{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CRNKLE2RVT67SZJD6JIKJZRBPJ","short_pith_number":"pith:CRNKLE2R","canonical_record":{"source":{"id":"2412.13924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:07:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d5a044670f601f5406a28b71e997149b733bc60905006310395887429a3081c","abstract_canon_sha256":"5f749a86ff1afed80ea12522069c88af21cb41d1a56053ac64f4ee9292380bac"},"schema_version":"1.0"},"canonical_sha256":"145aa59351acfdf96523f250a4e6217a721d918f5478fda20b09c5dcefa66cb8","source":{"kind":"arxiv","id":"2412.13924","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13924","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13924v1","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13924","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_12","alias_value":"CRNKLE2RVT67","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_16","alias_value":"CRNKLE2RVT67SZJD","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_8","alias_value":"CRNKLE2R","created_at":"2026-07-05T09:51:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CRNKLE2RVT67SZJD6JIKJZRBPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:07:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d5a044670f601f5406a28b71e997149b733bc60905006310395887429a3081c","abstract_canon_sha256":"5f749a86ff1afed80ea12522069c88af21cb41d1a56053ac64f4ee9292380bac"},"schema_version":"1.0"},"canonical_sha256":"145aa59351acfdf96523f250a4e6217a721d918f5478fda20b09c5dcefa66cb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:10.917350Z","signature_b64":"5BenX3Itv10rvAOuN3oT4Y1d6Lx43zdBywJXk25nnj3ZHOSjyzm3C/uS8vO1+NgSmahrCp4nCOY8YKK7owXeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"145aa59351acfdf96523f250a4e6217a721d918f5478fda20b09c5dcefa66cb8","last_reissued_at":"2026-07-05T09:51:10.916710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:10.916710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13924","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":"2026-07-05T09:51:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmHE6CQRHuzfWRiF/BvMhMPe5435ed+jGUd3C2KusSucP55sOu2XjZpflD8b8q9Z7PuYGUVfjzPUR0vzx+cmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:05:05.393679Z"},"content_sha256":"d77d50b5c815cc38550d20c4ae372fe20030f6080c4ab0b694d3bf7aa8e66073","schema_version":"1.0","event_id":"sha256:d77d50b5c815cc38550d20c4ae372fe20030f6080c4ab0b694d3bf7aa8e66073"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CRNKLE2RVT67SZJD6JIKJZRBPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language verY Rare for All","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amos Wolf, Ibrahim Merad, Yannick L\\'eo, Ziad Mazzawi","submitted_at":"2024-12-18T15:07:23Z","abstract_excerpt":"In the quest to overcome language barriers, encoder-decoder models like NLLB have expanded machine translation to rare languages, with some models (e.g., NLLB 1.3B) even trainable on a single GPU. While general-purpose LLMs perform well in translation, open LLMs prove highly competitive when fine-tuned for specific tasks involving unknown corpora. We introduce LYRA (Language verY Rare for All), a novel approach that combines open LLM fine-tuning, retrieval-augmented generation (RAG), and transfer learning from related high-resource languages. This study is exclusively focused on single-GPU tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13924","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/2412.13924/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":"2026-07-05T09:51:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p30/kTTikKNUjzwWIxyK1UnTsfbdx9MDxczRS2GGjdMhyOvcZtkrancPA+86DqaqqghMnBgI8aKtPgQmH73GDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:05:05.394199Z"},"content_sha256":"12e7ea2e98e1eecb164a4c76b3a0460ac25c7bec42c77cf2fac65b14bee5f3fe","schema_version":"1.0","event_id":"sha256:12e7ea2e98e1eecb164a4c76b3a0460ac25c7bec42c77cf2fac65b14bee5f3fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRNKLE2RVT67SZJD6JIKJZRBPJ/bundle.json","state_url":"https://pith.science