{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:36BA4U3LSJFUZXHGNIUHWUCZLI","short_pith_number":"pith:36BA4U3L","schema_version":"1.0","canonical_sha256":"df820e536b924b4cdce66a287b50595a04ed12910f146c2ca991e9fd5aa65165","source":{"kind":"arxiv","id":"2406.19973","version":2},"attestation_state":"computed","paper":{"title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Can Qin, Guohao Sun, Huazhu Fu, Linwei Wang, Zhiqiang Tao","submitted_at":"2024-06-28T15:01:23Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown significant potential in assisting medical diagnosis by leveraging extensive biomedical datasets. However, the advancement of medical image understanding and reasoning critically depends on building high-quality visual instruction data, which is costly and labor-intensive to obtain, particularly in the medical domain. To mitigate this data-starving issue, we introduce Self-Training Large Language and Vision Assistant for Medicine (STLLaVA-Med). The proposed method is designed to train a policy model (an LVLM) capable of auto-generating medical vi"},"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":"2406.19973","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-28T15:01:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"02595d63ceef0df589299739b988113948ff748963ca7b8ae8d702159a6b1ff2","abstract_canon_sha256":"937a890233c717229cdecec8231c8e6d26c18ec94b4b5fd238b8b0ddc5cc3f5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:44.879788Z","signature_b64":"hVDvD3cl07coJIpYGbZPZPsLwn3s+9GdyxTFPCx/wRHryHFX5gzOgUiUM7HRg8HBSJr0MG29/JfyjVI6jALqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df820e536b924b4cdce66a287b50595a04ed12910f146c2ca991e9fd5aa65165","last_reissued_at":"2026-07-05T09:25:44.879289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:44.879289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Can Qin, Guohao Sun, Huazhu Fu, Linwei Wang, Zhiqiang Tao","submitted_at":"2024-06-28T15:01:23Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown significant potential in assisting medical diagnosis by leveraging extensive biomedical datasets. However, the advancement of medical image understanding and reasoning critically depends on building high-quality visual instruction data, which is costly and labor-intensive to obtain, particularly in the medical domain. To mitigate this data-starving issue, we introduce Self-Training Large Language and Vision Assistant for Medicine (STLLaVA-Med). The proposed method is designed to train a policy model (an LVLM) capable of auto-generating medical vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19973","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/2406.19973/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":"2406.19973","created_at":"2026-07-05T09:25:44.879353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19973v2","created_at":"2026-07-05T09:25:44.879353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19973","created_at":"2026-07-05T09:25:44.879353+00:00"},{"alias_kind":"pith_short_12","alias_value":"36BA4U3LSJFU","created_at":"2026-07-05T09:25:44.879353+00:00"},{"alias_kind":"pith_short_16","alias_value":"36BA4U3LSJFUZXHG","created_at":"2026-07-05T09:25:44.879353+00:00"},{"alias_kind":"pith_short_8","alias_value":"36BA4U3L","created_at":"2026-07-05T09:25:44.879353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18687","citing_title":"Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI","json":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI.json","graph_json":"https://pith.science/api/pith-number/36BA4U3LSJFUZXHGNIUHWUCZLI/graph.json","events_json":"https://pith.science/api/pith-number/36BA4U3LSJFUZXHGNIUHWUCZLI/events.json","paper":"https://pith.science/paper/36BA4U3L"},"agent_actions":{"view_html":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI","download_json":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI.json","view_paper":"https://pith.science/paper/36BA4U3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19973&json=true","fetch_graph":"https://pith.science/api/pith-number/36BA4U3LSJFUZXHGNIUHWUCZLI/graph.json","fetch_events":"https://pith.science/api/pith-number/36BA4U3LSJFUZXHGNIUHWUCZLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI/action/storage_attestation","attest_author":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI/action/author_attestation","sign_citation":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI/action/citation_signature","submit_replication":"https://pith.science/pith/36BA4U3LSJFUZXHGNIUHWUCZLI/action/replication_record"}},"created_at":"2026-07-05T09:25:44.879353+00:00","updated_at":"2026-07-05T09:25:44.879353+00:00"}