{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YVDPPYLUO4UEMT3WSOH72SH36J","short_pith_number":"pith:YVDPPYLU","canonical_record":{"source":{"id":"2408.11294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T02:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"38da9a223a0d2e0ca2c1a3bde7ae2842370742455b97019221005c3814b83ede","abstract_canon_sha256":"f6b06dc12df944e4f39e1adb2268edf25ebf43a64aab13f71249ad166552f098"},"schema_version":"1.0"},"canonical_sha256":"c546f7e1747728464f76938ffd48fbf2596f0b4e318625a99c5aaeec20ed790e","source":{"kind":"arxiv","id":"2408.11294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11294","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11294v1","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11294","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"YVDPPYLUO4UE","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"YVDPPYLUO4UEMT3W","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"YVDPPYLU","created_at":"2026-07-05T08:57:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YVDPPYLUO4UEMT3WSOH72SH36J","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T02:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"38da9a223a0d2e0ca2c1a3bde7ae2842370742455b97019221005c3814b83ede","abstract_canon_sha256":"f6b06dc12df944e4f39e1adb2268edf25ebf43a64aab13f71249ad166552f098"},"schema_version":"1.0"},"canonical_sha256":"c546f7e1747728464f76938ffd48fbf2596f0b4e318625a99c5aaeec20ed790e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:41.512188Z","signature_b64":"NuIHj2pU+eULdq2hbVcA3oIn2BlXzksth7CsWxp6hCW1z55MheOUGm9Uya6+/Qsj3+ibNOMEdm5xkY3UMfewAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c546f7e1747728464f76938ffd48fbf2596f0b4e318625a99c5aaeec20ed790e","last_reissued_at":"2026-07-05T08:57:41.511769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:41.511769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11294","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":"2026-07-05T08:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/ufw0J98VGHmLbV/WG5N1z+tVJB/pkC076kFu4td0EnbdNcR76wAqwMWFiekF5BT8brQSO5RaO7xojfZXW7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:09:29.531898Z"},"content_sha256":"f1299461505378f5cf9f3bd086b3b0b3fefb7be5f07772da6e811a916fceaa5f","schema_version":"1.0","event_id":"sha256:f1299461505378f5cf9f3bd086b3b0b3fefb7be5f07772da6e811a916fceaa5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YVDPPYLUO4UEMT3WSOH72SH36J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RedWhale: An Adapted Korean LLM Through Efficient Continual Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh-Dung Vo, Daewoo Choi, Minseong Jung, Wonbeen Lee","submitted_at":"2024-08-21T02:49:41Z","abstract_excerpt":"The field of Natural Language Processing (NLP) has seen significant advancements with the development of Large Language Models (LLMs). However, much of this research remains focused on English, often overlooking low-resource languages like Korean. This oversight presents challenges due to the unique non-alphabetic token structure of Korean and the substantial memory and computational demands required for LLM training, which frequently lead to memory constraints and out-of-memory errors. To address these issues, we present RedWhale, a model specifically tailored for Korean language processing. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11294","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/2408.11294/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":"2026-07-05T08:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"joADtMfaFXUFk0xy7x5jvf4Mf4kCC810hOEJ7OW000RcZMXadbyJbkfsHFDUiFsEOQHgP8z6CeD+gKco7X+4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:09:29.532406Z"},"content_sha256":"7888d365cce967cc27664b6f9d4f249de0d4c1ea0a8d85902565aed75be38951","schema_version":"1.0","event_id":"sha256:7888d365cce967cc27664b6f9d4f249de0d4c1ea0a8d85902565aed75be38951"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVDPPYLUO4UEMT3WSOH72SH36J/bundle.json","state_url":"https://pith.science/pith/YVDPPYLUO4UEMT3WSOH72SH36J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVDPPYLUO4UEMT3WSOH72SH36J/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":"2026-08-05T08:09:29Z","links":{"resolver":"https://pith.science/pith/YVDPPYLUO4UEMT3WSOH72SH36J","bundle":"https://pith.science/pith/YVDPPYLUO4UEMT3WSOH72SH36J/bundle.json","state":"https://pith.science/pith/YVDPPYLUO4UEMT3WSOH72SH36J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVDPPYLUO4UEMT3WSOH72SH36J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YVDPPYLUO4UEMT3WSOH72SH36J","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":"f6b06dc12df944e4f39e1adb2268edf25ebf43a64aab13f71249ad166552f098","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T02:49:41Z","title_canon_sha256":"38da9a223a0d2e0ca2c1a3bde7ae2842370742455b97019221005c3814b83ede"},"schema_version":"1.0","source":{"id":"2408.11294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11294","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11294v1","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11294","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"YVDPPYLUO4UE","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"YVDPPYLUO4UEMT3W","created_at":"2026-07-05T08:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"YVDPPYLU","created_at":"2026-07-05T08:57:41Z"}],"graph_snapshots":[{"event_id":"sha256:7888d365cce967cc27664b6f9d4f249de0d4c1ea0a8d85902565aed75be38951","target":"graph","created_at":"2026-07-05T08:57:41Z","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/2408.11294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of Natural Language Processing (NLP) has seen significant advancements with the development of Large Language Models (LLMs). However, much of this research remains focused on English, often overlooking low-resource languages like Korean. This oversight presents challenges due to the unique non-alphabetic token structure of Korean and the substantial memory and computational demands required for LLM training, which frequently lead to memory constraints and out-of-memory errors. To address these issues, we present RedWhale, a model specifically tailored for Korean language processing. ","authors_text":"Anh-Dung Vo, Daewoo Choi, Minseong Jung, Wonbeen Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T02:49:41Z","title":"RedWhale: An Adapted Korean LLM Through Efficient Continual Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11294","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:f1299461505378f5cf9f3bd086b3b0b3fefb7be5f07772da6e811a916fceaa5f","target":"record","created_at":"2026-07-05T08:57:41Z","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":"f6b06dc12df944e4f39e1adb2268edf25ebf43a64aab13f71249ad166552f098","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T02:49:41Z","title_canon_sha256":"38da9a223a0d2e0ca2c1a3bde7ae2842370742455b97019221005c3814b83ede"},"schema_version":"1.0","source":{"id":"2408.11294","kind":"arxiv","version":1}},"canonical_sha256":"c546f7e1747728464f76938ffd48fbf2596f0b4e318625a99c5aaeec20ed790e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c546f7e1747728464f76938ffd48fbf2596f0b4e318625a99c5aaeec20ed790e","first_computed_at":"2026-07-05T08:57:41.511769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:41.511769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NuIHj2pU+eULdq2hbVcA3oIn2BlXzksth7CsWxp6hCW1z55MheOUGm9Uya6+/Qsj3+ibNOMEdm5xkY3UMfewAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:41.512188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1299461505378f5cf9f3bd086b3b0b3fefb7be5f07772da6e811a916fceaa5f","sha256:7888d365cce967cc27664b6f9d4f249de0d4c1ea0a8d85902565aed75be38951"],"state_sha256":"64d2774bef19e259053ba16cc652f3249564dfceb13a9c5a2490c05d674a67a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OLckS1uGqfA+YCFB7jhpwjT4a2QXy93pj5palOC+qMfadQDqmcKqKwlpMJI3yvDG9L4Tw0ecD1426ZDVeBjCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:09:29.536331Z","bundle_sha256":"71042ff746de9376424b14d45938c0e53d4d511319886d1fcebb68520834d09e"}}