{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7MB4UJDBVWSXDU45YPCYXXRI77","short_pith_number":"pith:7MB4UJDB","canonical_record":{"source":{"id":"2405.07745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T13:41:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"69b10ad064fb7fe49228cfd6c6d63c1d696e1479d745b2a3c9790137066b6efa","abstract_canon_sha256":"070898939c5f22d86371e876997e0d5d7e255bc6d80467f600529d4a501ba1a7"},"schema_version":"1.0"},"canonical_sha256":"fb03ca2461ada571d39dc3c58bde28ffd080e72cd16f21233b12591e3a4dc0a7","source":{"kind":"arxiv","id":"2405.07745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07745","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07745v1","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07745","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"7MB4UJDBVWSX","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"7MB4UJDBVWSXDU45","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"7MB4UJDB","created_at":"2026-07-05T08:18:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7MB4UJDBVWSXDU45YPCYXXRI77","target":"record","payload":{"canonical_record":{"source":{"id":"2405.07745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T13:41:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"69b10ad064fb7fe49228cfd6c6d63c1d696e1479d745b2a3c9790137066b6efa","abstract_canon_sha256":"070898939c5f22d86371e876997e0d5d7e255bc6d80467f600529d4a501ba1a7"},"schema_version":"1.0"},"canonical_sha256":"fb03ca2461ada571d39dc3c58bde28ffd080e72cd16f21233b12591e3a4dc0a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:27.080809Z","signature_b64":"k7UFu1UWWFsLArTvGCHxGWJ1X+MPHw2A0C7bXwqR63uDENcDYrR45KB/rrE/wIgR946NiVs/nREovhQqLoyJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb03ca2461ada571d39dc3c58bde28ffd080e72cd16f21233b12591e3a4dc0a7","last_reissued_at":"2026-07-05T08:18:27.080416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:27.080416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.07745","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":"2026-07-05T08:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AiGoI00HC2ZAMWghqvt37SOkOfqbHff7S29kAkFYV6lroJpIEZaGyafgT+eF2u7Ym1Mu8rgd3+98wizvRv2GDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T09:18:11.237594Z"},"content_sha256":"240af288c2b181af6f6072faa0d9ae0f5cd0086e1550b63d83da5d28141bc8d9","schema_version":"1.0","event_id":"sha256:240af288c2b181af6f6072faa0d9ae0f5cd0086e1550b63d83da5d28141bc8d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7MB4UJDBVWSXDU45YPCYXXRI77","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cagri Toraman","submitted_at":"2024-05-13T13:41:59Z","abstract_excerpt":"Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and multilingual pretraining. Monolingual pretraining is expensive due to hardware requirements, and multilingual models often have uneven performance across languages. This study explores an alternative solution by adapting large language models, primarily trained on English, to low-resource languages. We assess various strategies, including continual training, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07745","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/2405.07745/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":"2026-07-05T08:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHmeOS14tWex/23V1qd3USI4DMNo/DloRgiv1KjchFaFmnj9/S610ncehsjOOYi8Tlo4WeLlLPk7ehBAVBZ0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T09:18:11.238010Z"},"content_sha256":"f314b366fc65515aae6e4d882378b84953b417f9585cd867d07ec29fbb6172fd","schema_version":"1.0","event_id":"sha256:f314b366fc65515aae6e4d882378b84953b417f9585cd867d07ec29fbb6172fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MB4UJDBVWSXDU45YPCYXXRI77/bundle.json","state_url":"https://pith.science/pith/7MB4UJDBVWSXDU45YPCYXXRI77/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MB4UJDBVWSXDU45YPCYXXRI77/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":"2026-07-14T09:18:11Z","links":{"resolver":"https://pith.science/pith/7MB4UJDBVWSXDU45YPCYXXRI77","bundle":"https://pith.science/pith/7MB4UJDBVWSXDU45YPCYXXRI77/bundle.json","state":"https://pith.science/pith/7MB4UJDBVWSXDU45YPCYXXRI77/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MB4UJDBVWSXDU45YPCYXXRI77/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7MB4UJDBVWSXDU45YPCYXXRI77","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":"070898939c5f22d86371e876997e0d5d7e255bc6d80467f600529d4a501ba1a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T13:41:59Z","title_canon_sha256":"69b10ad064fb7fe49228cfd6c6d63c1d696e1479d745b2a3c9790137066b6efa"},"schema_version":"1.0","source":{"id":"2405.07745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07745","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07745v1","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07745","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"7MB4UJDBVWSX","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"7MB4UJDBVWSXDU45","created_at":"2026-07-05T08:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"7MB4UJDB","created_at":"2026-07-05T08:18:27Z"}],"graph_snapshots":[{"event_id":"sha256:f314b366fc65515aae6e4d882378b84953b417f9585cd867d07ec29fbb6172fd","target":"graph","created_at":"2026-07-05T08:18:27Z","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/2405.07745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and multilingual pretraining. Monolingual pretraining is expensive due to hardware requirements, and multilingual models often have uneven performance across languages. This study explores an alternative solution by adapting large language models, primarily trained on English, to low-resource languages. We assess various strategies, including continual training, i","authors_text":"Cagri Toraman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T13:41:59Z","title":"LlamaTurk: Adapting Open-Source Generative Large Language Models for Low-Resource Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07745","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":"sha256:240af288c2b181af6f6072faa0d9ae0f5cd0086e1550b63d83da5d28141bc8d9","target":"record","created_at":"2026-07-05T08:18:27Z","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":"070898939c5f22d86371e876997e0d5d7e255bc6d80467f600529d4a501ba1a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T13:41:59Z","title_canon_sha256":"69b10ad064fb7fe49228cfd6c6d63c1d696e1479d745b2a3c9790137066b6efa"},"schema_version":"1.0","source":{"id":"2405.07745","kind":"arxiv","version":1}},"canonical_sha256":"fb03ca2461ada571d39dc3c58bde28ffd080e72cd16f21233b12591e3a4dc0a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb03ca2461ada571d39dc3c58bde28ffd080e72cd16f21233b12591e3a4dc0a7","first_computed_at":"2026-07-05T08:18:27.080416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:27.080416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k7UFu1UWWFsLArTvGCHxGWJ1X+MPHw2A0C7bXwqR63uDENcDYrR45KB/rrE/wIgR946NiVs/nREovhQqLoyJCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:27.080809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.07745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:240af288c2b181af6f6072faa0d9ae0f5cd0086e1550b63d83da5d28141bc8d9","sha256:f314b366fc65515aae6e4d882378b84953b417f9585cd867d07ec29fbb6172fd"],"state_sha256":"9e65b7ffc7ef3ae3e551f1d8c36126b1fdef184e0c0cc833dbd8187898f04b70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1X6vBa577HGxoCDSZNtlaa1G73/z4v0ExSDj6bu4lIte9dqSZubGOGV6pAioJ8Hgkg1RG95ByferYfUCGqmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T09:18:11.240584Z","bundle_sha256":"ec8c103d956f53d80e1e4a86c179ca2e149a1087855dbf85259755aa4009d983"}}