{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2L4VMQARWNIAPTJPNAW63XHIAC","short_pith_number":"pith:2L4VMQAR","schema_version":"1.0","canonical_sha256":"d2f9564011b35007cd2f682deddce800aa193d71865e6434fdd195fcf647421b","source":{"kind":"arxiv","id":"2605.24699","version":1},"attestation_state":"computed","paper":{"title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Rey-Blanco, Roberto Cruz","submitted_at":"2026-05-23T18:36:58Z","abstract_excerpt":"Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can come from architectural and engine-level design. We present MDIA, a Multi-agent Diagnostic Intelligence Agent implemented as a 7-node specialty-routed clinical reasoning graph, on the full HealthBench Professional benchmark (n = 525), on a non-fine-tuned LLM. MDIA achieves 0.6272 under OpenAI's GPT-5.4-2026-03-05, which is +3.72 pp above the performance of OpenAI's ChatGPT for Clinicians. The experimental work shows that performance lift is att"},"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":"2605.24699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T18:36:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"936da72cb524cb2db1203b2b1bee900f65f6cfe3de68c4a0be16a17a046d9357","abstract_canon_sha256":"7166bad814874b0613f6917197d1473af2e545455acf715dce9508f10761a49c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:53.880093Z","signature_b64":"+ePsmtG4674SGdMzdHPMU/+ChU4vsknk8UYCDZgzfnJdEvR6QPX24X9wwt2JL4TFQEsQ86E2FU+C0I2X8h8cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2f9564011b35007cd2f682deddce800aa193d71865e6434fdd195fcf647421b","last_reissued_at":"2026-05-26T01:03:53.879295Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:53.879295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Rey-Blanco, Roberto Cruz","submitted_at":"2026-05-23T18:36:58Z","abstract_excerpt":"Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can come from architectural and engine-level design. We present MDIA, a Multi-agent Diagnostic Intelligence Agent implemented as a 7-node specialty-routed clinical reasoning graph, on the full HealthBench Professional benchmark (n = 525), on a non-fine-tuned LLM. MDIA achieves 0.6272 under OpenAI's GPT-5.4-2026-03-05, which is +3.72 pp above the performance of OpenAI's ChatGPT for Clinicians. The experimental work shows that performance lift is att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24699","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/2605.24699/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":"2605.24699","created_at":"2026-05-26T01:03:53.879446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24699v1","created_at":"2026-05-26T01:03:53.879446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24699","created_at":"2026-05-26T01:03:53.879446+00:00"},{"alias_kind":"pith_short_12","alias_value":"2L4VMQARWNIA","created_at":"2026-05-26T01:03:53.879446+00:00"},{"alias_kind":"pith_short_16","alias_value":"2L4VMQARWNIAPTJP","created_at":"2026-05-26T01:03:53.879446+00:00"},{"alias_kind":"pith_short_8","alias_value":"2L4VMQAR","created_at":"2026-05-26T01:03:53.879446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC","json":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC.json","graph_json":"https://pith.science/api/pith-number/2L4VMQARWNIAPTJPNAW63XHIAC/graph.json","events_json":"https://pith.science/api/pith-number/2L4VMQARWNIAPTJPNAW63XHIAC/events.json","paper":"https://pith.science/paper/2L4VMQAR"},"agent_actions":{"view_html":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC","download_json":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC.json","view_paper":"https://pith.science/paper/2L4VMQAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24699&json=true","fetch_graph":"https://pith.science/api/pith-number/2L4VMQARWNIAPTJPNAW63XHIAC/graph.json","fetch_events":"https://pith.science/api/pith-number/2L4VMQARWNIAPTJPNAW63XHIAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC/action/storage_attestation","attest_author":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC/action/author_attestation","sign_citation":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC/action/citation_signature","submit_replication":"https://pith.science/pith/2L4VMQARWNIAPTJPNAW63XHIAC/action/replication_record"}},"created_at":"2026-05-26T01:03:53.879446+00:00","updated_at":"2026-05-26T01:03:53.879446+00:00"}