{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O3EGJ65FIHEVD5EJM3FC5UXUCT","short_pith_number":"pith:O3EGJ65F","schema_version":"1.0","canonical_sha256":"76c864fba541c951f48966ca2ed2f414e446b1dd67b11e944e3e510b6e31a330","source":{"kind":"arxiv","id":"2304.01097","version":2},"attestation_state":"computed","paper":{"title":"DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinggang Shen, Honglin Xiong, Linlin Huang, Qian Wang, Sheng Wang, Yitao Zhu, Yuxiao Liu, Zihao Zhao","submitted_at":"2023-04-03T15:57:51Z","abstract_excerpt":"The recent progress of large language models (LLMs), including ChatGPT and GPT-4, in comprehending and responding to human instructions has been remarkable. Nevertheless, these models typically perform better in English and have not been explicitly trained for the medical domain, resulting in suboptimal precision in diagnoses, drug recommendations, and other medical advice. Additionally, training and deploying a dialogue model is still believed to be impossible for hospitals, hindering the promotion of LLMs. To tackle these challenges, we have collected databases of medical dialogues in Chines"},"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":"2304.01097","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T15:57:51Z","cross_cats_sorted":[],"title_canon_sha256":"66febbf77393aceae389d60face07f9ec5bb3949edf4096206c560b46cda2819","abstract_canon_sha256":"c8005e3d74959347c81d59e8e7afda047d64ad7437aca25e79f1bc294e74f554"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:37.622142Z","signature_b64":"1O5H1O3pyG8usxNLTZbD/E2xI2L8UPM0qCM/IWx46Y2jp9gQwRci8gBe9hfQYhZSThi4V/vY7ObKswjKZj4sAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76c864fba541c951f48966ca2ed2f414e446b1dd67b11e944e3e510b6e31a330","last_reissued_at":"2026-07-05T06:01:37.621736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:37.621736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinggang Shen, Honglin Xiong, Linlin Huang, Qian Wang, Sheng Wang, Yitao Zhu, Yuxiao Liu, Zihao Zhao","submitted_at":"2023-04-03T15:57:51Z","abstract_excerpt":"The recent progress of large language models (LLMs), including ChatGPT and GPT-4, in comprehending and responding to human instructions has been remarkable. Nevertheless, these models typically perform better in English and have not been explicitly trained for the medical domain, resulting in suboptimal precision in diagnoses, drug recommendations, and other medical advice. Additionally, training and deploying a dialogue model is still believed to be impossible for hospitals, hindering the promotion of LLMs. To tackle these challenges, we have collected databases of medical dialogues in Chines"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01097","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/2304.01097/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":"2304.01097","created_at":"2026-07-05T06:01:37.621792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01097v2","created_at":"2026-07-05T06:01:37.621792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01097","created_at":"2026-07-05T06:01:37.621792+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3EGJ65FIHEV","created_at":"2026-07-05T06:01:37.621792+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3EGJ65FIHEVD5EJ","created_at":"2026-07-05T06:01:37.621792+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3EGJ65F","created_at":"2026-07-05T06:01:37.621792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04535","citing_title":"Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29744","citing_title":"Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2306.00890","citing_title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":129,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT","json":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT.json","graph_json":"https://pith.science/api/pith-number/O3EGJ65FIHEVD5EJM3FC5UXUCT/graph.json","events_json":"https://pith.science/api/pith-number/O3EGJ65FIHEVD5EJM3FC5UXUCT/events.json","paper":"https://pith.science/paper/O3EGJ65F"},"agent_actions":{"view_html":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT","download_json":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT.json","view_paper":"https://pith.science/paper/O3EGJ65F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01097&json=true","fetch_graph":"https://pith.science/api/pith-number/O3EGJ65FIHEVD5EJM3FC5UXUCT/graph.json","fetch_events":"https://pith.science/api/pith-number/O3EGJ65FIHEVD5EJM3FC5UXUCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT/action/storage_attestation","attest_author":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT/action/author_attestation","sign_citation":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT/action/citation_signature","submit_replication":"https://pith.science/pith/O3EGJ65FIHEVD5EJM3FC5UXUCT/action/replication_record"}},"created_at":"2026-07-05T06:01:37.621792+00:00","updated_at":"2026-07-05T06:01:37.621792+00:00"}