{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FMFAJLKBZ6XQQNYIRUXB4D4VB5","short_pith_number":"pith:FMFAJLKB","schema_version":"1.0","canonical_sha256":"2b0a04ad41cfaf0837088d2e1e0f950f59925583048e951317a4c84e71662156","source":{"kind":"arxiv","id":"2403.03640","version":6},"attestation_state":"computed","paper":{"title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anningzhe Gao, Benyou Wang, Chunxian Zhang, Guorui Zhen, Haizhou Li, Junyin Chen, Nuo Chen, Xiangbo Wu, Xiang Wan, Xidong Wang, Yan Hu, Yidong Wang","submitted_at":"2024-03-06T11:56:02Z","abstract_excerpt":"Despite the vast repository of global medical knowledge predominantly being in English, local languages are crucial for delivering tailored healthcare services, particularly in areas with limited medical resources. To extend the reach of medical AI advancements to a broader population, we aim to develop medical LLMs across the six most widely spoken languages, encompassing a global population of 6.1 billion. This effort culminates in the creation of the ApolloCorpora multilingual medical dataset and the XMedBench benchmark. In the multilingual medical benchmark, the released Apollo models, at "},"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":"2403.03640","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T11:56:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3670fac9088317f62bb08d5b4e023866cc40b12f2fed895c0772b81f8e7d8b9a","abstract_canon_sha256":"59fadadc9e433309b6378707ff00ff1b3a11a8d548fcfa6685026db40550df3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:27.127659Z","signature_b64":"BjVGJsMOJQucDdxK9LpNSd+j8uCcflDCoR5lQRoVYIkRP/53j+++Ihg7FmXxrjVUXXRJdDNbkRqjYoaqnAbuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b0a04ad41cfaf0837088d2e1e0f950f59925583048e951317a4c84e71662156","last_reissued_at":"2026-07-05T09:19:27.125969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:27.125969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anningzhe Gao, Benyou Wang, Chunxian Zhang, Guorui Zhen, Haizhou Li, Junyin Chen, Nuo Chen, Xiangbo Wu, Xiang Wan, Xidong Wang, Yan Hu, Yidong Wang","submitted_at":"2024-03-06T11:56:02Z","abstract_excerpt":"Despite the vast repository of global medical knowledge predominantly being in English, local languages are crucial for delivering tailored healthcare services, particularly in areas with limited medical resources. To extend the reach of medical AI advancements to a broader population, we aim to develop medical LLMs across the six most widely spoken languages, encompassing a global population of 6.1 billion. This effort culminates in the creation of the ApolloCorpora multilingual medical dataset and the XMedBench benchmark. In the multilingual medical benchmark, the released Apollo models, at "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03640","kind":"arxiv","version":6},"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/2403.03640/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":"2403.03640","created_at":"2026-07-05T09:19:27.126032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03640v6","created_at":"2026-07-05T09:19:27.126032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03640","created_at":"2026-07-05T09:19:27.126032+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMFAJLKBZ6XQ","created_at":"2026-07-05T09:19:27.126032+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMFAJLKBZ6XQQNYI","created_at":"2026-07-05T09:19:27.126032+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMFAJLKB","created_at":"2026-07-05T09:19:27.126032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24200","citing_title":"MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30637","citing_title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25374","citing_title":"Language corpora for the Dutch medical domain","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5","json":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5.json","graph_json":"https://pith.science/api/pith-number/FMFAJLKBZ6XQQNYIRUXB4D4VB5/graph.json","events_json":"https://pith.science/api/pith-number/FMFAJLKBZ6XQQNYIRUXB4D4VB5/events.json","paper":"https://pith.science/paper/FMFAJLKB"},"agent_actions":{"view_html":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5","download_json":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5.json","view_paper":"https://pith.science/paper/FMFAJLKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03640&json=true","fetch_graph":"https://pith.science/api/pith-number/FMFAJLKBZ6XQQNYIRUXB4D4VB5/graph.json","fetch_events":"https://pith.science/api/pith-number/FMFAJLKBZ6XQQNYIRUXB4D4VB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5/action/storage_attestation","attest_author":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5/action/author_attestation","sign_citation":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5/action/citation_signature","submit_replication":"https://pith.science/pith/FMFAJLKBZ6XQQNYIRUXB4D4VB5/action/replication_record"}},"created_at":"2026-07-05T09:19:27.126032+00:00","updated_at":"2026-07-05T09:19:27.126032+00:00"}