{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5UFY6S276NHLM7SNOUTQKKLMVL","short_pith_number":"pith:5UFY6S27","canonical_record":{"source":{"id":"2405.15640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T15:30:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e0d20f859fb45d2b0048a59e6636244c6d768a9c2d2d603ac70eb52550789eb","abstract_canon_sha256":"a98ec6c194ff18789cda348b78348cb91a776e4215ae59f892c1ac29056e752a"},"schema_version":"1.0"},"canonical_sha256":"ed0b8f4b5ff34eb67e4d752705296caac0a3f3eac2b2c27de42d8978ad3ea60b","source":{"kind":"arxiv","id":"2405.15640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15640","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15640v1","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15640","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"5UFY6S276NHL","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"5UFY6S276NHLM7SN","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"5UFY6S27","created_at":"2026-07-05T08:22:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5UFY6S276NHLM7SNOUTQKKLMVL","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T15:30:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e0d20f859fb45d2b0048a59e6636244c6d768a9c2d2d603ac70eb52550789eb","abstract_canon_sha256":"a98ec6c194ff18789cda348b78348cb91a776e4215ae59f892c1ac29056e752a"},"schema_version":"1.0"},"canonical_sha256":"ed0b8f4b5ff34eb67e4d752705296caac0a3f3eac2b2c27de42d8978ad3ea60b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:52.011160Z","signature_b64":"XCnKXQn2mBbU8Q7zjubGLxigKlus9UJ5jChnC/rhYA9L0VWVywR7LDafAOn6d6hzsrSxpG5ZipZ1v2jH2E8XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed0b8f4b5ff34eb67e4d752705296caac0a3f3eac2b2c27de42d8978ad3ea60b","last_reissued_at":"2026-07-05T08:22:52.010671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:52.010671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15640","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":"2026-07-05T08:22:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WFrP7j/tC0l1Osy2s1tGVledea/xuhGYUCnfowhvWoIfxicIHffoJOMzTec3d1Pl6jJNYnIH28nT9m6uIVdlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:21:48.599544Z"},"content_sha256":"e59246d91ef9248870b5935cde7781e64f5ff4c36a185dac76fb9f1cc45a8699","schema_version":"1.0","event_id":"sha256:e59246d91ef9248870b5935cde7781e64f5ff4c36a185dac76fb9f1cc45a8699"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5UFY6S276NHLM7SNOUTQKKLMVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GECKO: Generative Language Model for English, Code and Korean","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Donggyu Kim, Sungwoo Oh","submitted_at":"2024-05-24T15:30:41Z","abstract_excerpt":"We introduce GECKO, a bilingual large language model (LLM) optimized for Korean and English, along with programming languages. GECKO is pretrained on the balanced, high-quality corpus of Korean and English employing LLaMA architecture. In this report, we share the experiences of several efforts to build a better data pipeline for the corpus and to train our model. GECKO shows great efficiency in token generations for both Korean and English, despite its small size of vocabulary. We measure the performance on the representative benchmarks in terms of Korean, English and Code, and it exhibits gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15640","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/2405.15640/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":"2026-07-05T08:22:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eD18KWIiGF3e1BtSW3J9L/5hl+18SLmwOPfXUGPrdZGA1raBS3Zvkr2oZjC3uG5FcqZAZZD03ib1AInMvE6qDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:21:48.599955Z"},"content_sha256":"1ce7ca01b2954fcf130c6bbd03fa8d9e59f12c5825b1df7d0df575ae78f878c9","schema_version":"1.0","event_id":"sha256:1ce7ca01b2954fcf130c6bbd03fa8d9e59f12c5825b1df7d0df575ae78f878c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UFY6S276NHLM7SNOUTQKKLMVL/bundle.json","state_url":"https://pith.science/pith/5UFY6S276NHLM7SNOUTQKKLMVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UFY6S276NHLM7SNOUTQKKLMVL/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":"2026-08-06T00:21:48Z","links":{"resolver":"https://pith.science/pith/5UFY6S276NHLM7SNOUTQKKLMVL","bundle":"https://pith.science/pith/5UFY6S276NHLM7SNOUTQKKLMVL/bundle.json","state":"https://pith.science/pith/5UFY6S276NHLM7SNOUTQKKLMVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UFY6S276NHLM7SNOUTQKKLMVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5UFY6S276NHLM7SNOUTQKKLMVL","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":"a98ec6c194ff18789cda348b78348cb91a776e4215ae59f892c1ac29056e752a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T15:30:41Z","title_canon_sha256":"7e0d20f859fb45d2b0048a59e6636244c6d768a9c2d2d603ac70eb52550789eb"},"schema_version":"1.0","source":{"id":"2405.15640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15640","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15640v1","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15640","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"5UFY6S276NHL","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"5UFY6S276NHLM7SN","created_at":"2026-07-05T08:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"5UFY6S27","created_at":"2026-07-05T08:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:1ce7ca01b2954fcf130c6bbd03fa8d9e59f12c5825b1df7d0df575ae78f878c9","target":"graph","created_at":"2026-07-05T08:22:52Z","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/2405.15640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce GECKO, a bilingual large language model (LLM) optimized for Korean and English, along with programming languages. GECKO is pretrained on the balanced, high-quality corpus of Korean and English employing LLaMA architecture. In this report, we share the experiences of several efforts to build a better data pipeline for the corpus and to train our model. GECKO shows great efficiency in token generations for both Korean and English, despite its small size of vocabulary. We measure the performance on the representative benchmarks in terms of Korean, English and Code, and it exhibits gr","authors_text":"Donggyu Kim, Sungwoo Oh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T15:30:41Z","title":"GECKO: Generative Language Model for English, Code and Korean"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15640","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:e59246d91ef9248870b5935cde7781e64f5ff4c36a185dac76fb9f1cc45a8699","target":"record","created_at":"2026-07-05T08:22:52Z","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":"a98ec6c194ff18789cda348b78348cb91a776e4215ae59f892c1ac29056e752a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T15:30:41Z","title_canon_sha256":"7e0d20f859fb45d2b0048a59e6636244c6d768a9c2d2d603ac70eb52550789eb"},"schema_version":"1.0","source":{"id":"2405.15640","kind":"arxiv","version":1}},"canonical_sha256":"ed0b8f4b5ff34eb67e4d752705296caac0a3f3eac2b2c27de42d8978ad3ea60b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed0b8f4b5ff34eb67e4d752705296caac0a3f3eac2b2c27de42d8978ad3ea60b","first_computed_at":"2026-07-05T08:22:52.010671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:52.010671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XCnKXQn2mBbU8Q7zjubGLxigKlus9UJ5jChnC/rhYA9L0VWVywR7LDafAOn6d6hzsrSxpG5ZipZ1v2jH2E8XBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:52.011160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e59246d91ef9248870b5935cde7781e64f5ff4c36a185dac76fb9f1cc45a8699","sha256:1ce7ca01b2954fcf130c6bbd03fa8d9e59f12c5825b1df7d0df575ae78f878c9"],"state_sha256":"1e9a1d6add029e0d0cec91683351b85eaf79b49190196a86aecda90a5aa42c8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IA6kPZOYo2C9psUIPxlDzKdMFzsQrfwq5lGiQQv9qFF9Vat/efN2KmKFLCny4eQfoKziO/k8JBkUqJK61a3cDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:21:48.602621Z","bundle_sha256":"75e261219b90e243a73e79cf66fd930202970c29f999bd309594efdcc1e47b44"}}