{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OEUE6A33RJOM4CQPMABVPPWDQY","short_pith_number":"pith:OEUE6A33","canonical_record":{"source":{"id":"1804.01768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T10:35:51Z","cross_cats_sorted":[],"title_canon_sha256":"a864f4b175ed53186259bc069a7ad6950236b8bae7c8a1d378ba0d925bd283ab","abstract_canon_sha256":"fd046329acfb871d4814d5b33b0dc9785c7bb462b2d5ad9e75c25d4c81079403"},"schema_version":"1.0"},"canonical_sha256":"71284f037b8a5cce0a0f600357bec386055aa16b2e799486901a70014ed6fa27","source":{"kind":"arxiv","id":"1804.01768","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01768","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01768v1","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01768","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"OEUE6A33RJOM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OEUE6A33RJOM4CQP","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OEUE6A33","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OEUE6A33RJOM4CQPMABVPPWDQY","target":"record","payload":{"canonical_record":{"source":{"id":"1804.01768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T10:35:51Z","cross_cats_sorted":[],"title_canon_sha256":"a864f4b175ed53186259bc069a7ad6950236b8bae7c8a1d378ba0d925bd283ab","abstract_canon_sha256":"fd046329acfb871d4814d5b33b0dc9785c7bb462b2d5ad9e75c25d4c81079403"},"schema_version":"1.0"},"canonical_sha256":"71284f037b8a5cce0a0f600357bec386055aa16b2e799486901a70014ed6fa27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:10.042397Z","signature_b64":"/DnJheiWLQRLPJF7q2r5UZJcQhwc3V2Fmp2+NhqD+zsZfux7v7siUSHv0yMmYYmA0yMn0MMe1YgyLRTFVU7YCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71284f037b8a5cce0a0f600357bec386055aa16b2e799486901a70014ed6fa27","last_reissued_at":"2026-05-18T00:19:10.041610Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:10.041610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.01768","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":"2026-05-18T00:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcx5IbwhplP1JN2WIDQsaiYoZ657eVx9MYapEwuzpbdmZLfZARE6hBNlyL7au19/fdnP8IUNA16RrwrSrqWBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:10:37.526945Z"},"content_sha256":"0163ecd3396e8786f8d2e4e8f871fe0dbeac1f7bc9c0fa58e1d6e1f7fd78ff75","schema_version":"1.0","event_id":"sha256:0163ecd3396e8786f8d2e4e8f871fe0dbeac1f7bc9c0fa58e1d6e1f7fd78ff75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OEUE6A33RJOM4CQPMABVPPWDQY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chinese-Portuguese Machine Translation: A Study on Building Parallel Corpora from Comparable Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao-Hong Liu, Longyue Wang, Siyou Liu","submitted_at":"2018-04-05T10:35:51Z","abstract_excerpt":"Although there are increasing and significant ties between China and Portuguese-speaking countries, there is not much parallel corpora in the Chinese-Portuguese language pair. Both languages are very populous, with 1.2 billion native Chinese speakers and 279 million native Portuguese speakers, the language pair, however, could be considered as low-resource in terms of available parallel corpora. In this paper, we describe our methods to curate Chinese-Portuguese parallel corpora and evaluate their quality. We extracted bilingual data from Macao government websites and proposed a hierarchical s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01768","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":"2026-05-18T00:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYHlxkZXhiCS+R1vaSXSYvSj2C2EGOpYimDa3I6nNLwfyl1zmNJtG2VWhZMBGTaYpL+J7l/DQjfHmRu/eZ+qBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:10:37.527590Z"},"content_sha256":"12f7cb0badccf52bbf3fe8f08b6e1a8384a8ecbd0720ecb95dc255f7555ae76e","schema_version":"1.0","event_id":"sha256:12f7cb0badccf52bbf3fe8f08b6e1a8384a8ecbd0720ecb95dc255f7555ae76e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OEUE6A33RJOM4CQPMABVPPWDQY/bundle.json","state_url":"https://pith