{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T54ILEOWNWRSCZYR6XBGMAPJCZ","short_pith_number":"pith:T54ILEOW","canonical_record":{"source":{"id":"2306.07414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T20:43:24Z","cross_cats_sorted":[],"title_canon_sha256":"4f333ba4967912c727ff847e1d9b395fc1f8b9bd519784d177699b6683b2349e","abstract_canon_sha256":"cc3f890814f12e4f746f2808d10668f3250d5f53d073837b08921e71b9f0524a"},"schema_version":"1.0"},"canonical_sha256":"9f788591d66da3216711f5c26601e9164e85edd8bc0f2111239c69da3a700c53","source":{"kind":"arxiv","id":"2306.07414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07414","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07414v1","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07414","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_12","alias_value":"T54ILEOWNWRS","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_16","alias_value":"T54ILEOWNWRSCZYR","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_8","alias_value":"T54ILEOW","created_at":"2026-07-05T06:20:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T54ILEOWNWRSCZYR6XBGMAPJCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T20:43:24Z","cross_cats_sorted":[],"title_canon_sha256":"4f333ba4967912c727ff847e1d9b395fc1f8b9bd519784d177699b6683b2349e","abstract_canon_sha256":"cc3f890814f12e4f746f2808d10668f3250d5f53d073837b08921e71b9f0524a"},"schema_version":"1.0"},"canonical_sha256":"9f788591d66da3216711f5c26601e9164e85edd8bc0f2111239c69da3a700c53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:03.729296Z","signature_b64":"OCkXp+h35abRn+86jn63LHZaLnhn4m0rRurEWBPZhtHi1TwwSMFxIruMMwDCky+kecxsy3e5nq2ym6m1Ugj/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f788591d66da3216711f5c26601e9164e85edd8bc0f2111239c69da3a700c53","last_reissued_at":"2026-07-05T06:20:03.728827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:03.728827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07414","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":"2026-07-05T06:20:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5890ztLDjLtgFoL6KiaaLmzbOddZA3mNExaVdH0fmm6LsUObzjD/hvgfLKoHJRI4h0f6+QUwACr1ttO59K9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:34:51.652680Z"},"content_sha256":"236de62d3cf30d95b669f1c9a37a1bbd51fc5262308d89ce43c9a70668f47acb","schema_version":"1.0","event_id":"sha256:236de62d3cf30d95b669f1c9a37a1bbd51fc5262308d89ce43c9a70668f47acb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T54ILEOWNWRSCZYR6XBGMAPJCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Textual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Catherine Gitau, Vukosi Marivate","submitted_at":"2023-06-12T20:43:24Z","abstract_excerpt":"In this work we investigate the impact of applying textual data augmentation tasks to low resource machine translation. There has been recent interest in investigating approaches for training systems for languages with limited resources and one popular approach is the use of data augmentation techniques. Data augmentation aims to increase the quantity of data that is available to train the system. In machine translation, majority of the language pairs around the world are considered low resource because they have little parallel data available and the quality of neural machine translation (NMT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07414","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/2306.07414/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":"2026-07-05T06:20:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMFdJ5UCtdF0uXz5w44/SyDfzx5JZ5DiKyljSHoRgU4ODzklwVVY6cgSMppIktFTRyzkj2lJjW5Uw+xE94A6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:34:51.656879Z"},"content_sha256":"abadff3135d1ee2656a236c786c8efee253c7df7f795ed8eacbadd6d8419478e","schema_version":"1.0","event_id":"sha256:abadff3135d1ee2656a236c786c8efee253c7df7f795ed8eacbadd6d8419478e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T54ILEOWNWRSCZYR6XBGMAPJCZ/bundle.json","state_url":"https://pith.science/pith/T54ILEOWNWRSCZYR6XBGMAPJCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T54ILEOWNWRSCZYR6XBGMAPJCZ/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":"2026-08-17T23:34:51Z","links":{"resolver":"https://pith.science/pith/T54ILEOWNWRSCZYR6XBGMAPJCZ","bundle":"https://pith.science/pith/T54ILEOWNWRSCZYR6XBGMAPJCZ/bundle.json","state":"https://pith.science/pith/T54ILEOWNWRSCZYR6XBGMAPJCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T54ILEOWNWRSCZYR6XBGMAPJCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T54ILEOWNWRSCZYR6XBGMAPJCZ","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":"cc3f890814f12e4f746f2808d10668f3250d5f53d073837b08921e71b9f0524a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T20:43:24Z","title_canon_sha256":"4f333ba4967912c727ff847e1d9b395fc1f8b9bd519784d177699b6683b2349e"},"schema_version":"1.0","source":{"id":"2306.07414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07414","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07414v1","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07414","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_12","alias_value":"T54ILEOWNWRS","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_16","alias_value":"T54ILEOWNWRSCZYR","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_8","alias_value":"T54ILEOW","created_at":"2026-07-05T06:20:03Z"}],"graph_snapshots":[{"event_id":"sha256:abadff3135d1ee2656a236c786c8efee253c7df7f795ed8eacbadd6d8419478e","target":"graph","created_at":"2026-07-05T06:20:03Z","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/2306.07414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we investigate the impact of applying textual data augmentation tasks to low resource machine translation. There has been recent interest in investigating approaches for training systems for languages with limited resources and one popular approach is the use of data augmentation techniques. Data augmentation aims to increase the quantity of data that is available to train the system. In machine translation, majority of the language pairs around the world are considered low resource because they have little parallel data available and the quality of neural machine translation (NMT","authors_text":"Catherine Gitau, Vukosi Marivate","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T20:43:24Z","title":"Textual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07414","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":"sha256:236de62d3cf30d95b669f1c9a37a1bbd51fc5262308d89ce43c9a70668f47acb","target":"record","created_at":"2026-07-05T06:20:03Z","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":"cc3f890814f12e4f746f2808d10668f3250d5f53d073837b08921e71b9f0524a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T20:43:24Z","title_canon_sha256":"4f333ba4967912c727ff847e1d9b395fc1f8b9bd519784d177699b6683b2349e"},"schema_version":"1.0","source":{"id":"2306.07414","kind":"arxiv","version":1}},"canonical_sha256":"9f788591d66da3216711f5c26601e9164e85edd8bc0f2111239c69da3a700c53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f788591d66da3216711f5c26601e9164e85edd8bc0f2111239c69da3a700c53","first_computed_at":"2026-07-05T06:20:03.728827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:03.728827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OCkXp+h35abRn+86jn63LHZaLnhn4m0rRurEWBPZhtHi1TwwSMFxIruMMwDCky+kecxsy3e5nq2ym6m1Ugj/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:03.729296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:236de62d3cf30d95b669f1c9a37a1bbd51fc5262308d89ce43c9a70668f47acb","sha256:abadff3135d1ee2656a236c786c8efee253c7df7f795ed8eacbadd6d8419478e"],"state_sha256":"d08e6f5a7453a91facd28b837f40a9bf997c000bf37a2be402b180f1dee686be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CCSCfbwNWDQX2fYuSypwcEP9Vb5CJfzbNXgSrLyyAHON3ykVnn8AHPxyHvwPfsTzvLJMZAPSNx3djkCoZYr9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:34:51.677006Z","bundle_sha256":"1a401b227641580712dd9e86363f6fbab2078b01ec70a884942f9061001cf3cf"}}