{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MFGEPO32PZDSB3HM4XR32LBGMO","short_pith_number":"pith:MFGEPO32","schema_version":"1.0","canonical_sha256":"614c47bb7a7e4720ecece5e3bd2c2663a6bb5b4a46976471a5f8dda5700c78cc","source":{"kind":"arxiv","id":"2412.12661","version":2},"attestation_state":"computed","paper":{"title":"MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Aditya Grover, Daniel Israel, Hritik Bansal, Shufan Li, Siyan Zhao, Tung Nguyen","submitted_at":"2024-12-17T08:30:00Z","abstract_excerpt":"Recent advancements in mixed-modal generative have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and generating multimodal patient reports. However, existing datasets face challenges such as small sizes, limited coverage of biomedical tasks and domains, and a reliance on narrow sources. To address these gaps, we present MedMax, a large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models. With 1.47 million instances, MedMax encompasses a diverse range of tasks, "},"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":"2412.12661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-17T08:30:00Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"c4c8e2ecdec7365927eb4c20139d85149d27e1f1022769992d4198a1b9f6b1c2","abstract_canon_sha256":"61eff5c8fd2a135578e4219a34d5f8b749982632fe39675ec09b49928c17ec43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:38.868163Z","signature_b64":"cW8usW8mLFrfNYdQrRxv5usOOXcsAuKC0f/2677QLfyIvWMuM1E6VfCC9tlCoJeSSlKgj4z+9k5pfflEGljnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"614c47bb7a7e4720ecece5e3bd2c2663a6bb5b4a46976471a5f8dda5700c78cc","last_reissued_at":"2026-07-05T10:52:38.867694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:38.867694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Aditya Grover, Daniel Israel, Hritik Bansal, Shufan Li, Siyan Zhao, Tung Nguyen","submitted_at":"2024-12-17T08:30:00Z","abstract_excerpt":"Recent advancements in mixed-modal generative have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and generating multimodal patient reports. However, existing datasets face challenges such as small sizes, limited coverage of biomedical tasks and domains, and a reliance on narrow sources. To address these gaps, we present MedMax, a large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models. With 1.47 million instances, MedMax encompasses a diverse range of tasks, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12661","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/2412.12661/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":"2412.12661","created_at":"2026-07-05T10:52:38.867752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12661v2","created_at":"2026-07-05T10:52:38.867752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12661","created_at":"2026-07-05T10:52:38.867752+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFGEPO32PZDS","created_at":"2026-07-05T10:52:38.867752+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFGEPO32PZDSB3HM","created_at":"2026-07-05T10:52:38.867752+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFGEPO32","created_at":"2026-07-05T10:52:38.867752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27500","citing_title":"Aloe-Vision: Robust Vision-Language Models for Healthcare","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15808","citing_title":"Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRI","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO","json":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO.json","graph_json":"https://pith.science/api/pith-number/MFGEPO32PZDSB3HM4XR32LBGMO/graph.json","events_json":"https://pith.science/api/pith-number/MFGEPO32PZDSB3HM4XR32LBGMO/events.json","paper":"https://pith.science/paper/MFGEPO32"},"agent_actions":{"view_html":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO","download_json":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO.json","view_paper":"https://pith.science/paper/MFGEPO32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12661&json=true","fetch_graph":"https://pith.science/api/pith-number/MFGEPO32PZDSB3HM4XR32LBGMO/graph.json","fetch_events":"https://pith.science/api/pith-number/MFGEPO32PZDSB3HM4XR32LBGMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO/action/storage_attestation","attest_author":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO/action/author_attestation","sign_citation":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO/action/citation_signature","submit_replication":"https://pith.science/pith/MFGEPO32PZDSB3HM4XR32LBGMO/action/replication_record"}},"created_at":"2026-07-05T10:52:38.867752+00:00","updated_at":"2026-07-05T10:52:38.867752+00:00"}