{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F7JE4VLRLJQF5WBZY7XSQUMGOI","short_pith_number":"pith:F7JE4VLR","canonical_record":{"source":{"id":"2509.03972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T07:56:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a3a0f6d7be6ad46952d8466912fb0f868832e7646761ba9c121af0b5b0cf09ad","abstract_canon_sha256":"bfea9fceecd29afc592cc2723fd854a0829e9a92fba4d5d88e1d4a864d398434"},"schema_version":"1.0"},"canonical_sha256":"2fd24e55715a605ed839c7ef2851867207451947689830ec956e8eee70d35036","source":{"kind":"arxiv","id":"2509.03972","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03972","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03972v1","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03972","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"F7JE4VLRLJQF","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"F7JE4VLRLJQF5WBZ","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"F7JE4VLR","created_at":"2026-07-05T12:04:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F7JE4VLRLJQF5WBZY7XSQUMGOI","target":"record","payload":{"canonical_record":{"source":{"id":"2509.03972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T07:56:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a3a0f6d7be6ad46952d8466912fb0f868832e7646761ba9c121af0b5b0cf09ad","abstract_canon_sha256":"bfea9fceecd29afc592cc2723fd854a0829e9a92fba4d5d88e1d4a864d398434"},"schema_version":"1.0"},"canonical_sha256":"2fd24e55715a605ed839c7ef2851867207451947689830ec956e8eee70d35036","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:50.779266Z","signature_b64":"Q91NtjrWTcyFA43WEZrlVTD5YnLT0P8/hFmDS1w0qFTQTgkaT3kFPxxF6D563JCHkr7bIJy78/Ie4BOh9wBuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fd24e55715a605ed839c7ef2851867207451947689830ec956e8eee70d35036","last_reissued_at":"2026-07-05T12:04:50.778812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:50.778812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.03972","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":"2026-07-05T12:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"37ceUGuAyGhp6i636DPqzP1jymezdx8smaDtFebYgsJR9X3/vgFiOJyOm3+CD9dcNGmOd1OmruHp7/N3tKGbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:35:31.478400Z"},"content_sha256":"e23383fd52908d9c0664bf13fb4a73f4b64b49a5bc4103400da363d9fbc21fe0","schema_version":"1.0","event_id":"sha256:e23383fd52908d9c0664bf13fb4a73f4b64b49a5bc4103400da363d9fbc21fe0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F7JE4VLRLJQF5WBZY7XSQUMGOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Beomgyu Kim, Changseok Song, Daewon Suh, Dahye Choi, Dongpin Oh, Dongseok Kim, Gangwon Jo, Haesol Lee, Jaeyeon Huh, Jangwoong Kim, Jeesoo Lee, Jihwan Kim, Jiyoung Park, Junghwan Lim, Junhyeok Lee, Kibong Choi, Sungmin Lee, Taehyun Kim, Wai Ting Cheung","submitted_at":"2025-09-04T07:56:24Z","abstract_excerpt":"We introduce Llama-3-Motif, a language model consisting of 102 billion parameters, specifically designed to enhance Korean capabilities while retaining strong performance in English. Developed on the Llama 3 architecture, Llama-3-Motif employs advanced training techniques, including LlamaPro and Masked Structure Growth, to effectively scale the model without altering its core Transformer architecture. Using the MoAI platform for efficient training across hyperscale GPU clusters, we optimized Llama-3-Motif using a carefully curated dataset that maintains a balanced ratio of Korean and English d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03972","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/2509.03972/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":"2026-07-05T12:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AaZ0meuwDudcWNTGWklPYOjRehEGF8FFEmhFzv6hh2DNqIs3YntTvPaQwWaVGZP0Hf/RYltzyGjt2U89NrcoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:35:31.479431Z"},"content_sha256":"e8fc83c49f6f5791e3a1ccc39607c068b65b289c8f7e1aae68342ea46c87e51f","schema_version":"1.0","event_id":"sha256:e8fc83c49f6f5791e3a1ccc39607c068b65b289c8f7e1aae68342ea46c87e51f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7JE4VLRLJQF5WBZY7XSQUMGOI/bundle.json","state_url":"https://pith.science