.science/pith/OEUE6A33RJOM4CQPMABVPPWDQY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OEUE6A33RJOM4CQPMABVPPWDQY/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":"2026-05-26T00:10:37Z","links":{"resolver":"https://pith.science/pith/OEUE6A33RJOM4CQPMABVPPWDQY","bundle":"https://pith.science/pith/OEUE6A33RJOM4CQPMABVPPWDQY/bundle.json","state":"https://pith.science/pith/OEUE6A33RJOM4CQPMABVPPWDQY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OEUE6A33RJOM4CQPMABVPPWDQY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OEUE6A33RJOM4CQPMABVPPWDQY","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":"fd046329acfb871d4814d5b33b0dc9785c7bb462b2d5ad9e75c25d4c81079403","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T10:35:51Z","title_canon_sha256":"a864f4b175ed53186259bc069a7ad6950236b8bae7c8a1d378ba0d925bd283ab"},"schema_version":"1.0","source":{"id":"1804.01768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01768","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01768v1","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01768","created_at":"2026-05-18T00:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"OEUE6A33RJOM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OEUE6A33RJOM4CQP","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OEUE6A33","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:12f7cb0badccf52bbf3fe8f08b6e1a8384a8ecbd0720ecb95dc255f7555ae76e","target":"graph","created_at":"2026-05-18T00:19:10Z","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":"Although there are increasing and significant ties between China and Portuguese-speaking countries, there is not much parallel corpora in the Chinese-Portuguese language pair. Both languages are very populous, with 1.2 billion native Chinese speakers and 279 million native Portuguese speakers, the language pair, however, could be considered as low-resource in terms of available parallel corpora. In this paper, we describe our methods to curate Chinese-Portuguese parallel corpora and evaluate their quality. We extracted bilingual data from Macao government websites and proposed a hierarchical s","authors_text":"Chao-Hong Liu, Longyue Wang, Siyou Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T10:35:51Z","title":"Chinese-Portuguese Machine Translation: A Study on Building Parallel Corpora from Comparable Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01768","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":"sha256:0163ecd3396e8786f8d2e4e8f871fe0dbeac1f7bc9c0fa58e1d6e1f7fd78ff75","target":"record","created_at":"2026-05-18T00:19:10Z","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":"fd046329acfb871d4814d5b33b0dc9785c7bb462b2d5ad9e75c25d4c81079403","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-04-05T10:35:51Z","title_canon_sha256":"a864f4b175ed53186259bc069a7ad6950236b8bae7c8a1d378ba0d925bd283ab"},"schema_version":"1.0","source":{"id":"1804.01768","kind":"arxiv","version":1}},"canonical_sha256":"71284f037b8a5cce0a0f600357bec386055aa16b2e799486901a70014ed6fa27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71284f037b8a5cce0a0f600357bec386055aa16b2e799486901a70014ed6fa27","first_computed_at":"2026-05-18T00:19:10.041610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:10.041610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/DnJheiWLQRLPJF7q2r5UZJcQhwc3V2Fmp2+NhqD+zsZfux7v7siUSHv0yMmYYmA0yMn0MMe1YgyLRTFVU7YCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:10.042397Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0163ecd3396e8786f8d2e4e8f871fe0dbeac1f7bc9c0fa58e1d6e1f7fd78ff75","sha256:12f7cb0badccf52bbf3fe8f08b6e1a8384a8ecbd0720ecb95dc255f7555ae76e"],"state_sha256":"930f67639c6245c4f4da6405849bba65494b2fe6d1343a0bf1c5708a11938f11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqvdwNKOi9n2TqgXjD0hB825GFh98gVvUv3Fs/K3j+YAFUApN/54NSLcQwi2G2x7PEfCYCG85DLtJI+R3FkpCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:10:37.531037Z","bundle_sha256":"a4f20777bfac27744b770f45a91d2a536001548516c34b12a649f3f2841c4ad2"}}