{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JLDKRSWDZZCC3O3TRVFJWLQVAB","short_pith_number":"pith:JLDKRSWD","canonical_record":{"source":{"id":"2504.02674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T15:14:19Z","cross_cats_sorted":[],"title_canon_sha256":"8792da6755c37ea950d84c39f60d0c2ed5915a4501c1dc5ded83e3e8eb1865f5","abstract_canon_sha256":"fd3dd502449b27bed6eb7ffbe80cc024348b6cdfeaa9f16686a4f3effa3776e6"},"schema_version":"1.0"},"canonical_sha256":"4ac6a8cac3ce442dbb738d4a9b2e15005ff8704ba353bd3d2084dbcad5ccc894","source":{"kind":"arxiv","id":"2504.02674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02674","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02674v1","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02674","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"JLDKRSWDZZCC","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"pith_short_16","alias_value":"JLDKRSWDZZCC3O3T","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"pith_short_8","alias_value":"JLDKRSWD","created_at":"2026-07-05T10:44:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JLDKRSWDZZCC3O3TRVFJWLQVAB","target":"record","payload":{"canonical_record":{"source":{"id":"2504.02674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T15:14:19Z","cross_cats_sorted":[],"title_canon_sha256":"8792da6755c37ea950d84c39f60d0c2ed5915a4501c1dc5ded83e3e8eb1865f5","abstract_canon_sha256":"fd3dd502449b27bed6eb7ffbe80cc024348b6cdfeaa9f16686a4f3effa3776e6"},"schema_version":"1.0"},"canonical_sha256":"4ac6a8cac3ce442dbb738d4a9b2e15005ff8704ba353bd3d2084dbcad5ccc894","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:00.715723Z","signature_b64":"UcBAPokTXGrO/G8dgC6Wii3O03j4rtXsZ0zk8kVCHqoSNvLr9M24n5fjgiFF8qeEv45kSB4ULkYkTB2s1aSCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ac6a8cac3ce442dbb738d4a9b2e15005ff8704ba353bd3d2084dbcad5ccc894","last_reissued_at":"2026-07-05T10:44:00.715160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:00.715160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.02674","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":"2026-07-05T10:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gnvrlStY9lm3oZ7N1iuwoadSEOC7UahYVm3jfYwExAI58eRbw+ZvZJRwyFuxrICo+hmttAD0ja3MtWo2x/hDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T08:53:10.356354Z"},"content_sha256":"6a679c9c3ef46748c823842fbf761d5e8c3a7ff57a99c1c84deb64d507007a6e","schema_version":"1.0","event_id":"sha256:6a679c9c3ef46748c823842fbf761d5e8c3a7ff57a99c1c84deb64d507007a6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JLDKRSWDZZCC3O3TRVFJWLQVAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Limitations of Religious Data and the Importance of the Target Domain: Towards Machine Translation for Guinea-Bissau Creole","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Gow-Smith, Jacqueline Rowe, Mark Hepple","submitted_at":"2025-04-03T15:14:19Z","abstract_excerpt":"We introduce a new dataset for machine translation of Guinea-Bissau Creole (Kiriol), comprising around 40 thousand parallel sentences to English and Portuguese. This dataset is made up of predominantly religious data (from the Bible and texts from the Jehovah's Witnesses), but also a small amount of general domain data (from a dictionary). This mirrors the typical resource availability of many low resource languages. We train a number of transformer-based models to investigate how to improve domain transfer from religious data to a more general domain. We find that adding even 300 sentences fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02674","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/2504.02674/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":"2026-07-05T10:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i//tQiYrfudrf7/5XA+jqq2+ZGdTCB8naabgq3WGW9NMCGxx0XFhq1A3xTStz30fHki2NYp0jN6fPhErhuc4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T08:53:10.356717Z"},"content_sha256":"43833a3b5b9f04439c8fb2c93544b4acdf0e302e12252552bcbd30a668d6bdf4","schema_version":"1.0","event_id":"sha256:43833a3b5b9f04439c8fb2c93544b4acdf0e302e12252552bcbd30a668d6bdf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLDKRSWDZZCC3O3TRVFJWLQVAB/bundle