{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TOEZ7OURKGZE22DC4ABKSOJJY4","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":"3dccae00d961fe4cf6f24a6f8736e9a0d0acbf878784f7b1e291faf4477121d1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T20:54:44Z","title_canon_sha256":"5adc6968214305a465d38686485940c920c673cfc1b396f3c2deb91ebbb3e0f7"},"schema_version":"1.0","source":{"id":"2504.15431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15431","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15431v1","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15431","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"TOEZ7OURKGZE","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"TOEZ7OURKGZE22DC","created_at":"2026-07-05T10:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"TOEZ7OUR","created_at":"2026-07-05T10:52:24Z"}],"graph_snapshots":[{"event_id":"sha256:cf29f67f1bae48bf02861e48891790ba269a01b7f2667de4c66f931d27f13151","target":"graph","created_at":"2026-07-05T10:52:24Z","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/2504.15431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Trillion-7B, the most token-efficient Korean-centric multilingual LLM available. Our novel Cross-lingual Document Attention (XLDA) mechanism enables highly efficient and effective knowledge transfer from English to target languages like Korean and Japanese. Combined with optimized data mixtures, language-specific filtering, and tailored tokenizer construction, Trillion-7B achieves competitive performance while dedicating only 10\\% of its 2T training tokens to multilingual data and requiring just 59.4K H100 GPU hours (\\$148K) for full training. Comprehensive evaluations across 27 b","authors_text":"Hyungguk Kim, Jamin Shin (Trillion Labs), Juyoung Suk, Kyuseok Kim, Seungtaek Choi, Sungjun Han, Suyeong An, Wonsuk Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T20:54:44Z","title":"Trillion 7B Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15431","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":"sha256:6d0d6c41c76afe129d2441990db1e9c367ff64f24fd8cf812fcb8b59010de047","target":"record","created_at":"2026-07-05T10:52:24Z","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":"3dccae00d961fe4cf6f24a6f8736e9a0d0acbf878784f7b1e291faf4477121d1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T20:54:44Z","title_canon_sha256":"5adc6968214305a465d38686485940c920c673cfc1b396f3c2deb91ebbb3e0f7"},"schema_version":"1.0","source":{"id":"2504.15431","kind":"arxiv","version":1}},"canonical_sha256":"9b899fba9151b24d6862e002a93929c7248208252343b6c307e44ea008f86058","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b899fba9151b24d6862e002a93929c7248208252343b6c307e44ea008f86058","first_computed_at":"2026-07-05T10:52:24.505269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:24.505269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t1yM/jy6vPUHy0z188l8o1A04c3X2bXjBINt5JAPFRyl4p6lqAnKsPkNLsFH8hz3hdIymRqSxLYPVfgGm6xVCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:24.505800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d0d6c41c76afe129d2441990db1e9c367ff64f24fd8cf812fcb8b59010de047","sha256:cf29f67f1bae48bf02861e48891790ba269a01b7f2667de4c66f931d27f13151"],"state_sha256":"ce449a417f9c8df5e47815d20f984274990d4ed0dc911010d97f34e74064d3bf"}