{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PYGKKENINA26SHDDUVWO723PO3","short_pith_number":"pith:PYGKKENI","canonical_record":{"source":{"id":"2412.15236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T05:27:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6aa3c826922d494105ffd96968febf53b4ca180b896e8f1827cb5b6bec93c2f","abstract_canon_sha256":"5d1a79bdec81c69fbe22076d03856ae37fef83d1e222b4e7da3bfeb70bf795ab"},"schema_version":"1.0"},"canonical_sha256":"7e0ca511a86835e91c63a56cefeb6f76d80a4bb228e866022f7204972ac6ed2e","source":{"kind":"arxiv","id":"2412.15236","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15236","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15236v2","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15236","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"pith_short_12","alias_value":"PYGKKENINA26","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"pith_short_16","alias_value":"PYGKKENINA26SHDD","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"pith_short_8","alias_value":"PYGKKENI","created_at":"2026-07-05T09:53:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PYGKKENINA26SHDDUVWO723PO3","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T05:27:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6aa3c826922d494105ffd96968febf53b4ca180b896e8f1827cb5b6bec93c2f","abstract_canon_sha256":"5d1a79bdec81c69fbe22076d03856ae37fef83d1e222b4e7da3bfeb70bf795ab"},"schema_version":"1.0"},"canonical_sha256":"7e0ca511a86835e91c63a56cefeb6f76d80a4bb228e866022f7204972ac6ed2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:09.566295Z","signature_b64":"DYOPoEGKtdJ6kLKiN5G3n4H+7YnQmRoEGR1MPkTYR7lySmWqAOreHnqBnLn0ViQPL4pcoW8K2TMI2mwIrP02BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e0ca511a86835e91c63a56cefeb6f76d80a4bb228e866022f7204972ac6ed2e","last_reissued_at":"2026-07-05T09:53:09.565836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:09.565836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15236","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"feKsSkLJSu/+Hv/yy90sXGhP1uoTqI/y5ASx15V2IgrF4p6q/gA2U33Bro5eVGx/q65J6I66KmkOOK/zUV5eCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:03:06.514326Z"},"content_sha256":"0c56147235cb0840cbf0951028ab2421ece6a8984cd4f2676910c4d8a36d1c9e","schema_version":"1.0","event_id":"sha256:0c56147235cb0840cbf0951028ab2421ece6a8984cd4f2676910c4d8a36d1c9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PYGKKENINA26SHDDUVWO723PO3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CareBot: A Pioneering Full-Process Open-Source Medical Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hua Zhou, Lulu Zhao, Weihao Zeng, Xiaofeng Shi","submitted_at":"2024-12-12T05:27:43Z","abstract_excerpt":"Recently, both closed-source LLMs and open-source communities have made significant strides, outperforming humans in various general domains. However, their performance in specific professional domains such as medicine, especially within the open-source community, remains suboptimal due to the complexity of medical knowledge. In this paper, we propose CareBot, a bilingual medical LLM, which leverages a comprehensive approach integrating continuous pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning with human feedback (RLHF). Our novel two-stage CPT method, comprising "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15236","kind":"arxiv","version":2},"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/2412.15236/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":"2026-07-05T09:53:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OvcuGxu4zF0zndiAw4/5chh/H9Glktr4GttxNo1nY0f9VqpIwqDzJDHrLuJCrxPmpisBs6HxWiyYXowKVtNGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:03:06.514840Z"},"content_sha256":"17a3050175d573ff1511613f2b36ca6892c2aaa3613be7dd2e729a4cecfc75a6","schema_version":"1.0","event_id":"sha256:17a3050175d573ff1511613f2b36ca6892c2aaa3613be7dd2e729a4cecfc75a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYGKKENINA26SHDDUVWO723PO3/bundle.json","state_url":"https://pith.science/pith/PYGKKENINA26SHDDUVWO723PO3