{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WEPM6ZLSUI7BBB7VYCMQLEWC6W","short_pith_number":"pith:WEPM6ZLS","schema_version":"1.0","canonical_sha256":"b11ecf6572a23e1087f5c0990592c2f58e69a9dbeb4d1cc2d5cfc23aff9f601d","source":{"kind":"arxiv","id":"2406.09454","version":1},"attestation_state":"computed","paper":{"title":"Advancing High Resolution Vision-Language Models in Biomedicine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Arda Pekis, Kevin Brown, Zekai Chen","submitted_at":"2024-06-12T18:29:26Z","abstract_excerpt":"Multi-modal learning has significantly advanced generative AI, especially in vision-language modeling. Innovations like GPT-4V and open-source projects such as LLaVA have enabled robust conversational agents capable of zero-shot task completions. However, applying these technologies in the biomedical field presents unique challenges. Recent initiatives like LLaVA-Med have started to adapt instruction-tuning for biomedical contexts using large datasets such as PMC-15M. Our research offers three key contributions: (i) we present a new instruct dataset enriched with medical image-text pairs from "},"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":"2406.09454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T18:29:26Z","cross_cats_sorted":["cs.AI","cs.CV","q-bio.QM"],"title_canon_sha256":"8797a586319e964da3dbbf91f2ee55faea828cd178775b6e8bfd9bcbf68111a0","abstract_canon_sha256":"6c3ab76bc0dc35628494211b2b5ca744930c5e53f18e28fee0da4f4c18e5b2b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:54.237956Z","signature_b64":"wEk0bWKxGFd3MaBo/OG8T57CnrpGhRuadtjT9mCeyfqnZpPt5qCa5SH/F1CSayVQVRzxIhtcBkdTixAG5sOmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b11ecf6572a23e1087f5c0990592c2f58e69a9dbeb4d1cc2d5cfc23aff9f601d","last_reissued_at":"2026-07-05T08:31:54.237536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:54.237536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing High Resolution Vision-Language Models in Biomedicine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Arda Pekis, Kevin Brown, Zekai Chen","submitted_at":"2024-06-12T18:29:26Z","abstract_excerpt":"Multi-modal learning has significantly advanced generative AI, especially in vision-language modeling. Innovations like GPT-4V and open-source projects such as LLaVA have enabled robust conversational agents capable of zero-shot task completions. However, applying these technologies in the biomedical field presents unique challenges. Recent initiatives like LLaVA-Med have started to adapt instruction-tuning for biomedical contexts using large datasets such as PMC-15M. Our research offers three key contributions: (i) we present a new instruct dataset enriched with medical image-text pairs from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09454","kind":"arxiv","version":1},"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/2406.09454/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":"2406.09454","created_at":"2026-07-05T08:31:54.237597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09454v1","created_at":"2026-07-05T08:31:54.237597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09454","created_at":"2026-07-05T08:31:54.237597+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEPM6ZLSUI7B","created_at":"2026-07-05T08:31:54.237597+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEPM6ZLSUI7BBB7V","created_at":"2026-07-05T08:31:54.237597+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEPM6ZLS","created_at":"2026-07-05T08:31:54.237597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09209","citing_title":"Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W","json":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W.json","graph_json":"https://pith.science/api/pith-number/WEPM6ZLSUI7BBB7VYCMQLEWC6W/graph.json","events_json":"https://pith.science/api/pith-number/WEPM6ZLSUI7BBB7VYCMQLEWC6W/events.json","paper":"https://pith.science/paper/WEPM6ZLS"},"agent_actions":{"view_html":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W","download_json":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W.json","view_paper":"https://pith.science/paper/WEPM6ZLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09454&json=true","fetch_graph":"https://pith.science/api/pith-number/WEPM6ZLSUI7BBB7VYCMQLEWC6W/graph.json","fetch_events":"https://pith.science/api/pith-number/WEPM6ZLSUI7BBB7VYCMQLEWC6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W/action/storage_attestation","attest_author":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W/action/author_attestation","sign_citation":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W/action/citation_signature","submit_replication":"https://pith.science/pith/WEPM6ZLSUI7BBB7VYCMQLEWC6W/action/replication_record"}},"created_at":"2026-07-05T08:31:54.237597+00:00","updated_at":"2026-07-05T08:31:54.237597+00:00"}