{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RQ3IC73EA3DNFJIXPRLPAIKB7G","short_pith_number":"pith:RQ3IC73E","schema_version":"1.0","canonical_sha256":"8c36817f6406c6d2a5177c56f02141f984191b09d0c209bbbd73153e1094d1ec","source":{"kind":"arxiv","id":"2310.17956","version":2},"attestation_state":"computed","paper":{"title":"Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dading Chong, Junling Liu, Peilin Zhou, Qichen Ye, Yining Hua, Ziming Wang","submitted_at":"2023-10-27T08:05:21Z","abstract_excerpt":"Large Language Models (LLMs) have introduced a new era of proficiency in comprehending complex healthcare and biomedical topics. However, there is a noticeable lack of models in languages other than English and models that can interpret multi-modal input, which is crucial for global healthcare accessibility. In response, this study introduces Qilin-Med-VL, the first Chinese large vision-language model designed to integrate the analysis of textual and visual data. Qilin-Med-VL combines a pre-trained Vision Transformer (ViT) with a foundational LLM. It undergoes a thorough two-stage curriculum t"},"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":"2310.17956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T08:05:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"84fb4f7d50e15858fea5f36908f99455c4e022219879df38f5fa1372290d591d","abstract_canon_sha256":"1252b41ddea31b4581bf356cccb1b4270bea5279876bac4f2b506bd3b4d2faf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:40.271301Z","signature_b64":"sS/ECN5P5z5G6uvsEuJEvzBqloPBdfqg8kbSkEMrIZ153g5q+ZfB9ookHT1m4kzSQb57T9gpcMrkJDS0MQRxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c36817f6406c6d2a5177c56f02141f984191b09d0c209bbbd73153e1094d1ec","last_reissued_at":"2026-07-05T07:07:40.270833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:40.270833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dading Chong, Junling Liu, Peilin Zhou, Qichen Ye, Yining Hua, Ziming Wang","submitted_at":"2023-10-27T08:05:21Z","abstract_excerpt":"Large Language Models (LLMs) have introduced a new era of proficiency in comprehending complex healthcare and biomedical topics. However, there is a noticeable lack of models in languages other than English and models that can interpret multi-modal input, which is crucial for global healthcare accessibility. In response, this study introduces Qilin-Med-VL, the first Chinese large vision-language model designed to integrate the analysis of textual and visual data. Qilin-Med-VL combines a pre-trained Vision Transformer (ViT) with a foundational LLM. It undergoes a thorough two-stage curriculum t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17956","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/2310.17956/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":"2310.17956","created_at":"2026-07-05T07:07:40.270886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17956v2","created_at":"2026-07-05T07:07:40.270886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17956","created_at":"2026-07-05T07:07:40.270886+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQ3IC73EA3DN","created_at":"2026-07-05T07:07:40.270886+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQ3IC73EA3DNFJIX","created_at":"2026-07-05T07:07:40.270886+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQ3IC73E","created_at":"2026-07-05T07:07:40.270886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00535","citing_title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10415","citing_title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G","json":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G.json","graph_json":"https://pith.science/api/pith-number/RQ3IC73EA3DNFJIXPRLPAIKB7G/graph.json","events_json":"https://pith.science/api/pith-number/RQ3IC73EA3DNFJIXPRLPAIKB7G/events.json","paper":"https://pith.science/paper/RQ3IC73E"},"agent_actions":{"view_html":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G","download_json":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G.json","view_paper":"https://pith.science/paper/RQ3IC73E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17956&json=true","fetch_graph":"https://pith.science/api/pith-number/RQ3IC73EA3DNFJIXPRLPAIKB7G/graph.json","fetch_events":"https://pith.science/api/pith-number/RQ3IC73EA3DNFJIXPRLPAIKB7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G/action/storage_attestation","attest_author":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G/action/author_attestation","sign_citation":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G/action/citation_signature","submit_replication":"https://pith.science/pith/RQ3IC73EA3DNFJIXPRLPAIKB7G/action/replication_record"}},"created_at":"2026-07-05T07:07:40.270886+00:00","updated_at":"2026-07-05T07:07:40.270886+00:00"}