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYGKKENINA26SHDDUVWO723PO3/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":"2026-08-14T18:03:06Z","links":{"resolver":"https://pith.science/pith/PYGKKENINA26SHDDUVWO723PO3","bundle":"https://pith.science/pith/PYGKKENINA26SHDDUVWO723PO3/bundle.json","state":"https://pith.science/pith/PYGKKENINA26SHDDUVWO723PO3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYGKKENINA26SHDDUVWO723PO3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PYGKKENINA26SHDDUVWO723PO3","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":"5d1a79bdec81c69fbe22076d03856ae37fef83d1e222b4e7da3bfeb70bf795ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T05:27:43Z","title_canon_sha256":"c6aa3c826922d494105ffd96968febf53b4ca180b896e8f1827cb5b6bec93c2f"},"schema_version":"1.0","source":{"id":"2412.15236","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15236","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15236v2","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15236","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"pith_short_12","alias_value":"PYGKKENINA26","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"pith_short_16","alias_value":"PYGKKENINA26SHDD","created_at":"2026-07-05T09:53:09Z"},{"alias_kind":"pith_short_8","alias_value":"PYGKKENI","created_at":"2026-07-05T09:53:09Z"}],"graph_snapshots":[{"event_id":"sha256:17a3050175d573ff1511613f2b36ca6892c2aaa3613be7dd2e729a4cecfc75a6","target":"graph","created_at":"2026-07-05T09:53:09Z","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/2412.15236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, both closed-source LLMs and open-source communities have made significant strides, outperforming humans in various general domains. However, their performance in specific professional domains such as medicine, especially within the open-source community, remains suboptimal due to the complexity of medical knowledge. In this paper, we propose CareBot, a bilingual medical LLM, which leverages a comprehensive approach integrating continuous pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning with human feedback (RLHF). Our novel two-stage CPT method, comprising ","authors_text":"Hua Zhou, Lulu Zhao, Weihao Zeng, Xiaofeng Shi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T05:27:43Z","title":"CareBot: A Pioneering Full-Process Open-Source Medical Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15236","kind":"arxiv","version":2},"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":"sha256:0c56147235cb0840cbf0951028ab2421ece6a8984cd4f2676910c4d8a36d1c9e","target":"record","created_at":"2026-07-05T09:53:09Z","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":"5d1a79bdec81c69fbe22076d03856ae37fef83d1e222b4e7da3bfeb70bf795ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T05:27:43Z","title_canon_sha256":"c6aa3c826922d494105ffd96968febf53b4ca180b896e8f1827cb5b6bec93c2f"},"schema_version":"1.0","source":{"id":"2412.15236","kind":"arxiv","version":2}},"canonical_sha256":"7e0ca511a86835e91c63a56cefeb6f76d80a4bb228e866022f7204972ac6ed2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e0ca511a86835e91c63a56cefeb6f76d80a4bb228e866022f7204972ac6ed2e","first_computed_at":"2026-07-05T09:53:09.565836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:09.565836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DYOPoEGKtdJ6kLKiN5G3n4H+7YnQmRoEGR1MPkTYR7lySmWqAOreHnqBnLn0ViQPL4pcoW8K2TMI2mwIrP02BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:09.566295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15236","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c56147235cb0840cbf0951028ab2421ece6a8984cd4f2676910c4d8a36d1c9e","sha256:17a3050175d573ff1511613f2b36ca6892c2aaa3613be7dd2e729a4cecfc75a6"],"state_sha256":"f541a660e85235828b4301e5b4839eeac8eba3e3d1621b47945ec7b8592f962e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aT6/ejNZYXXR0ZxiLSA50YDMLDSpY0YjLJrOG1Nr6yn8cNFl4PiJI9x2EJUA8xzxI6RQTts5pRPaRWWmZTG+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:03:06.519027Z","bundle_sha256":"21149f7275746464d8a8243a8aa6237e2a566d0df660076bf0995dd7b610420d"}}