{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:72GNJHZQL3BEBYLYTTWXO7G3UP","short_pith_number":"pith:72GNJHZQ","canonical_record":{"source":{"id":"2412.02775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T19:17:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0f14cf0590aaf7d6bad0567c584fdcc902fad949012ed68f06944183e917b544","abstract_canon_sha256":"973ba65cee83d88023dac46d7ddfc5f55530fd8e055f5b1114821d93fe38624f"},"schema_version":"1.0"},"canonical_sha256":"fe8cd49f305ec240e1789ced777cdba3eed0386d928436269afbf85277fba7ec","source":{"kind":"arxiv","id":"2412.02775","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02775","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02775v1","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02775","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"72GNJHZQL3BE","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"72GNJHZQL3BEBYLY","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"72GNJHZQ","created_at":"2026-07-05T09:44:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:72GNJHZQL3BEBYLYTTWXO7G3UP","target":"record","payload":{"canonical_record":{"source":{"id":"2412.02775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T19:17:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0f14cf0590aaf7d6bad0567c584fdcc902fad949012ed68f06944183e917b544","abstract_canon_sha256":"973ba65cee83d88023dac46d7ddfc5f55530fd8e055f5b1114821d93fe38624f"},"schema_version":"1.0"},"canonical_sha256":"fe8cd49f305ec240e1789ced777cdba3eed0386d928436269afbf85277fba7ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:19.323842Z","signature_b64":"1Qwg98GWqxSq7j/lEZr3Wr6DCDtuCek54/A4jJ8WQgWX0T+qQRss9JtaC/QagA8gUcsZq61xj+aSogUrRj0vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe8cd49f305ec240e1789ced777cdba3eed0386d928436269afbf85277fba7ec","last_reissued_at":"2026-07-05T09:44:19.323397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:19.323397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.02775","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":"2026-07-05T09:44:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQgDTLpwotNVz4Aaxu5tFqdADhJQ+FRqJRdEBm5pGZE9E8s0jlLKMfIdS9Vvxh913lBqnzuEm2ifkfnpZh8ZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:20:36.244176Z"},"content_sha256":"ecbdbfb8f97db3251da8aa40df0445e70f1263555c952cd445631b307056a29e","schema_version":"1.0","event_id":"sha256:ecbdbfb8f97db3251da8aa40df0445e70f1263555c952cd445631b307056a29e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:72GNJHZQL3BEBYLYTTWXO7G3UP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Zeer, Atahan Uz, Elif Ince, Eren Dogan, H. Toprak Kesgin, M. Egemen Uzun, M. Fatih Amasyali, M. Kaan Yuce, Osama Shbib, Yusuf Erdem","submitted_at":"2024-12-03T19:17:18Z","abstract_excerpt":"In this study, we develop and assess new corpus selection and training methodologies to improve the effectiveness of Turkish language models. Specifically, we adapted Large Language Model generated datasets and translated English datasets into Turkish, integrating these resources into the training process. This approach led to substantial enhancements in model accuracy for both few-shot and zero-shot learning scenarios. Furthermore, the merging of these adapted models was found to markedly improve their performance. Human evaluative metrics, including task-specific performance assessments, fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02775","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/2412.02775/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":"2026-07-05T09:44:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"411umAUWoNYEG3RPWVmK6+2Kwm/KrqZMzQZcdgIFzPx2RPBg1ktJlsdnVKfNID5rWuFZPMrMJ1TgwXlf8Z/QCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:20:36.244887Z"},"content_sha256":"42bb8ad3f589bd982f3c12a82c393a93c06b054c704906f12c5f2c12386ae806","schema_version":"1.0","event_id":"sha256:42bb8ad3f589bd982f3c12a82c393a93c06b054c704906f12c5f2c12386ae806"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72GNJHZQL3BEBYLYTTWXO7G3UP/bundle.json","state_url":