{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HZFNEDORBAM4EJHBE2FCGB4RQB","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":"7f4719e5cf693ba143c91ba904745e2f41761e50e0e6de02ca6bc2f7e854bbb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T10:01:52Z","title_canon_sha256":"e6fd559008df4733ae884e30ec658c770b038a88fce239682ce5196a8ed74ac9"},"schema_version":"1.0","source":{"id":"2411.10083","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10083","created_at":"2026-07-05T09:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10083v3","created_at":"2026-07-05T09:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10083","created_at":"2026-07-05T09:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"HZFNEDORBAM4","created_at":"2026-07-05T09:44:16Z"},{"alias_kind":"pith_short_16","alias_value":"HZFNEDORBAM4EJHB","created_at":"2026-07-05T09:44:16Z"},{"alias_kind":"pith_short_8","alias_value":"HZFNEDOR","created_at":"2026-07-05T09:44:16Z"}],"graph_snapshots":[{"event_id":"sha256:68fb83055f9b4c314245c57ad66b7622ffe72203a14ff7716aec6bef534f1134","target":"graph","created_at":"2026-07-05T09:44:16Z","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/2411.10083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Xmodel-1.5, a 1-billion-parameter multilingual large language model pretrained on 2 trillion tokens, designed for balanced performance and scalability. Unlike most large models that use the BPE tokenizer, Xmodel-1.5 employs a custom unigram tokenizer with 65,280 tokens, optimizing both efficiency and accuracy. The model delivers competitive results across multiple languages, including Thai, Arabic, French, Chinese, and English, outperforming Alibaba's PolyLM-1.7B on respective evaluation datasets. Xmodel-1.5 excels in benchmarks like mMMLU and PIQA, and achieves state-of-the-art r","authors_text":"Jiang Ling, Lin Qingquan, Liu Yang, Wang Qun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T10:01:52Z","title":"Xmodel-1.5: An 1B-scale Multilingual LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10083","kind":"arxiv","version":3},"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":"sha256:798cc8eb12812c47465d1429a91019ebca705fa2f9d1e0f810477a982c4eb8f5","target":"record","created_at":"2026-07-05T09:44:16Z","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":"7f4719e5cf693ba143c91ba904745e2f41761e50e0e6de02ca6bc2f7e854bbb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T10:01:52Z","title_canon_sha256":"e6fd559008df4733ae884e30ec658c770b038a88fce239682ce5196a8ed74ac9"},"schema_version":"1.0","source":{"id":"2411.10083","kind":"arxiv","version":3}},"canonical_sha256":"3e4ad20dd10819c224e1268a230791805893b73106b1197739d70a30713db106","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e4ad20dd10819c224e1268a230791805893b73106b1197739d70a30713db106","first_computed_at":"2026-07-05T09:44:16.712477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:16.712477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9nmDilmw3EJnY4Nn5ezGBvVUClBPolgZvhZSPYlK8lNYjasW+VipkYic6ZMrpOA/od71Qmp9BVm9fys8oYgjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:16.713054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10083","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:798cc8eb12812c47465d1429a91019ebca705fa2f9d1e0f810477a982c4eb8f5","sha256:68fb83055f9b4c314245c57ad66b7622ffe72203a14ff7716aec6bef534f1134"],"state_sha256":"15648212175116102b358c8993c3e5b7b9d516aa1b57083f660c631644c9cb22"}