{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WBQQHSTXKUMVCQJBGRB6AKCVOH","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":"6867973ca6300538bff5eecbf271669f8928b02bbc84c762fc42aac53ddbc280","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-07T15:14:32Z","title_canon_sha256":"4dcd0357f6318f43db283cad01bda6cbefb83b245f6a5a31478e9dc378b5bd35"},"schema_version":"1.0","source":{"id":"2007.03541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03541","created_at":"2026-07-05T03:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03541v1","created_at":"2026-07-05T03:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03541","created_at":"2026-07-05T03:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"WBQQHSTXKUMV","created_at":"2026-07-05T03:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"WBQQHSTXKUMVCQJB","created_at":"2026-07-05T03:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"WBQQHSTX","created_at":"2026-07-05T03:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:a742d79b1552db3471f6bb30164a4874dd0d8c4c90b0b9fe4ba56cc5e76ee2c0","target":"graph","created_at":"2026-07-05T03:04:01Z","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/2007.03541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The primary objective of our work is to build a large-scale English-Thai dataset for machine translation. We construct an English-Thai machine translation dataset with over 1 million segment pairs, curated from various sources, namely news, Wikipedia articles, SMS messages, task-based dialogs, web-crawled data and government documents. Methodology for gathering data, building parallel texts and removing noisy sentence pairs are presented in a reproducible manner. We train machine translation models based on this dataset. Our models' performance are comparable to that of Google Translation API ","authors_text":"Attapol T. Rutherford, Charin Polpanumas, Lalita Lowphansirikul, Sarana Nutanong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-07T15:14:32Z","title":"scb-mt-en-th-2020: A Large English-Thai Parallel Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03541","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:cf25f03f58793dc5082c15bc5e06346ddc137eb056ca3a81dfd542456485ca2b","target":"record","created_at":"2026-07-05T03:04:01Z","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":"6867973ca6300538bff5eecbf271669f8928b02bbc84c762fc42aac53ddbc280","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-07T15:14:32Z","title_canon_sha256":"4dcd0357f6318f43db283cad01bda6cbefb83b245f6a5a31478e9dc378b5bd35"},"schema_version":"1.0","source":{"id":"2007.03541","kind":"arxiv","version":1}},"canonical_sha256":"b06103ca7755195141213443e0285571e68c1b9fba95c32a2b9a9537bf2491e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b06103ca7755195141213443e0285571e68c1b9fba95c32a2b9a9537bf2491e0","first_computed_at":"2026-07-05T03:04:01.394636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:04:01.394636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GeQapbBaqO++U2YM6pHXLbsz5Z0sK51BnKvr9fsj+ybJjurw624u+wwqamGRONfr7VgL53oVsc1bjLcTuCqHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:04:01.395029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf25f03f58793dc5082c15bc5e06346ddc137eb056ca3a81dfd542456485ca2b","sha256:a742d79b1552db3471f6bb30164a4874dd0d8c4c90b0b9fe4ba56cc5e76ee2c0"],"state_sha256":"e85b2075549684705808c18786bdf466b38467302b9174d66bbe67c68273af6a"}