{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PMI7K22QU33FM7PXDI2HCLPOYX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ba31ec7df7d1ecec7a5007b8cb26001250f7e5c0891d2ad620d55c96b53f4cdb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T14:27:37Z","title_canon_sha256":"cec6c24f240bc8a296343df551aed83762bd4d641e6a2613477d1740bd26f586"},"schema_version":"1.0","source":{"id":"2505.17952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17952","created_at":"2026-07-05T11:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17952v1","created_at":"2026-07-05T11:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17952","created_at":"2026-07-05T11:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"PMI7K22QU33F","created_at":"2026-07-05T11:08:34Z"},{"alias_kind":"pith_short_16","alias_value":"PMI7K22QU33FM7PX","created_at":"2026-07-05T11:08:34Z"},{"alias_kind":"pith_short_8","alias_value":"PMI7K22Q","created_at":"2026-07-05T11:08:34Z"}],"graph_snapshots":[{"event_id":"sha256:d307a666e68acece88f556c14bd68190ae9cf461bb69de5f3c9c81dffd417a75","target":"graph","created_at":"2026-07-05T11:08:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.17952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improving performance on complex tasks and enabling interpretable decision making in large language models (LLMs), especially for clinical applications, requires effective reasoning. Yet this remains challenging without supervised fine-tuning (SFT) on costly chain-of-thought (CoT) data distilled from closed-source models (e.g., GPT-4o). In this work, we present AlphaMed, the first medical LLM to show that reasoning capability can emerge purely through reinforcement learning (RL), using minimalist rule-based rewards on public multiple-choice QA datasets, without relying on SFT or distilled CoT ","authors_text":"Che Liu, Daniel Rueckert, Fangzhen Lin, Haozhe Wang, Jiazhen Pan, Rossella Arcucci, Wenjia Bai, Yong Dai, Zhongwei Wan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T14:27:37Z","title":"Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17952","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab3608fcf19403b5691705d182f21b8f3d1abde83408ebef4821d4b3a76f3b99","target":"record","created_at":"2026-07-05T11:08:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ba31ec7df7d1ecec7a5007b8cb26001250f7e5c0891d2ad620d55c96b53f4cdb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T14:27:37Z","title_canon_sha256":"cec6c24f240bc8a296343df551aed83762bd4d641e6a2613477d1740bd26f586"},"schema_version":"1.0","source":{"id":"2505.17952","kind":"arxiv","version":1}},"canonical_sha256":"7b11f56b50a6f6567df71a34712deec5df5dfeba3acb5013211b8b180ccd96c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b11f56b50a6f6567df71a34712deec5df5dfeba3acb5013211b8b180ccd96c0","first_computed_at":"2026-07-05T11:08:34.231420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:34.231420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAdviW73N7vff6WKybfFiKY1A9518ifh90RefnhvaGYmJv/rsx3SLC8Gtvq1HeNlAUlx6zY2fpicfl5XUEYUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:34.231873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab3608fcf19403b5691705d182f21b8f3d1abde83408ebef4821d4b3a76f3b99","sha256:d307a666e68acece88f556c14bd68190ae9cf461bb69de5f3c9c81dffd417a75"],"state_sha256":"2336e7fd80c49a25c0af08c78248a40dd2c2c6d264af39c1dc7138245268b80b"}