{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MHY4IJOM5AWQZDUXMEKYT2CVDX","short_pith_number":"pith:MHY4IJOM","schema_version":"1.0","canonical_sha256":"61f1c425cce82d0c8e97611589e8551de182451e0ffd6adfbd7199d79f0f8a12","source":{"kind":"arxiv","id":"2605.14126","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reinforcement learning post-training raises a Qwen3-8B model to 77 percent correctness on FHIR clinical queries, surpassing larger closed models.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jan P. Bremer, Marius S. Knorr, Nils Schweingruber, Robert M\\\"uller","submitted_at":"2026-05-13T21:27:21Z","abstract_excerpt":"Fast Healthcare Interoperability Resources (FHIR) is the dominant standard for interoperable exchange of healthcare data. In FHIR, electronic health records form a directed graph of resources. Answering clinically meaningful questions over FHIR requires agents to perform multi-step reasoning, filtering, and aggregation across multiple resource types. Prior work shows that even tool-augmented LLM agents (retrieval, code execution, multi-turn planning) often select the wrong resources or violate traversal constraints. We study this problem in the context of FHIR-AgentBench, a benchmark for reali"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T21:27:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"567d44002f2e6213549591e3fea47891316a6c7be41cba3fa01d3f383819bb43","abstract_canon_sha256":"52e8853a78ec8c87734ac98a6b25bb71dc31ecc07f94480c1c465ac50bb3f52c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:11.845231Z","signature_b64":"N+z7dji17VA84s713s2VIuavtNqVIbFO1ixN/PAV00tvWrEZ4J+C8GT4Z7L+eM0V2xbArOJBda9s3tb+sQ8KAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61f1c425cce82d0c8e97611589e8551de182451e0ffd6adfbd7199d79f0f8a12","last_reissued_at":"2026-05-17T23:39:11.844744Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:11.844744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reinforcement learning post-training raises a Qwen3-8B model to 77 percent correctness on FHIR clinical queries, surpassing larger closed models.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jan P. Bremer, Marius S. Knorr, Nils Schweingruber, Robert M\\\"uller","submitted_at":"2026-05-13T21:27:21Z","abstract_excerpt":"Fast Healthcare Interoperability Resources (FHIR) is the dominant standard for interoperable exchange of healthcare data. In FHIR, electronic health records form a directed graph of resources. Answering clinically meaningful questions over FHIR requires agents to perform multi-step reasoning, filtering, and aggregation across multiple resource types. Prior work shows that even tool-augmented LLM agents (retrieval, code execution, multi-turn planning) often select the wrong resources or violate traversal constraints. We study this problem in the context of FHIR-AgentBench, a benchmark for reali"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Empirically, our approach improves answer correctness from 50% (o4-mini) to 77% on FHIR-AgentBench using a smaller and cheaper Qwen3-8B model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an LLM Judge can supply reliable execution-grounded rewards without bias or systematic errors in judging multi-step FHIR traversals.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RL post-training lifts answer correctness on FHIR-AgentBench from 50% (o4-mini) to 77% with a cheaper Qwen3-8B CodeAct agent.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reinforcement learning post-training raises a Qwen3-8B model to 77 percent correctness on FHIR clinical queries, surpassing larger closed models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2095daef2331626e1d156c9ec4667e7e43672ac467fb9794f2adbff6b352a9c9"},"source":{"id":"2605.14126","kind":"arxiv","version":1},"verdict":{"id":"2f1d9550-d38b-4e8b-8e77-f703c37219b7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T04:53:35.494733Z","strongest_claim":"Empirically, our approach improves answer correctness from 50% (o4-mini) to 77% on FHIR-AgentBench using a smaller and cheaper Qwen3-8B model.","one_line_summary":"RL post-training lifts answer correctness on FHIR-AgentBench from 50% (o4-mini) to 77% with a cheaper Qwen3-8B CodeAct agent.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an LLM Judge can supply reliable execution-grounded rewards without bias or systematic errors in judging multi-step FHIR traversals.","pith_extraction_headline":"Reinforcement learning post-training raises a Qwen3-8B model to 77 percent correctness on FHIR clinical queries, surpassing larger closed models."},"references":{"count":66,"sample":[{"doi":"10.1093/jamia/ocx080","year":2017,"title":"Journal of the American Medical Informatics Association , author =","work_id":"c24070b8-a397-4077-97ed-5d4542edbc17","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.5009/gnl230272","year":2024,"title":"Gut and Liver , author =","work_id":"eabf3f84-9d5d-4b21-80a0-54e9e513f7b6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1001/journalofethics.2017.19.3.stas1-1703","year":2017,"title":"AMA journal of ethics , author =","work_id":"c8fd5c90-8a64-448f-b22f-64ef902ae287","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1002/wics.1549","year":2021,"title":"WIREs Computational Statistics , author =","work_id":"2dfbcab8-e428-4f15-aedd-905ef9aa0e76","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.isci.2024.109713","year":2024,"title":"iScience , author =","work_id":"acf0f2f5-0d21-4841-94a0-9e376fa33c40","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":66,"snapshot_sha256":"febf422a970a46c5f57efe1720c3f691045ab70d9445ee05ce14580ddab0f610","internal_anchors":8},"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":"2605.14126","created_at":"2026-05-17T23:39:11.844832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14126v1","created_at":"2026-05-17T23:39:11.844832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14126","created_at":"2026-05-17T23:39:11.844832+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHY4IJOM5AWQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHY4IJOM5AWQZDUX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHY4IJOM","created_at":"2026-05-18T12:33:37.589309+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/MHY4IJOM5AWQZDUXMEKYT2CVDX","json":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX.json","graph_json":"https://pith.science/api/pith-number/MHY4IJOM5AWQZDUXMEKYT2CVDX/graph.json","events_json":"https://pith.science/api/pith-number/MHY4IJOM5AWQZDUXMEKYT2CVDX/events.json","paper":"https://pith.science/paper/MHY4IJOM"},"agent_actions":{"view_html":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX","download_json":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX.json","view_paper":"https://pith.science/paper/MHY4IJOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14126&json=true","fetch_graph":"https://pith.science/api/pith-number/MHY4IJOM5AWQZDUXMEKYT2CVDX/graph.json","fetch_events":"https://pith.science/api/pith-number/MHY4IJOM5AWQZDUXMEKYT2CVDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX/action/storage_attestation","attest_author":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX/action/author_attestation","sign_citation":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX/action/citation_signature","submit_replication":"https://pith.science/pith/MHY4IJOM5AWQZDUXMEKYT2CVDX/action/replication_record"}},"created_at":"2026-05-17T23:39:11.844832+00:00","updated_at":"2026-05-17T23:39:11.844832+00:00"}