{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L7NWVTDQVRY5MREU6MBVQR3YVP","short_pith_number":"pith:L7NWVTDQ","schema_version":"1.0","canonical_sha256":"5fdb6acc70ac71d64494f303584778abde55f52a240a57b1ef07689fb7fb469b","source":{"kind":"arxiv","id":"2304.09919","version":1},"attestation_state":"computed","paper":{"title":"The eBible Corpus: Data and Model Benchmarks for Bible Translation for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Colin Leong, Damien Daspit, David Baines, Joel Mathew, Jonathan Robie, Marcus Schwarting, Michael Martin, Taeho Jang, Ulf Hermjakob, Vesa Akerman","submitted_at":"2023-04-19T18:52:49Z","abstract_excerpt":"Efficiently and accurately translating a corpus into a low-resource language remains a challenge, regardless of the strategies employed, whether manual, automated, or a combination of the two. Many Christian organizations are dedicated to the task of translating the Holy Bible into languages that lack a modern translation. Bible translation (BT) work is currently underway for over 3000 extremely low resource languages. We introduce the eBible corpus: a dataset containing 1009 translations of portions of the Bible with data in 833 different languages across 75 language families. In addition to "},"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":"2304.09919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T18:52:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"40d6030a3b86e1d4e01f3a7433cecf90dbf4e20cac0003494733c72d3a8ed2ef","abstract_canon_sha256":"0f393bdc9fbadcee9f36ffc58346f20c0802d0615b161e4bd69f89d721b99ced"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:51.673941Z","signature_b64":"ExEJuqV9KChTrtd0H3HwyoQM4Ezf1B5lzc3MAY2HmC8yBZeUa9np3uBB8QlZim2Z1wAyU9lSBz3SCQqX08aaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fdb6acc70ac71d64494f303584778abde55f52a240a57b1ef07689fb7fb469b","last_reissued_at":"2026-07-05T06:02:51.673429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:51.673429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The eBible Corpus: Data and Model Benchmarks for Bible Translation for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Colin Leong, Damien Daspit, David Baines, Joel Mathew, Jonathan Robie, Marcus Schwarting, Michael Martin, Taeho Jang, Ulf Hermjakob, Vesa Akerman","submitted_at":"2023-04-19T18:52:49Z","abstract_excerpt":"Efficiently and accurately translating a corpus into a low-resource language remains a challenge, regardless of the strategies employed, whether manual, automated, or a combination of the two. Many Christian organizations are dedicated to the task of translating the Holy Bible into languages that lack a modern translation. Bible translation (BT) work is currently underway for over 3000 extremely low resource languages. We introduce the eBible corpus: a dataset containing 1009 translations of portions of the Bible with data in 833 different languages across 75 language families. In addition to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09919","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.09919/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2304.09919","created_at":"2026-07-05T06:02:51.673498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09919v1","created_at":"2026-07-05T06:02:51.673498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09919","created_at":"2026-07-05T06:02:51.673498+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7NWVTDQVRY5","created_at":"2026-07-05T06:02:51.673498+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7NWVTDQVRY5MREU","created_at":"2026-07-05T06:02:51.673498+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7NWVTDQ","created_at":"2026-07-05T06:02:51.673498+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/L7NWVTDQVRY5MREU6MBVQR3YVP","json":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP.json","graph_json":"https://pith.science/api/pith-number/L7NWVTDQVRY5MREU6MBVQR3YVP/graph.json","events_json":"https://pith.science/api/pith-number/L7NWVTDQVRY5MREU6MBVQR3YVP/events.json","paper":"https://pith.science/paper/L7NWVTDQ"},"agent_actions":{"view_html":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP","download_json":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP.json","view_paper":"https://pith.science/paper/L7NWVTDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09919&json=true","fetch_graph":"https://pith.science/api/pith-number/L7NWVTDQVRY5MREU6MBVQR3YVP/graph.json","fetch_events":"https://pith.science/api/pith-number/L7NWVTDQVRY5MREU6MBVQR3YVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP/action/storage_attestation","attest_author":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP/action/author_attestation","sign_citation":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP/action/citation_signature","submit_replication":"https://pith.science/pith/L7NWVTDQVRY5MREU6MBVQR3YVP/action/replication_record"}},"created_at":"2026-07-05T06:02:51.673498+00:00","updated_at":"2026-07-05T06:02:51.673498+00:00"}