1gk1x3RRxLsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:26:29.210770Z"},"content_sha256":"daac098cbdb613ee4ee82fde4a5f94cd8e4f602792feed7f7cf19f7fef028458","schema_version":"1.0","event_id":"sha256:daac098cbdb613ee4ee82fde4a5f94cd8e4f602792feed7f7cf19f7fef028458"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/bundle.json","state_url":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T00:26:29Z","links":{"resolver":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H","bundle":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/bundle.json","state":"https://pith.science/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QFWEOWUINIYINDUGG2Y4UJC3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7QFWEOWUINIYINDUGG2Y4UJC3H","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":"f86bbaeabb0a9d87c977ae93f4664ae38ce8d6a46bace740ecbcfe535d142447","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-06T07:33:00Z","title_canon_sha256":"124abeefe213eac76e93c5e70f8a8aed262dd060819a624036fabe37b0808bff"},"schema_version":"1.0","source":{"id":"1905.01852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01852","created_at":"2026-05-17T23:46:57Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01852v1","created_at":"2026-05-17T23:46:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01852","created_at":"2026-05-17T23:46:57Z"},{"alias_kind":"pith_short_12","alias_value":"7QFWEOWUINIY","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7QFWEOWUINIYINDU","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7QFWEOWU","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:daac098cbdb613ee4ee82fde4a5f94cd8e4f602792feed7f7cf19f7fef028458","target":"graph","created_at":"2026-05-17T23:46:57Z","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"},"paper":{"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","authors_text":"Felipe Soares, Karin Becker, Viviane Pereira Moreira","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-06T07:33:00Z","title":"A Large Parallel Corpus of Full-Text Scientific Articles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01852","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":"sha256:5503bfa33d3cb9f3a53ba56e837c68d971f47cd9477aab5fb334d7ea2235f89c","target":"record","created_at":"2026-05-17T23:46:57Z","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":"f86bbaeabb0a9d87c977ae93f4664ae38ce8d6a46bace740ecbcfe535d142447","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-06T07:33:00Z","title_canon_sha256":"124abeefe213eac76e93c5e70f8a8aed262dd060819a624036fabe37b0808bff"},"schema_version":"1.0","source":{"id":"1905.01852","kind":"arxiv","version":1}},"canonical_sha256":"fc0b623ad4435184347431b58e5122d9c49430c677f3230baa7c9a71baf55789","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc0b623ad4435184347431b58e5122d9c49430c677f3230baa7c9a71baf55789","first_computed_at":"2026-05-17T23:46:57.231785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:57.231785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PmNKtCJv7qER4RzvSGVknBngi8ChhpP8MM+W4/nru3J9c66si936COOolunUKcHAUz+r82tSVxZ5Vn+vij3oDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:57.232577Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5503bfa33d3cb9f3a53ba56e837c68d971f47cd9477aab5fb334d7ea2235f89c","sha256:daac098cbdb613ee4ee82fde4a5f94cd8e4f602792feed7f7cf19f7fef028458"],"state_sha256":"70c6db0f3606d474b8cd5b7aac4fc5fa7962e3c19415ff387abeed1dc60ab439"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JkAklve2NffDhFOjGFSr1RoOayWM8hmZDmtLKpKswVQNMXFfoVko4zOq4z0bikV3iZwM7v9poQnzwZtRV2ELAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T00:26:29.213729Z","bundle_sha256":"9483bfb22a4ad9b470d637e5b93595e963da45790458b3be2db380910e9a333a"}}