/pith/CRNKLE2RVT67SZJD6JIKJZRBPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRNKLE2RVT67SZJD6JIKJZRBPJ/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":"2026-08-15T10:05:05Z","links":{"resolver":"https://pith.science/pith/CRNKLE2RVT67SZJD6JIKJZRBPJ","bundle":"https://pith.science/pith/CRNKLE2RVT67SZJD6JIKJZRBPJ/bundle.json","state":"https://pith.science/pith/CRNKLE2RVT67SZJD6JIKJZRBPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRNKLE2RVT67SZJD6JIKJZRBPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CRNKLE2RVT67SZJD6JIKJZRBPJ","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":"5f749a86ff1afed80ea12522069c88af21cb41d1a56053ac64f4ee9292380bac","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:07:23Z","title_canon_sha256":"3d5a044670f601f5406a28b71e997149b733bc60905006310395887429a3081c"},"schema_version":"1.0","source":{"id":"2412.13924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13924","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13924v1","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13924","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_12","alias_value":"CRNKLE2RVT67","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_16","alias_value":"CRNKLE2RVT67SZJD","created_at":"2026-07-05T09:51:10Z"},{"alias_kind":"pith_short_8","alias_value":"CRNKLE2R","created_at":"2026-07-05T09:51:10Z"}],"graph_snapshots":[{"event_id":"sha256:12e7ea2e98e1eecb164a4c76b3a0460ac25c7bec42c77cf2fac65b14bee5f3fe","target":"graph","created_at":"2026-07-05T09:51:10Z","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/2412.13924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the quest to overcome language barriers, encoder-decoder models like NLLB have expanded machine translation to rare languages, with some models (e.g., NLLB 1.3B) even trainable on a single GPU. While general-purpose LLMs perform well in translation, open LLMs prove highly competitive when fine-tuned for specific tasks involving unknown corpora. We introduce LYRA (Language verY Rare for All), a novel approach that combines open LLM fine-tuning, retrieval-augmented generation (RAG), and transfer learning from related high-resource languages. This study is exclusively focused on single-GPU tra","authors_text":"Amos Wolf, Ibrahim Merad, Yannick L\\'eo, Ziad Mazzawi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:07:23Z","title":"Language verY Rare for All"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13924","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:d77d50b5c815cc38550d20c4ae372fe20030f6080c4ab0b694d3bf7aa8e66073","target":"record","created_at":"2026-07-05T09:51:10Z","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":"5f749a86ff1afed80ea12522069c88af21cb41d1a56053ac64f4ee9292380bac","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T15:07:23Z","title_canon_sha256":"3d5a044670f601f5406a28b71e997149b733bc60905006310395887429a3081c"},"schema_version":"1.0","source":{"id":"2412.13924","kind":"arxiv","version":1}},"canonical_sha256":"145aa59351acfdf96523f250a4e6217a721d918f5478fda20b09c5dcefa66cb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"145aa59351acfdf96523f250a4e6217a721d918f5478fda20b09c5dcefa66cb8","first_computed_at":"2026-07-05T09:51:10.916710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:10.916710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5BenX3Itv10rvAOuN3oT4Y1d6Lx43zdBywJXk25nnj3ZHOSjyzm3C/uS8vO1+NgSmahrCp4nCOY8YKK7owXeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:10.917350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d77d50b5c815cc38550d20c4ae372fe20030f6080c4ab0b694d3bf7aa8e66073","sha256:12e7ea2e98e1eecb164a4c76b3a0460ac25c7bec42c77cf2fac65b14bee5f3fe"],"state_sha256":"5d08a38e4413e733e0eeea7318f9d5408a89714066ff153f24b060f8f99cb38d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JDVbJFBP47bCYNw5BFaGyBbCwtP7wepXCS/XyJP5V/9Ie2mC4In6yvvy0/16XjF6pyc5wsMhH4c+PcqRNmxJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:05:05.398169Z","bundle_sha256":"cb7ff9a678aaf1ebf8761b7426c2f3dc4d206f0b048ee6327f078700208a08f2"}}