"https://pith.science/pith/72GNJHZQL3BEBYLYTTWXO7G3UP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72GNJHZQL3BEBYLYTTWXO7G3UP/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":"2026-08-19T15:20:36Z","links":{"resolver":"https://pith.science/pith/72GNJHZQL3BEBYLYTTWXO7G3UP","bundle":"https://pith.science/pith/72GNJHZQL3BEBYLYTTWXO7G3UP/bundle.json","state":"https://pith.science/pith/72GNJHZQL3BEBYLYTTWXO7G3UP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72GNJHZQL3BEBYLYTTWXO7G3UP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:72GNJHZQL3BEBYLYTTWXO7G3UP","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":"973ba65cee83d88023dac46d7ddfc5f55530fd8e055f5b1114821d93fe38624f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T19:17:18Z","title_canon_sha256":"0f14cf0590aaf7d6bad0567c584fdcc902fad949012ed68f06944183e917b544"},"schema_version":"1.0","source":{"id":"2412.02775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02775","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02775v1","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02775","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"72GNJHZQL3BE","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"72GNJHZQL3BEBYLY","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"72GNJHZQ","created_at":"2026-07-05T09:44:19Z"}],"graph_snapshots":[{"event_id":"sha256:42bb8ad3f589bd982f3c12a82c393a93c06b054c704906f12c5f2c12386ae806","target":"graph","created_at":"2026-07-05T09:44:19Z","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/2412.02775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we develop and assess new corpus selection and training methodologies to improve the effectiveness of Turkish language models. Specifically, we adapted Large Language Model generated datasets and translated English datasets into Turkish, integrating these resources into the training process. This approach led to substantial enhancements in model accuracy for both few-shot and zero-shot learning scenarios. Furthermore, the merging of these adapted models was found to markedly improve their performance. Human evaluative metrics, including task-specific performance assessments, fur","authors_text":"Ahmed Zeer, Atahan Uz, Elif Ince, Eren Dogan, H. Toprak Kesgin, M. Egemen Uzun, M. Fatih Amasyali, M. Kaan Yuce, Osama Shbib, Yusuf Erdem","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T19:17:18Z","title":"Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02775","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:ecbdbfb8f97db3251da8aa40df0445e70f1263555c952cd445631b307056a29e","target":"record","created_at":"2026-07-05T09:44:19Z","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":"973ba65cee83d88023dac46d7ddfc5f55530fd8e055f5b1114821d93fe38624f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T19:17:18Z","title_canon_sha256":"0f14cf0590aaf7d6bad0567c584fdcc902fad949012ed68f06944183e917b544"},"schema_version":"1.0","source":{"id":"2412.02775","kind":"arxiv","version":1}},"canonical_sha256":"fe8cd49f305ec240e1789ced777cdba3eed0386d928436269afbf85277fba7ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe8cd49f305ec240e1789ced777cdba3eed0386d928436269afbf85277fba7ec","first_computed_at":"2026-07-05T09:44:19.323397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:19.323397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Qwg98GWqxSq7j/lEZr3Wr6DCDtuCek54/A4jJ8WQgWX0T+qQRss9JtaC/QagA8gUcsZq61xj+aSogUrRj0vAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:19.323842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecbdbfb8f97db3251da8aa40df0445e70f1263555c952cd445631b307056a29e","sha256:42bb8ad3f589bd982f3c12a82c393a93c06b054c704906f12c5f2c12386ae806"],"state_sha256":"d6d15f51d6f62029e51bb7f4430d1d1d0fd324267e64486d44f2eef5864f53e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8rdv8ifJ9pqVRSMatgTGFzLEdnDM+H3WGQYrKWbhN8mGpUDBN9fcRZZYL+EjP603HadnHhLBRoVeeLU/rErFAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:20:36.252677Z","bundle_sha256":"a0231e98531e53fda7d935da6acec1526a973665915e94e34df963e309c2fd97"}}