{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6OH4C5OU5KL3Q2UAYQMU5L7KHG","short_pith_number":"pith:6OH4C5OU","schema_version":"1.0","canonical_sha256":"f38fc175d4ea97b86a80c4194eafea39a2c453d5ca3dcc88834734ee325f1e80","source":{"kind":"arxiv","id":"2505.06898","version":1},"attestation_state":"computed","paper":{"title":"Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bodong Du, Haonan Wang, Honglong Yang, Lehan Wang, Qixiang Zhang, Shanshan Song, Xiaomeng Li, Xinpeng Ding, Yi Qin","submitted_at":"2025-05-11T08:32:01Z","abstract_excerpt":"Generalist Medical AI (GMAI) systems have demonstrated expert-level performance in biomedical perception tasks, yet their clinical utility remains limited by inadequate multi-modal explainability and suboptimal prognostic capabilities. Here, we present XMedGPT, a clinician-centric, multi-modal AI assistant that integrates textual and visual interpretability to support transparent and trustworthy medical decision-making. XMedGPT not only produces accurate diagnostic and descriptive outputs, but also grounds referenced anatomical sites within medical images, bridging critical gaps in interpretab"},"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":"2505.06898","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-11T08:32:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1dff9de8ea4b4b108e865051b2cef6c060aaf4f609a282d67bada0bdc2329a29","abstract_canon_sha256":"ac23d4b0d7e99515adaa959b80b384df64b02e4240689b4885e7ecd1410c4436"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:38.823705Z","signature_b64":"nOteKCZ4QkPzFU41GsDEpdVKWgJnmf6RuwzaVFBPEIYtCWLzD6iDLXs8bn+LHVt3UqWFWvwB2S9ubvRfMriCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f38fc175d4ea97b86a80c4194eafea39a2c453d5ca3dcc88834734ee325f1e80","last_reissued_at":"2026-07-05T11:01:38.823148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:38.823148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bodong Du, Haonan Wang, Honglong Yang, Lehan Wang, Qixiang Zhang, Shanshan Song, Xiaomeng Li, Xinpeng Ding, Yi Qin","submitted_at":"2025-05-11T08:32:01Z","abstract_excerpt":"Generalist Medical AI (GMAI) systems have demonstrated expert-level performance in biomedical perception tasks, yet their clinical utility remains limited by inadequate multi-modal explainability and suboptimal prognostic capabilities. Here, we present XMedGPT, a clinician-centric, multi-modal AI assistant that integrates textual and visual interpretability to support transparent and trustworthy medical decision-making. XMedGPT not only produces accurate diagnostic and descriptive outputs, but also grounds referenced anatomical sites within medical images, bridging critical gaps in interpretab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06898","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/2505.06898/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":"2505.06898","created_at":"2026-07-05T11:01:38.823206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06898v1","created_at":"2026-07-05T11:01:38.823206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06898","created_at":"2026-07-05T11:01:38.823206+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OH4C5OU5KL3","created_at":"2026-07-05T11:01:38.823206+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OH4C5OU5KL3Q2UA","created_at":"2026-07-05T11:01:38.823206+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OH4C5OU","created_at":"2026-07-05T11:01:38.823206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22567","citing_title":"Unifying Biomedical Vision-Language Expertise: Towards a Generalist Foundation Model via Multi-CLIP Knowledge Distillation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG","json":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG.json","graph_json":"https://pith.science/api/pith-number/6OH4C5OU5KL3Q2UAYQMU5L7KHG/graph.json","events_json":"https://pith.science/api/pith-number/6OH4C5OU5KL3Q2UAYQMU5L7KHG/events.json","paper":"https://pith.science/paper/6OH4C5OU"},"agent_actions":{"view_html":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG","download_json":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG.json","view_paper":"https://pith.science/paper/6OH4C5OU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06898&json=true","fetch_graph":"https://pith.science/api/pith-number/6OH4C5OU5KL3Q2UAYQMU5L7KHG/graph.json","fetch_events":"https://pith.science/api/pith-number/6OH4C5OU5KL3Q2UAYQMU5L7KHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG/action/storage_attestation","attest_author":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG/action/author_attestation","sign_citation":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG/action/citation_signature","submit_replication":"https://pith.science/pith/6OH4C5OU5KL3Q2UAYQMU5L7KHG/action/replication_record"}},"created_at":"2026-07-05T11:01:38.823206+00:00","updated_at":"2026-07-05T11:01:38.823206+00:00"}