{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FIBTPSEHSNRTJJB6CTVMO6ZZBH","short_pith_number":"pith:FIBTPSEH","schema_version":"1.0","canonical_sha256":"2a0337c887936334a43e14eac77b3909da51e0c4c2c963b442373ea48a7f3f6f","source":{"kind":"arxiv","id":"2508.04915","version":1},"attestation_state":"computed","paper":{"title":"ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MA"],"primary_cat":"cs.AI","authors_text":"Huiya Zhao, Junyi Gao, Liantao Ma, Yasha Wang, Yinghao Zhu, Zixiang Wang","submitted_at":"2025-08-06T22:39:38Z","abstract_excerpt":"The efficacy of AI agents in healthcare research is hindered by their reliance on static, predefined strategies. This creates a critical limitation: agents can become better tool-users but cannot learn to become better strategic planners, a crucial skill for complex domains like healthcare. We introduce HealthFlow, a self-evolving AI agent that overcomes this limitation through a novel meta-level evolution mechanism. HealthFlow autonomously refines its own high-level problem-solving policies by distilling procedural successes and failures into a durable, strategic knowledge base. To anchor our"},"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":"2508.04915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-06T22:39:38Z","cross_cats_sorted":["cs.CL","cs.MA"],"title_canon_sha256":"483cd6523b74e3f6e3d014cdd89df313b6362cf7d07ef90379a67350e2470b1d","abstract_canon_sha256":"f0daf47c9444e554d09d73ddc1c79b9046b39d168d0a7ad575d17b550aba62b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:03.995511Z","signature_b64":"nGwzGxB1Vd+WrPTspeTik6CWo6BtK07wgvHkbuIlqWZEKbHKdtxLUSwGxYtWujJen/oYUIBeh3bv/B2bU1nyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a0337c887936334a43e14eac77b3909da51e0c4c2c963b442373ea48a7f3f6f","last_reissued_at":"2026-07-05T11:50:03.995086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:03.995086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MA"],"primary_cat":"cs.AI","authors_text":"Huiya Zhao, Junyi Gao, Liantao Ma, Yasha Wang, Yinghao Zhu, Zixiang Wang","submitted_at":"2025-08-06T22:39:38Z","abstract_excerpt":"The efficacy of AI agents in healthcare research is hindered by their reliance on static, predefined strategies. This creates a critical limitation: agents can become better tool-users but cannot learn to become better strategic planners, a crucial skill for complex domains like healthcare. We introduce HealthFlow, a self-evolving AI agent that overcomes this limitation through a novel meta-level evolution mechanism. HealthFlow autonomously refines its own high-level problem-solving policies by distilling procedural successes and failures into a durable, strategic knowledge base. To anchor our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04915","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/2508.04915/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":"2508.04915","created_at":"2026-07-05T11:50:03.995141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04915v1","created_at":"2026-07-05T11:50:03.995141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04915","created_at":"2026-07-05T11:50:03.995141+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIBTPSEHSNRT","created_at":"2026-07-05T11:50:03.995141+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIBTPSEHSNRTJJB6","created_at":"2026-07-05T11:50:03.995141+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIBTPSEH","created_at":"2026-07-05T11:50:03.995141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16081","citing_title":"Veritas-RPM: Provenance-Guided Multi-Agent False Positive Suppression for Remote Patient Monitoring","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH","json":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH.json","graph_json":"https://pith.science/api/pith-number/FIBTPSEHSNRTJJB6CTVMO6ZZBH/graph.json","events_json":"https://pith.science/api/pith-number/FIBTPSEHSNRTJJB6CTVMO6ZZBH/events.json","paper":"https://pith.science/paper/FIBTPSEH"},"agent_actions":{"view_html":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH","download_json":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH.json","view_paper":"https://pith.science/paper/FIBTPSEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04915&json=true","fetch_graph":"https://pith.science/api/pith-number/FIBTPSEHSNRTJJB6CTVMO6ZZBH/graph.json","fetch_events":"https://pith.science/api/pith-number/FIBTPSEHSNRTJJB6CTVMO6ZZBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH/action/storage_attestation","attest_author":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH/action/author_attestation","sign_citation":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH/action/citation_signature","submit_replication":"https://pith.science/pith/FIBTPSEHSNRTJJB6CTVMO6ZZBH/action/replication_record"}},"created_at":"2026-07-05T11:50:03.995141+00:00","updated_at":"2026-07-05T11:50:03.995141+00:00"}