{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RLORSMJTTMAZADT4LNP6YTJWY5","short_pith_number":"pith:RLORSMJT","canonical_record":{"source":{"id":"2402.13963","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:47:20Z","cross_cats_sorted":[],"title_canon_sha256":"66ea971070010cea2042ef3f5265ed6a8a43c8ce3b14c8780c624e49c80ac1d0","abstract_canon_sha256":"bd1b566472d15c9fc77a6d38b706e74182f3d97a839cd4286d417a20209fcfd1"},"schema_version":"1.0"},"canonical_sha256":"8add1931339b01900e7c5b5fec4d36c74471befe101aa4fc202dce5266081bf8","source":{"kind":"arxiv","id":"2402.13963","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13963","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13963v4","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13963","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"RLORSMJTTMAZ","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"RLORSMJTTMAZADT4","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"RLORSMJT","created_at":"2026-07-05T08:26:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RLORSMJTTMAZADT4LNP6YTJWY5","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13963","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:47:20Z","cross_cats_sorted":[],"title_canon_sha256":"66ea971070010cea2042ef3f5265ed6a8a43c8ce3b14c8780c624e49c80ac1d0","abstract_canon_sha256":"bd1b566472d15c9fc77a6d38b706e74182f3d97a839cd4286d417a20209fcfd1"},"schema_version":"1.0"},"canonical_sha256":"8add1931339b01900e7c5b5fec4d36c74471befe101aa4fc202dce5266081bf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:20.271284Z","signature_b64":"2hrJRHbdHdmS5Z1h2rkUoSDm3razUx1a+UaSZWQbkQBnBV8W6pYzjVHTl/etAJZAWZnVlTOyaeOjN1ELDyzqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8add1931339b01900e7c5b5fec4d36c74471befe101aa4fc202dce5266081bf8","last_reissued_at":"2026-07-05T08:26:20.270869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:20.270869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13963","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8w8sDllFvYhQIH8yV9tlR+ovItV7uKjIp8V9Ta5t83UV6QNgwk0DprZMDj40BAEdI3xOBYK5+cgu01bjRD5bDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:00:23.253053Z"},"content_sha256":"e65738f557dc3e349c4898aaf21b9e8a3e89cfc645f9f0a4420722a4a1a3f11c","schema_version":"1.0","event_id":"sha256:e65738f557dc3e349c4898aaf21b9e8a3e89cfc645f9f0a4420722a4a1a3f11c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RLORSMJTTMAZADT4LNP6YTJWY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Building Multilingual Language Model for Medicine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaoyi Wu, Haicheng Wang, Pengcheng Qiu, Weidi Xie, Weixiong Lin, Xiaoman Zhang, Yanfeng Wang, Ya Zhang","submitted_at":"2024-02-21T17:47:20Z","abstract_excerpt":"The development of open-source, multilingual medical language models can benefit a wide, linguistically diverse audience from different regions. To promote this domain, we present contributions from the following: First, we construct a multilingual medical corpus, containing approximately 25.5B tokens encompassing 6 main languages, termed as MMedC, enabling auto-regressive domain adaptation for general LLMs; Second, to monitor the development of multilingual medical LLMs, we propose a multilingual medical multi-choice question-answering benchmark with rationale, termed as MMedBench; Third, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13963","kind":"arxiv","version":4},"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/2402.13963/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EajJQfltwt4z9WBPKgPaOmbs/O/IY/svh83VoXTGKw1PucBx8Qd4zCbh8R3UyLYQlB6TfcgxTXWF1RewdJf/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:00:23.253578Z"},"content_sha256":"35c5781f1d9c3bc72d6e669ee502813999783245c624abf365dfdc7fc4d966e0","schema_version":"1.0","event_id":"sha256:35c5781f1d9c3bc72d6e669ee502813999783245c624abf365dfdc7fc4d966e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLORSMJTTMAZADT4LNP6YTJWY5/bundle.json","state_url":"https://pith.science/pith/RLORSMJTTMAZADT4LNP6YTJWY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLORSMJTTMAZADT4LNP6YTJWY5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T04:00:23Z","links":{"resolver":"https://pith.science/pith/RLORSMJTTMAZADT4LNP6YTJWY5","bundle":"https://pith.science/pith/RLORSMJTTMAZADT4LNP6YTJWY5/bundle.json","state":"https://pith.science/pith/RLORSMJTTMAZADT4LNP6YTJWY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLORSMJTTMAZADT4LNP6YTJWY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLORSMJTTMAZADT4LNP6YTJWY5","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":"bd1b566472d15c9fc77a6d38b706e74182f3d97a839cd4286d417a20209fcfd1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:47:20Z","title_canon_sha256":"66ea971070010cea2042ef3f5265ed6a8a43c8ce3b14c8780c624e49c80ac1d0"},"schema_version":"1.0","source":{"id":"2402.13963","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13963","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13963v4","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13963","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"RLORSMJTTMAZ","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"RLORSMJTTMAZADT4","created_at":"2026-07-05T08:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"RLORSMJT","created_at":"2026-07-05T08:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:35c5781f1d9c3bc72d6e669ee502813999783245c624abf365dfdc7fc4d966e0","target":"graph","created_at":"2026-07-05T08:26:20Z","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/2402.13963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of open-source, multilingual medical language models can benefit a wide, linguistically diverse audience from different regions. To promote this domain, we present contributions from the following: First, we construct a multilingual medical corpus, containing approximately 25.5B tokens encompassing 6 main languages, termed as MMedC, enabling auto-regressive domain adaptation for general LLMs; Second, to monitor the development of multilingual medical LLMs, we propose a multilingual medical multi-choice question-answering benchmark with rationale, termed as MMedBench; Third, we ","authors_text":"Chaoyi Wu, Haicheng Wang, Pengcheng Qiu, Weidi Xie, Weixiong Lin, Xiaoman Zhang, Yanfeng Wang, Ya Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:47:20Z","title":"Towards Building Multilingual Language Model for Medicine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13963","kind":"arxiv","version":4},"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:e65738f557dc3e349c4898aaf21b9e8a3e89cfc645f9f0a4420722a4a1a3f11c","target":"record","created_at":"2026-07-05T08:26:20Z","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":"bd1b566472d15c9fc77a6d38b706e74182f3d97a839cd4286d417a20209fcfd1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T17:47:20Z","title_canon_sha256":"66ea971070010cea2042ef3f5265ed6a8a43c8ce3b14c8780c624e49c80ac1d0"},"schema_version":"1.0","source":{"id":"2402.13963","kind":"arxiv","version":4}},"canonical_sha256":"8add1931339b01900e7c5b5fec4d36c74471befe101aa4fc202dce5266081bf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8add1931339b01900e7c5b5fec4d36c74471befe101aa4fc202dce5266081bf8","first_computed_at":"2026-07-05T08:26:20.270869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:20.270869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2hrJRHbdHdmS5Z1h2rkUoSDm3razUx1a+UaSZWQbkQBnBV8W6pYzjVHTl/etAJZAWZnVlTOyaeOjN1ELDyzqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:20.271284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13963","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e65738f557dc3e349c4898aaf21b9e8a3e89cfc645f9f0a4420722a4a1a3f11c","sha256:35c5781f1d9c3bc72d6e669ee502813999783245c624abf365dfdc7fc4d966e0"],"state_sha256":"09f2a5b54a64be6748c1a9a8a54f108829284e5ccdac33651bfba4c8eac0ae91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVHgVl6bD2OOL5cH588bjNfgJ0FdpE7i4yNnufmGvFPI9shMta3wLomIFMijuqGnMCajAqDCZ/Y0QWlYHGP9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:00:23.257567Z","bundle_sha256":"c9a51497ce14a44db95aa28b5b4afd5c13f1635b54fa6d08bd1d79f5b7e147d4"}}