{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EMRATPWO2T67HXXQTFQYPP656T","short_pith_number":"pith:EMRATPWO","canonical_record":{"source":{"id":"2405.05376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:06:19Z","cross_cats_sorted":[],"title_canon_sha256":"b867c7a69127fa3d40a3dce441f875e6c50b7e841ddebffb0fe41e06370a490b","abstract_canon_sha256":"0c671d4a103c3de25e2ce671133d993dcf479644aaffbcb11acf8974639135a7"},"schema_version":"1.0"},"canonical_sha256":"232209beced4fdf3def0996187bfddf4d7fb48c3bf05cfbac921334f3266f1b0","source":{"kind":"arxiv","id":"2405.05376","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05376","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05376v2","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05376","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"EMRATPWO2T67","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"EMRATPWO2T67HXXQ","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"EMRATPWO","created_at":"2026-07-05T08:18:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EMRATPWO2T67HXXQTFQYPP656T","target":"record","payload":{"canonical_record":{"source":{"id":"2405.05376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:06:19Z","cross_cats_sorted":[],"title_canon_sha256":"b867c7a69127fa3d40a3dce441f875e6c50b7e841ddebffb0fe41e06370a490b","abstract_canon_sha256":"0c671d4a103c3de25e2ce671133d993dcf479644aaffbcb11acf8974639135a7"},"schema_version":"1.0"},"canonical_sha256":"232209beced4fdf3def0996187bfddf4d7fb48c3bf05cfbac921334f3266f1b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:33.810271Z","signature_b64":"W1HMZf/2CXVNtt+Y7m4EWy+juDjgfJxIQptalGSQvNN60oO4REQJ1obqPavrd1kEjPCTnHtO8UKJv3FjI5p4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"232209beced4fdf3def0996187bfddf4d7fb48c3bf05cfbac921334f3266f1b0","last_reissued_at":"2026-07-05T08:18:33.809792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:33.809792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.05376","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qbke/NPnmdNCZdaYGdjaIHn/OaB01jsCzsbPzuCT4cvaFRJG60buSS3di9CdKxJ8deviHvpoCuoD7ET8qC4XCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:26:56.268652Z"},"content_sha256":"49372157e8972a0c1a6ef90fd82a6804b715170be3265fa70564c53b30da9221","schema_version":"1.0","event_id":"sha256:49372157e8972a0c1a6ef90fd82a6804b715170be3265fa70564c53b30da9221"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EMRATPWO2T67HXXQTFQYPP656T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Krey\\`ol-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ammon Shurtz, Ashi Garg, Bismarck Bamfo Odoom, Claire Bizon Monroc, Hasan Muhammad, Kenton Murray, Lo\\\"ic Grobol, Matthew Dean Stutzman, Naome A. Etori, Nathaniel R. Robinson, Olanrewaju Samuel, Onenamiyi Onesi, Raj Dabre, Rasul Dent, Sanjeev Khudanpur, Stephen D. Richardson, Vijay Murari Tiyyala","submitted_at":"2024-05-08T19:06:19Z","abstract_excerpt":"A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their speakers could benefit from machine translation (MT). These languages are predominantly used in much of Latin America, Africa and the Caribbean. We present the largest cumulative dataset to date for Creole language MT, including 14.5M unique Creole sentences with parallel translations -- 11.6M of which we release publicly, and the largest bitexts g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05376","kind":"arxiv","version":2},"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/2405.05376/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hasSyMtGcmlB5NfmU4cN1hmhcpTI30RHbTpmksCTaiMaLpj4ja7OXGk/qJ/pB888C8rhHrt44Wb8mTWKEe+gAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:26:56.269024Z"},"content_sha256":"e1c2992debf56f864fa83a99087187727ae9d4dd9dd5700fc231879b112ba9e8","schema_version":"1.0","event_id":"sha256:e1c2992debf56f864fa83a99087187727ae9d4dd9dd5700fc231879b112ba9e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMRATPWO2T67HXXQTFQYPP656T/bundle.json","state_url":"https://pith.science/pith/EMRATPWO2T67HXXQTFQYPP656T