{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IVSZQVYNR7ISHE5IFVUBDRQJ7I","short_pith_number":"pith:IVSZQVYN","schema_version":"1.0","canonical_sha256":"456598570d8fd12393a82d6811c609fa2a2c11de5f364c660c2d7b79ea8345fd","source":{"kind":"arxiv","id":"2503.13856","version":1},"attestation_state":"computed","paper":{"title":"MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hewei Wang, Kai Chen, Tianpei Yang, Wei Dong, Xinfeng Li, Yang Gao","submitted_at":"2025-03-18T03:07:34Z","abstract_excerpt":"Large Language Models (LLMs) have made significant progress in various fields. However, challenges remain in Multi-Disciplinary Team (MDT) medical consultations. Current research enhances reasoning through role assignment, task decomposition, and accumulation of medical experience. Multi-role collaboration in MDT consultations often results in excessively long dialogue histories. This increases the model's cognitive burden and degrades both efficiency and accuracy. Some methods only store treatment histories. They do not extract effective experience or reflect on errors. This limits knowledge "},"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":"2503.13856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T03:07:34Z","cross_cats_sorted":[],"title_canon_sha256":"7367257313c18d9d3154432d891d7ab9a52dd963b456e396aaa763e173040605","abstract_canon_sha256":"9cec0a83ddfc0bbc0b9bd762aca5c90a0279feca45fc853e0d13855b783932d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:19.893026Z","signature_b64":"qHiEys1s0XHoOxdRH4Stj4aRyIgtuTHbW4DgWJU3eJdZWFNncBvOH8VbPvktTD1WUF4756KD7JjWwB0B9puxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"456598570d8fd12393a82d6811c609fa2a2c11de5f364c660c2d7b79ea8345fd","last_reissued_at":"2026-07-05T10:33:19.892391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:19.892391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hewei Wang, Kai Chen, Tianpei Yang, Wei Dong, Xinfeng Li, Yang Gao","submitted_at":"2025-03-18T03:07:34Z","abstract_excerpt":"Large Language Models (LLMs) have made significant progress in various fields. However, challenges remain in Multi-Disciplinary Team (MDT) medical consultations. Current research enhances reasoning through role assignment, task decomposition, and accumulation of medical experience. Multi-role collaboration in MDT consultations often results in excessively long dialogue histories. This increases the model's cognitive burden and degrades both efficiency and accuracy. Some methods only store treatment histories. They do not extract effective experience or reflect on errors. This limits knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13856","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/2503.13856/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":"2503.13856","created_at":"2026-07-05T10:33:19.892465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13856v1","created_at":"2026-07-05T10:33:19.892465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13856","created_at":"2026-07-05T10:33:19.892465+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVSZQVYNR7IS","created_at":"2026-07-05T10:33:19.892465+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVSZQVYNR7ISHE5I","created_at":"2026-07-05T10:33:19.892465+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVSZQVYN","created_at":"2026-07-05T10:33:19.892465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":163,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03416","citing_title":"MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02812","citing_title":"Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I","json":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I.json","graph_json":"https://pith.science/api/pith-number/IVSZQVYNR7ISHE5IFVUBDRQJ7I/graph.json","events_json":"https://pith.science/api/pith-number/IVSZQVYNR7ISHE5IFVUBDRQJ7I/events.json","paper":"https://pith.science/paper/IVSZQVYN"},"agent_actions":{"view_html":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I","download_json":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I.json","view_paper":"https://pith.science/paper/IVSZQVYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13856&json=true","fetch_graph":"https://pith.science/api/pith-number/IVSZQVYNR7ISHE5IFVUBDRQJ7I/graph.json","fetch_events":"https://pith.science/api/pith-number/IVSZQVYNR7ISHE5IFVUBDRQJ7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I/action/storage_attestation","attest_author":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I/action/author_attestation","sign_citation":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I/action/citation_signature","submit_replication":"https://pith.science/pith/IVSZQVYNR7ISHE5IFVUBDRQJ7I/action/replication_record"}},"created_at":"2026-07-05T10:33:19.892465+00:00","updated_at":"2026-07-05T10:33:19.892465+00:00"}