{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PEZNFKYIZHRGUUFKSORGBREYCI","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":"9ee8aa306785efb2994c3142fb8869f83b090bb441a107f6f0c8310b634979b8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T12:29:27Z","title_canon_sha256":"0f30ac73c082d455e5333d0899a89242bd4cb18f18e90b754a7c468ea335668f"},"schema_version":"1.0","source":{"id":"2401.12246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12246","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12246v1","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12246","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_12","alias_value":"PEZNFKYIZHRG","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_16","alias_value":"PEZNFKYIZHRGUUFK","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_8","alias_value":"PEZNFKYI","created_at":"2026-07-05T07:36:27Z"}],"graph_snapshots":[{"event_id":"sha256:6715d884c0757dc5a9c162779fc12e604a22b1d299a86934f9007ddcc21a2bec","target":"graph","created_at":"2026-07-05T07:36:27Z","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/2401.12246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we introduce Orion-14B, a collection of multilingual large language models with 14 billion parameters. We utilize a data scheduling approach to train a foundational model on a diverse corpus of 2.5 trillion tokens, sourced from texts in English, Chinese, Japanese, Korean, and other languages. Additionally, we fine-tuned a series of models tailored for conversational applications and other specific use cases. Our evaluation results demonstrate that Orion-14B achieves state-of-the-art performance across a broad spectrum of tasks. We make the Orion-14B model family and its associat","authors_text":"Dacheng Zhang, Du Chen, Haihui Pan, Kun Han, Leichao Xu, Xiaopu Li, Yi Huang, Yongqiang Li, Yongqiang Liu, Zhipeng Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T12:29:27Z","title":"Orion-14B: Open-source Multilingual Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12246","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:c892fb8384dc1cd1f65b11fc31ee293eb030e82b653e54bd3cf36db8be50b79e","target":"record","created_at":"2026-07-05T07:36:27Z","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":"9ee8aa306785efb2994c3142fb8869f83b090bb441a107f6f0c8310b634979b8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-20T12:29:27Z","title_canon_sha256":"0f30ac73c082d455e5333d0899a89242bd4cb18f18e90b754a7c468ea335668f"},"schema_version":"1.0","source":{"id":"2401.12246","kind":"arxiv","version":1}},"canonical_sha256":"7932d2ab08c9e26a50aa93a260c498123b4465385f7578734a3cd7fad84b3134","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7932d2ab08c9e26a50aa93a260c498123b4465385f7578734a3cd7fad84b3134","first_computed_at":"2026-07-05T07:36:27.860292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:27.860292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9UA+NDA1K+02FqnH/EGDnXSIXAS8Q6NNE8QTq0kBvWRYPnmisv2Lt9LjfMXhtjwJacJzJOyklrk0IwTAFNPcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:27.860848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c892fb8384dc1cd1f65b11fc31ee293eb030e82b653e54bd3cf36db8be50b79e","sha256:6715d884c0757dc5a9c162779fc12e604a22b1d299a86934f9007ddcc21a2bec"],"state_sha256":"7bb32a315e480217e93fcd4d71fd6f170c9d731fbc98c6c3ca220a8f07cb9aef"}