{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KW7NUIT6V4N2Q6IDRELSOJYH4K","short_pith_number":"pith:KW7NUIT6","canonical_record":{"source":{"id":"2402.01939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T22:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"da578f34dde3f2db65cee23dfcd24d128e4ca893d24626cb1875304d6eadaef9","abstract_canon_sha256":"90665773b69686d270bd905272a9f811c60f45dd4ffd7ff206798834574cb511"},"schema_version":"1.0"},"canonical_sha256":"55beda227eaf1ba879038917272707e2a0da5cffa679394268bd4ee8a215424d","source":{"kind":"arxiv","id":"2402.01939","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01939","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01939v1","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01939","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"pith_short_12","alias_value":"KW7NUIT6V4N2","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"pith_short_16","alias_value":"KW7NUIT6V4N2Q6ID","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"pith_short_8","alias_value":"KW7NUIT6","created_at":"2026-07-05T07:41:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KW7NUIT6V4N2Q6IDRELSOJYH4K","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T22:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"da578f34dde3f2db65cee23dfcd24d128e4ca893d24626cb1875304d6eadaef9","abstract_canon_sha256":"90665773b69686d270bd905272a9f811c60f45dd4ffd7ff206798834574cb511"},"schema_version":"1.0"},"canonical_sha256":"55beda227eaf1ba879038917272707e2a0da5cffa679394268bd4ee8a215424d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:08.498141Z","signature_b64":"qrFsoRQbaEj9b2LuMUsOSaiCsr+EQM4bQG15VfONeuvov2ZLTJbR+9++yKXX7vCJPHEWuIJWGndpZhbEtr12Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55beda227eaf1ba879038917272707e2a0da5cffa679394268bd4ee8a215424d","last_reissued_at":"2026-07-05T07:41:08.497731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:08.497731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01939","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":"2026-07-05T07:41:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1O7cij2K4Uv13pPFxzU7XwKxg5chKOiQewb1WF3vrBclbUwIweo54tzDYDo32sVyIBeGZLEWcRdawiVVzHKbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:12:54.531033Z"},"content_sha256":"004e7ba32ae21a5b3f47e981718dbf684e1a674df152c820502d3f85d4d8050a","schema_version":"1.0","event_id":"sha256:004e7ba32ae21a5b3f47e981718dbf684e1a674df152c820502d3f85d4d8050a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KW7NUIT6V4N2Q6IDRELSOJYH4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Md Mahfuz ibn Alam, Sina Ahmadi","submitted_at":"2024-02-02T22:25:44Z","abstract_excerpt":"The availability of parallel texts is crucial to the performance of machine translation models. However, most of the world's languages face the predominant challenge of data scarcity. In this paper, we propose strategies to synthesize parallel data relying on morpho-syntactic information and using bilingual lexicons along with a small amount of seed parallel data. Our methodology adheres to a realistic scenario backed by the small parallel seed data. It is linguistically informed, as it aims to create augmented data that is more likely to be grammatically correct. We analyze how our synthetic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01939","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/2402.01939/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":"2026-07-05T07:41:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tjq5+ZQCd8hzxg27Gd9Ut1ro4OkKO/hkwnsP7fPRH7joMe2BX+qQWil4vcE3ffwHuLz0FfMEhFmJdJKt3OFrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:12:54.531989Z"},"content_sha256":"a866586c60416fbcf04fb98b042ee985f4f775cbb49c2e848179dc72f72d9621","schema_version":"1.0","event_id":"sha256:a866586c60416fbcf04fb98b042ee985f4f775cbb49c2e848179dc72f72d9621"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KW7NUIT6V4N2Q6IDRELSOJYH4K/bundle.json","state_url":"https://pith.science/pith/KW7NUIT6V4N2Q6IDRELSOJYH4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KW7NUIT6V4N2Q6IDRELSOJYH4K/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":"2026-08-04T06:12:54Z","links":{"resolver":"https://pith.science/pith/KW7NUIT6V4N2Q6IDRELSOJYH4K","bundle":"https://pith.science/pith/KW7NUIT6V4N2Q6IDRELSOJYH4K/bundle.json","state":"https://pith.science/pith/KW7NUIT6V4N2Q6IDRELSOJYH4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KW7NUIT6V4N2Q6IDRELSOJYH4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KW7NUIT6V4N2Q6IDRELSOJYH4K","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":"90665773b69686d270bd905272a9f811c60f45dd4ffd7ff206798834574cb511","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T22:25:44Z","title_canon_sha256":"da578f34dde3f2db65cee23dfcd24d128e4ca893d24626cb1875304d6eadaef9"},"schema_version":"1.0","source":{"id":"2402.01939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01939","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01939v1","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01939","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"pith_short_12","alias_value":"KW7NUIT6V4N2","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"pith_short_16","alias_value":"KW7NUIT6V4N2Q6ID","created_at":"2026-07-05T07:41:08Z"},{"alias_kind":"pith_short_8","alias_value":"KW7NUIT6","created_at":"2026-07-05T07:41:08Z"}],"graph_snapshots":[{"event_id":"sha256:a866586c60416fbcf04fb98b042ee985f4f775cbb49c2e848179dc72f72d9621","target":"graph","created_at":"2026-07-05T07:41:08Z","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/2402.01939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The availability of parallel texts is crucial to the performance of machine translation models. However, most of the world's languages face the predominant challenge of data scarcity. In this paper, we propose strategies to synthesize parallel data relying on morpho-syntactic information and using bilingual lexicons along with a small amount of seed parallel data. Our methodology adheres to a realistic scenario backed by the small parallel seed data. It is linguistically informed, as it aims to create augmented data that is more likely to be grammatically correct. We analyze how our synthetic ","authors_text":"Antonios Anastasopoulos, Md Mahfuz ibn Alam, Sina Ahmadi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T22:25:44Z","title":"A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01939","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":"sha256:004e7ba32ae21a5b3f47e981718dbf684e1a674df152c820502d3f85d4d8050a","target":"record","created_at":"2026-07-05T07:41:08Z","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":"90665773b69686d270bd905272a9f811c60f45dd4ffd7ff206798834574cb511","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T22:25:44Z","title_canon_sha256":"da578f34dde3f2db65cee23dfcd24d128e4ca893d24626cb1875304d6eadaef9"},"schema_version":"1.0","source":{"id":"2402.01939","kind":"arxiv","version":1}},"canonical_sha256":"55beda227eaf1ba879038917272707e2a0da5cffa679394268bd4ee8a215424d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55beda227eaf1ba879038917272707e2a0da5cffa679394268bd4ee8a215424d","first_computed_at":"2026-07-05T07:41:08.497731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:08.497731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qrFsoRQbaEj9b2LuMUsOSaiCsr+EQM4bQG15VfONeuvov2ZLTJbR+9++yKXX7vCJPHEWuIJWGndpZhbEtr12Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:08.498141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:004e7ba32ae21a5b3f47e981718dbf684e1a674df152c820502d3f85d4d8050a","sha256:a866586c60416fbcf04fb98b042ee985f4f775cbb49c2e848179dc72f72d9621"],"state_sha256":"8232378fd30763a8c07ddfd56e87476f0e76ff6048f02c6a308a797132ab48be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eqkSHV6jamCwse7J5f+42rQbLxIuLfZeE4JvBeKla6l47UMPMvhvrA3iNWeO0e4uPuJTTE9/u2lxw7qZ6+/mCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:12:54.544136Z","bundle_sha256":"53cafc769b19192fccf655c5f8b231d9fe6aa3253ee4304b5e7f6e488c62213e"}}