{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QQ2VEBSDVJB5ABTEEEFB5Z3VTQ","short_pith_number":"pith:QQ2VEBSD","schema_version":"1.0","canonical_sha256":"8435520643aa43d00664210a1ee7759c3aefea005f947e0f00a3789ff9d591a2","source":{"kind":"arxiv","id":"2506.14142","version":1},"attestation_state":"computed","paper":{"title":"RadFabric: Agentic AI System with Reasoning Capability for Radiology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fang Zeng, Kai Zhang, Lichao Sun, Ninghao Liu, Tianming Liu, Tianyu Lin, Wenting Chen, Xiang Li, Yichen Wu, Yi Dong, Yifan Zhou, Yihang Su, Yijun Luo, Yixuan Yuan, Yucheng Shi, Zhaojun Ding, Zhen Xiang","submitted_at":"2025-06-17T03:10:33Z","abstract_excerpt":"Chest X ray (CXR) imaging remains a critical diagnostic tool for thoracic conditions, but current automated systems face limitations in pathology coverage, diagnostic accuracy, and integration of visual and textual reasoning. To address these gaps, we propose RadFabric, a multi agent, multimodal reasoning framework that unifies visual and textual analysis for comprehensive CXR interpretation. RadFabric is built on the Model Context Protocol (MCP), enabling modularity, interoperability, and scalability for seamless integration of new diagnostic agents. The system employs specialized CXR agents "},"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":"2506.14142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T03:10:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bd6b62df6bb2e33885cf1ea3703b8eb57bfe06ceeb37445e6389266a528bbad8","abstract_canon_sha256":"a3fa10ca62cd1e17b1c34456976d5d6d7929f43a377657891266dd6c32403450"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:49.888292Z","signature_b64":"OXHAfgdPrwAMrm83pz4C774sLE+gj+NmM2sxdLTD0HY+w+EkU2Jv44CaOwjk+6Plclakb3CHINkIgTXkjVeVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8435520643aa43d00664210a1ee7759c3aefea005f947e0f00a3789ff9d591a2","last_reissued_at":"2026-07-05T11:22:49.887654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:49.887654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RadFabric: Agentic AI System with Reasoning Capability for Radiology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fang Zeng, Kai Zhang, Lichao Sun, Ninghao Liu, Tianming Liu, Tianyu Lin, Wenting Chen, Xiang Li, Yichen Wu, Yi Dong, Yifan Zhou, Yihang Su, Yijun Luo, Yixuan Yuan, Yucheng Shi, Zhaojun Ding, Zhen Xiang","submitted_at":"2025-06-17T03:10:33Z","abstract_excerpt":"Chest X ray (CXR) imaging remains a critical diagnostic tool for thoracic conditions, but current automated systems face limitations in pathology coverage, diagnostic accuracy, and integration of visual and textual reasoning. To address these gaps, we propose RadFabric, a multi agent, multimodal reasoning framework that unifies visual and textual analysis for comprehensive CXR interpretation. RadFabric is built on the Model Context Protocol (MCP), enabling modularity, interoperability, and scalability for seamless integration of new diagnostic agents. The system employs specialized CXR agents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14142","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/2506.14142/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":"2506.14142","created_at":"2026-07-05T11:22:49.887729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14142v1","created_at":"2026-07-05T11:22:49.887729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14142","created_at":"2026-07-05T11:22:49.887729+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQ2VEBSDVJB5","created_at":"2026-07-05T11:22:49.887729+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQ2VEBSDVJB5ABTE","created_at":"2026-07-05T11:22:49.887729+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQ2VEBSD","created_at":"2026-07-05T11:22:49.887729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.20490","citing_title":"RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02695","citing_title":"XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12144","citing_title":"VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ","json":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ.json","graph_json":"https://pith.science/api/pith-number/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/graph.json","events_json":"https://pith.science/api/pith-number/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/events.json","paper":"https://pith.science/paper/QQ2VEBSD"},"agent_actions":{"view_html":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ","download_json":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ.json","view_paper":"https://pith.science/paper/QQ2VEBSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14142&json=true","fetch_graph":"https://pith.science/api/pith-number/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/action/storage_attestation","attest_author":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/action/author_attestation","sign_citation":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/action/citation_signature","submit_replication":"https://pith.science/pith/QQ2VEBSDVJB5ABTEEEFB5Z3VTQ/action/replication_record"}},"created_at":"2026-07-05T11:22:49.887729+00:00","updated_at":"2026-07-05T11:22:49.887729+00:00"}