.json","state_url":"https://pith.science/pith/JLDKRSWDZZCC3O3TRVFJWLQVAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLDKRSWDZZCC3O3TRVFJWLQVAB/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":"2026-07-21T08:53:10Z","links":{"resolver":"https://pith.science/pith/JLDKRSWDZZCC3O3TRVFJWLQVAB","bundle":"https://pith.science/pith/JLDKRSWDZZCC3O3TRVFJWLQVAB/bundle.json","state":"https://pith.science/pith/JLDKRSWDZZCC3O3TRVFJWLQVAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLDKRSWDZZCC3O3TRVFJWLQVAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JLDKRSWDZZCC3O3TRVFJWLQVAB","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":"fd3dd502449b27bed6eb7ffbe80cc024348b6cdfeaa9f16686a4f3effa3776e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T15:14:19Z","title_canon_sha256":"8792da6755c37ea950d84c39f60d0c2ed5915a4501c1dc5ded83e3e8eb1865f5"},"schema_version":"1.0","source":{"id":"2504.02674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02674","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02674v1","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02674","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"JLDKRSWDZZCC","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"pith_short_16","alias_value":"JLDKRSWDZZCC3O3T","created_at":"2026-07-05T10:44:00Z"},{"alias_kind":"pith_short_8","alias_value":"JLDKRSWD","created_at":"2026-07-05T10:44:00Z"}],"graph_snapshots":[{"event_id":"sha256:43833a3b5b9f04439c8fb2c93544b4acdf0e302e12252552bcbd30a668d6bdf4","target":"graph","created_at":"2026-07-05T10:44:00Z","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/2504.02674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a new dataset for machine translation of Guinea-Bissau Creole (Kiriol), comprising around 40 thousand parallel sentences to English and Portuguese. This dataset is made up of predominantly religious data (from the Bible and texts from the Jehovah's Witnesses), but also a small amount of general domain data (from a dictionary). This mirrors the typical resource availability of many low resource languages. We train a number of transformer-based models to investigate how to improve domain transfer from religious data to a more general domain. We find that adding even 300 sentences fr","authors_text":"Edward Gow-Smith, Jacqueline Rowe, Mark Hepple","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T15:14:19Z","title":"Limitations of Religious Data and the Importance of the Target Domain: Towards Machine Translation for Guinea-Bissau Creole"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02674","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":"sha256:6a679c9c3ef46748c823842fbf761d5e8c3a7ff57a99c1c84deb64d507007a6e","target":"record","created_at":"2026-07-05T10:44:00Z","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":"fd3dd502449b27bed6eb7ffbe80cc024348b6cdfeaa9f16686a4f3effa3776e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T15:14:19Z","title_canon_sha256":"8792da6755c37ea950d84c39f60d0c2ed5915a4501c1dc5ded83e3e8eb1865f5"},"schema_version":"1.0","source":{"id":"2504.02674","kind":"arxiv","version":1}},"canonical_sha256":"4ac6a8cac3ce442dbb738d4a9b2e15005ff8704ba353bd3d2084dbcad5ccc894","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ac6a8cac3ce442dbb738d4a9b2e15005ff8704ba353bd3d2084dbcad5ccc894","first_computed_at":"2026-07-05T10:44:00.715160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:00.715160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UcBAPokTXGrO/G8dgC6Wii3O03j4rtXsZ0zk8kVCHqoSNvLr9M24n5fjgiFF8qeEv45kSB4ULkYkTB2s1aSCAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:00.715723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a679c9c3ef46748c823842fbf761d5e8c3a7ff57a99c1c84deb64d507007a6e","sha256:43833a3b5b9f04439c8fb2c93544b4acdf0e302e12252552bcbd30a668d6bdf4"],"state_sha256":"fcc3356f235287b33ef9eaf6078feee6243b9ae3200449fd4a851726a21f93c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y7tx7xZW6tnNu3aXYxtAtqkV21Ojw2b86ewWHxmXncP5YrkzzeodPflEmOV5Q401P9y/mbbfO5U1fOmaeAFTBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T08:53:10.358846Z","bundle_sha256":"34a05a05f5369d89a7537299c3ea5fdca5741560129c7d0d9ddbe07341e99f7f"}}