{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:67BC3JCR7X2LWKZ2LYXTLGD3YH","short_pith_number":"pith:67BC3JCR","schema_version":"1.0","canonical_sha256":"f7c22da451fdf4bb2b3a5e2f35987bc1ef04cae67afc1bf6692aae73fdcf8460","source":{"kind":"arxiv","id":"2506.19835","version":1},"attestation_state":"computed","paper":{"title":"MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianbing Shen, Lingran Song, Yucheng Zhou","submitted_at":"2025-06-24T17:52:43Z","abstract_excerpt":"Recent advancements in medical Large Language Models (LLMs) have showcased their powerful reasoning and diagnostic capabilities. Despite their success, current unified multimodal medical LLMs face limitations in knowledge update costs, comprehensiveness, and flexibility. To address these challenges, we introduce the Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis (MAM). Inspired by our empirical findings highlighting the benefits of role assignment and diagnostic discernment in LLMs, MAM decomposes the medical diagnostic process into specialized roles: a General Practitioner, S"},"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":"2506.19835","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-24T17:52:43Z","cross_cats_sorted":[],"title_canon_sha256":"f005e37248c4e97b25d1b0c36ec234e051a2ea8e132f7d15cf68c6766769c82e","abstract_canon_sha256":"09dbf9a77ebf0edf521d7a668e793244fa0721ddc2d25b73178fccf89b945a9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:39.220845Z","signature_b64":"vLFr3FId6bJysGcztb0X8Aaekn4Q2xUkVk2wACFNel7q/kHScc2DHoBVO7EUzA+ytbqUkwKfyM3PfLmAB5j5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7c22da451fdf4bb2b3a5e2f35987bc1ef04cae67afc1bf6692aae73fdcf8460","last_reissued_at":"2026-07-05T11:26:39.220366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:39.220366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianbing Shen, Lingran Song, Yucheng Zhou","submitted_at":"2025-06-24T17:52:43Z","abstract_excerpt":"Recent advancements in medical Large Language Models (LLMs) have showcased their powerful reasoning and diagnostic capabilities. Despite their success, current unified multimodal medical LLMs face limitations in knowledge update costs, comprehensiveness, and flexibility. To address these challenges, we introduce the Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis (MAM). Inspired by our empirical findings highlighting the benefits of role assignment and diagnostic discernment in LLMs, MAM decomposes the medical diagnostic process into specialized roles: a General Practitioner, S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19835","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/2506.19835/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":"2506.19835","created_at":"2026-07-05T11:26:39.220421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19835v1","created_at":"2026-07-05T11:26:39.220421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19835","created_at":"2026-07-05T11:26:39.220421+00:00"},{"alias_kind":"pith_short_12","alias_value":"67BC3JCR7X2L","created_at":"2026-07-05T11:26:39.220421+00:00"},{"alias_kind":"pith_short_16","alias_value":"67BC3JCR7X2LWKZ2","created_at":"2026-07-05T11:26:39.220421+00:00"},{"alias_kind":"pith_short_8","alias_value":"67BC3JCR","created_at":"2026-07-05T11:26:39.220421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07761","citing_title":"Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning","ref_index":150,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":162,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH","json":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH.json","graph_json":"https://pith.science/api/pith-number/67BC3JCR7X2LWKZ2LYXTLGD3YH/graph.json","events_json":"https://pith.science/api/pith-number/67BC3JCR7X2LWKZ2LYXTLGD3YH/events.json","paper":"https://pith.science/paper/67BC3JCR"},"agent_actions":{"view_html":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH","download_json":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH.json","view_paper":"https://pith.science/paper/67BC3JCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19835&json=true","fetch_graph":"https://pith.science/api/pith-number/67BC3JCR7X2LWKZ2LYXTLGD3YH/graph.json","fetch_events":"https://pith.science/api/pith-number/67BC3JCR7X2LWKZ2LYXTLGD3YH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH/action/storage_attestation","attest_author":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH/action/author_attestation","sign_citation":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH/action/citation_signature","submit_replication":"https://pith.science/pith/67BC3JCR7X2LWKZ2LYXTLGD3YH/action/replication_record"}},"created_at":"2026-07-05T11:26:39.220421+00:00","updated_at":"2026-07-05T11:26:39.220421+00:00"}