{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HZFNEDORBAM4EJHBE2FCGB4RQB","short_pith_number":"pith:HZFNEDOR","schema_version":"1.0","canonical_sha256":"3e4ad20dd10819c224e1268a230791805893b73106b1197739d70a30713db106","source":{"kind":"arxiv","id":"2411.10083","version":3},"attestation_state":"computed","paper":{"title":"Xmodel-1.5: An 1B-scale Multilingual LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiang Ling, Lin Qingquan, Liu Yang, Wang Qun","submitted_at":"2024-11-15T10:01:52Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.10083","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T10:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"e6fd559008df4733ae884e30ec658c770b038a88fce239682ce5196a8ed74ac9","abstract_canon_sha256":"7f4719e5cf693ba143c91ba904745e2f41761e50e0e6de02ca6bc2f7e854bbb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:16.713054Z","signature_b64":"9nmDilmw3EJnY4Nn5ezGBvVUClBPolgZvhZSPYlK8lNYjasW+VipkYic6ZMrpOA/od71Qmp9BVm9fys8oYgjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e4ad20dd10819c224e1268a230791805893b73106b1197739d70a30713db106","last_reissued_at":"2026-07-05T09:44:16.712477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:16.712477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Xmodel-1.5: An 1B-scale Multilingual LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiang Ling, Lin Qingquan, Liu Yang, Wang Qun","submitted_at":"2024-11-15T10:01:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10083","kind":"arxiv","version":3},"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/2411.10083/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.10083","created_at":"2026-07-05T09:44:16.712548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10083v3","created_at":"2026-07-05T09:44:16.712548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10083","created_at":"2026-07-05T09:44:16.712548+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZFNEDORBAM4","created_at":"2026-07-05T09:44:16.712548+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZFNEDORBAM4EJHB","created_at":"2026-07-05T09:44:16.712548+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZFNEDOR","created_at":"2026-07-05T09:44:16.712548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB","json":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB.json","graph_json":"https://pith.science/api/pith-number/HZFNEDORBAM4EJHBE2FCGB4RQB/graph.json","events_json":"https://pith.science/api/pith-number/HZFNEDORBAM4EJHBE2FCGB4RQB/events.json","paper":"https://pith.science/paper/HZFNEDOR"},"agent_actions":{"view_html":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB","download_json":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB.json","view_paper":"https://pith.science/paper/HZFNEDOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10083&json=true","fetch_graph":"https://pith.science/api/pith-number/HZFNEDORBAM4EJHBE2FCGB4RQB/graph.json","fetch_events":"https://pith.science/api/pith-number/HZFNEDORBAM4EJHBE2FCGB4RQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB/action/storage_attestation","attest_author":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB/action/author_attestation","sign_citation":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB/action/citation_signature","submit_replication":"https://pith.science/pith/HZFNEDORBAM4EJHBE2FCGB4RQB/action/replication_record"}},"created_at":"2026-07-05T09:44:16.712548+00:00","updated_at":"2026-07-05T09:44:16.712548+00:00"}