/pith/F7JE4VLRLJQF5WBZY7XSQUMGOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7JE4VLRLJQF5WBZY7XSQUMGOI/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":"2026-08-10T20:35:31Z","links":{"resolver":"https://pith.science/pith/F7JE4VLRLJQF5WBZY7XSQUMGOI","bundle":"https://pith.science/pith/F7JE4VLRLJQF5WBZY7XSQUMGOI/bundle.json","state":"https://pith.science/pith/F7JE4VLRLJQF5WBZY7XSQUMGOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7JE4VLRLJQF5WBZY7XSQUMGOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F7JE4VLRLJQF5WBZY7XSQUMGOI","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":"bfea9fceecd29afc592cc2723fd854a0829e9a92fba4d5d88e1d4a864d398434","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T07:56:24Z","title_canon_sha256":"a3a0f6d7be6ad46952d8466912fb0f868832e7646761ba9c121af0b5b0cf09ad"},"schema_version":"1.0","source":{"id":"2509.03972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03972","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03972v1","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03972","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"F7JE4VLRLJQF","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"F7JE4VLRLJQF5WBZ","created_at":"2026-07-05T12:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"F7JE4VLR","created_at":"2026-07-05T12:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:e8fc83c49f6f5791e3a1ccc39607c068b65b289c8f7e1aae68342ea46c87e51f","target":"graph","created_at":"2026-07-05T12:04:50Z","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/2509.03972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Llama-3-Motif, a language model consisting of 102 billion parameters, specifically designed to enhance Korean capabilities while retaining strong performance in English. Developed on the Llama 3 architecture, Llama-3-Motif employs advanced training techniques, including LlamaPro and Masked Structure Growth, to effectively scale the model without altering its core Transformer architecture. Using the MoAI platform for efficient training across hyperscale GPU clusters, we optimized Llama-3-Motif using a carefully curated dataset that maintains a balanced ratio of Korean and English d","authors_text":"Beomgyu Kim, Changseok Song, Daewon Suh, Dahye Choi, Dongpin Oh, Dongseok Kim, Gangwon Jo, Haesol Lee, Jaeyeon Huh, Jangwoong Kim, Jeesoo Lee, Jihwan Kim, Jiyoung Park, Junghwan Lim, Junhyeok Lee, Kibong Choi, Sungmin Lee, Taehyun Kim, Wai Ting Cheung","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T07:56:24Z","title":"Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03972","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:e23383fd52908d9c0664bf13fb4a73f4b64b49a5bc4103400da363d9fbc21fe0","target":"record","created_at":"2026-07-05T12:04:50Z","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":"bfea9fceecd29afc592cc2723fd854a0829e9a92fba4d5d88e1d4a864d398434","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T07:56:24Z","title_canon_sha256":"a3a0f6d7be6ad46952d8466912fb0f868832e7646761ba9c121af0b5b0cf09ad"},"schema_version":"1.0","source":{"id":"2509.03972","kind":"arxiv","version":1}},"canonical_sha256":"2fd24e55715a605ed839c7ef2851867207451947689830ec956e8eee70d35036","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fd24e55715a605ed839c7ef2851867207451947689830ec956e8eee70d35036","first_computed_at":"2026-07-05T12:04:50.778812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:50.778812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q91NtjrWTcyFA43WEZrlVTD5YnLT0P8/hFmDS1w0qFTQTgkaT3kFPxxF6D563JCHkr7bIJy78/Ie4BOh9wBuAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:50.779266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e23383fd52908d9c0664bf13fb4a73f4b64b49a5bc4103400da363d9fbc21fe0","sha256:e8fc83c49f6f5791e3a1ccc39607c068b65b289c8f7e1aae68342ea46c87e51f"],"state_sha256":"137409dc0a80fc00f55bfe40eb524514c44976bbd74d560cd146ce38c94a3f2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KrINyaiXI0NfnHKrUML4CMxBVmg2Mh88AMJ/i92cxRY1BbId0TZ2rlwjvcMmFaLPPvTq3hT9HFp1PdfwHWtoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:35:31.485032Z","bundle_sha256":"8e3d9c2c56d09b5a69db6991826ff16ea7030fb1601973b7bd933f541c6bfa6d"}}