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMRATPWO2T67HXXQTFQYPP656T/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":"2026-07-07T15:26:56Z","links":{"resolver":"https://pith.science/pith/EMRATPWO2T67HXXQTFQYPP656T","bundle":"https://pith.science/pith/EMRATPWO2T67HXXQTFQYPP656T/bundle.json","state":"https://pith.science/pith/EMRATPWO2T67HXXQTFQYPP656T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMRATPWO2T67HXXQTFQYPP656T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EMRATPWO2T67HXXQTFQYPP656T","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":"0c671d4a103c3de25e2ce671133d993dcf479644aaffbcb11acf8974639135a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:06:19Z","title_canon_sha256":"b867c7a69127fa3d40a3dce441f875e6c50b7e841ddebffb0fe41e06370a490b"},"schema_version":"1.0","source":{"id":"2405.05376","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05376","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05376v2","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05376","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"EMRATPWO2T67","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"EMRATPWO2T67HXXQ","created_at":"2026-07-05T08:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"EMRATPWO","created_at":"2026-07-05T08:18:33Z"}],"graph_snapshots":[{"event_id":"sha256:e1c2992debf56f864fa83a99087187727ae9d4dd9dd5700fc231879b112ba9e8","target":"graph","created_at":"2026-07-05T08:18:33Z","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/2405.05376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their speakers could benefit from machine translation (MT). These languages are predominantly used in much of Latin America, Africa and the Caribbean. We present the largest cumulative dataset to date for Creole language MT, including 14.5M unique Creole sentences with parallel translations -- 11.6M of which we release publicly, and the largest bitexts g","authors_text":"Ammon Shurtz, Ashi Garg, Bismarck Bamfo Odoom, Claire Bizon Monroc, Hasan Muhammad, Kenton Murray, Lo\\\"ic Grobol, Matthew Dean Stutzman, Naome A. Etori, Nathaniel R. Robinson, Olanrewaju Samuel, Onenamiyi Onesi, Raj Dabre, Rasul Dent, Sanjeev Khudanpur, Stephen D. Richardson, Vijay Murari Tiyyala","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:06:19Z","title":"Krey\\`ol-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05376","kind":"arxiv","version":2},"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":"sha256:49372157e8972a0c1a6ef90fd82a6804b715170be3265fa70564c53b30da9221","target":"record","created_at":"2026-07-05T08:18:33Z","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":"0c671d4a103c3de25e2ce671133d993dcf479644aaffbcb11acf8974639135a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:06:19Z","title_canon_sha256":"b867c7a69127fa3d40a3dce441f875e6c50b7e841ddebffb0fe41e06370a490b"},"schema_version":"1.0","source":{"id":"2405.05376","kind":"arxiv","version":2}},"canonical_sha256":"232209beced4fdf3def0996187bfddf4d7fb48c3bf05cfbac921334f3266f1b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"232209beced4fdf3def0996187bfddf4d7fb48c3bf05cfbac921334f3266f1b0","first_computed_at":"2026-07-05T08:18:33.809792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:33.809792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W1HMZf/2CXVNtt+Y7m4EWy+juDjgfJxIQptalGSQvNN60oO4REQJ1obqPavrd1kEjPCTnHtO8UKJv3FjI5p4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:33.810271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05376","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49372157e8972a0c1a6ef90fd82a6804b715170be3265fa70564c53b30da9221","sha256:e1c2992debf56f864fa83a99087187727ae9d4dd9dd5700fc231879b112ba9e8"],"state_sha256":"5f836b9f0255ff0f11813202d700591372918ff444e6bd2e6115c59bb6cd59ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5oP7P9VqrLZfMlYVctQ8oFR79L/ozMvl0eqG9eZvWrq2cvdjmH2hE5VM9EyLxJ+fN1kdWVtK5Muy0OxpGn5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:26:56.270925Z","bundle_sha256":"856dfa0daa241f08fa5b9a13036e8a27bc5b2efd1189589e8745b3e3419d6ca9"}}