{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LZ2YREIDXGXE5UB6E72J7UES5T","short_pith_number":"pith:LZ2YREID","canonical_record":{"source":{"id":"2504.13950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T09:16:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5af46fa9aa20b8972f092c5c0064c90d3e51c08497d22a15ab75b3b8d0346ed0","abstract_canon_sha256":"cb852cab1081493099ac38d81cb26a6b0731620667bf7f2505c280ca97d6d5ba"},"schema_version":"1.0"},"canonical_sha256":"5e75889103b9ae4ed03e27f49fd092ecfc7057903ccc22e246742a21969bc023","source":{"kind":"arxiv","id":"2504.13950","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13950","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13950v1","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13950","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"LZ2YREIDXGXE","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_16","alias_value":"LZ2YREIDXGXE5UB6","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_8","alias_value":"LZ2YREID","created_at":"2026-07-05T10:51:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LZ2YREIDXGXE5UB6E72J7UES5T","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T09:16:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5af46fa9aa20b8972f092c5c0064c90d3e51c08497d22a15ab75b3b8d0346ed0","abstract_canon_sha256":"cb852cab1081493099ac38d81cb26a6b0731620667bf7f2505c280ca97d6d5ba"},"schema_version":"1.0"},"canonical_sha256":"5e75889103b9ae4ed03e27f49fd092ecfc7057903ccc22e246742a21969bc023","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:08.631438Z","signature_b64":"7+bXqWLPSyqZVpYm+66l6XOCNeylvN+BpDx/WWWYSdQ6jV2dVY9Gk5Ib5BlCTFw844tlraFUs8EJP3Ii0FIBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e75889103b9ae4ed03e27f49fd092ecfc7057903ccc22e246742a21969bc023","last_reissued_at":"2026-07-05T10:51:08.630938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:08.630938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13950","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TanV+g+fz68yc9jnvrsBsNIouZDydUTT3FKImeSt3iTVI+ok5QkTXW3Dkccry3DEddM0AmcYF+QrCePs/pY4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:58:08.695023Z"},"content_sha256":"d0b077926dc9deae4dfbc292d1a285ae3d791877366354210a84f2122748f069","schema_version":"1.0","event_id":"sha256:d0b077926dc9deae4dfbc292d1a285ae3d791877366354210a84f2122748f069"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LZ2YREIDXGXE5UB6E72J7UES5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Heng Li, Jiang Liu, Yan Hu, Zhang Zhang, Zhongxi Qiu","submitted_at":"2025-04-16T09:16:12Z","abstract_excerpt":"This paper explores optimal data selection strategies for Reinforcement Learning with Verified Rewards (RLVR) training in the medical domain. While RLVR has shown exceptional potential for enhancing reasoning capabilities in large language models, most prior implementations have focused on mathematics and logical puzzles, with limited exploration of domain-specific applications like medicine. We investigate four distinct data sampling strategies from MedQA-USMLE: random sampling (baseline), and filtering using Phi-4, Gemma-3-27b-it, and Gemma-3-12b-it models. Using Gemma-3-12b-it as our base m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13950","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/2504.13950/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KxVPvMOV+7O9dcwTVe5ynVrO3yGragVFhqJq5Z+8FjUZ1R2EYAWITWDMG2oSjYhgJqJctz0hAovBmbZtxNsACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:58:08.695979Z"},"content_sha256":"029e1dde6c9f575ac6ee71c8dfa7b03521b97223daf4e9a3a0a75adc393250c1","schema_version":"1.0","event_id":"sha256:029e1dde6c9f575ac6ee71c8dfa7b03521b97223daf4e9a3a0a75adc393250c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZ2YREIDXGXE5UB6E72J7UES5T/bundle.json","state_url":"https://pith.science/pith/LZ2YREIDXGXE5UB6E72J7UES5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZ2YREIDXGXE5UB6E72J7UES5T/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T15:58:08Z","links":{"resolver":"https://pith.science/pith/LZ2YREIDXGXE5UB6E72J7UES5T","bundle":"https://pith.science/pith/LZ2YREIDXGXE5UB6E72J7UES5T/bundle.json","state":"https://pith.science/pith/LZ2YREIDXGXE5UB6E72J7UES5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZ2YREIDXGXE5UB6E72J7UES5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LZ2YREIDXGXE5UB6E72J7UES5T","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":"cb852cab1081493099ac38d81cb26a6b0731620667bf7f2505c280ca97d6d5ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T09:16:12Z","title_canon_sha256":"5af46fa9aa20b8972f092c5c0064c90d3e51c08497d22a15ab75b3b8d0346ed0"},"schema_version":"1.0","source":{"id":"2504.13950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13950","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13950v1","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13950","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"LZ2YREIDXGXE","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_16","alias_value":"LZ2YREIDXGXE5UB6","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_8","alias_value":"LZ2YREID","created_at":"2026-07-05T10:51:08Z"}],"graph_snapshots":[{"event_id":"sha256:029e1dde6c9f575ac6ee71c8dfa7b03521b97223daf4e9a3a0a75adc393250c1","target":"graph","created_at":"2026-07-05T10:51:08Z","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/2504.13950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores optimal data selection strategies for Reinforcement Learning with Verified Rewards (RLVR) training in the medical domain. While RLVR has shown exceptional potential for enhancing reasoning capabilities in large language models, most prior implementations have focused on mathematics and logical puzzles, with limited exploration of domain-specific applications like medicine. We investigate four distinct data sampling strategies from MedQA-USMLE: random sampling (baseline), and filtering using Phi-4, Gemma-3-27b-it, and Gemma-3-12b-it models. Using Gemma-3-12b-it as our base m","authors_text":"Heng Li, Jiang Liu, Yan Hu, Zhang Zhang, Zhongxi Qiu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T09:16:12Z","title":"Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13950","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:d0b077926dc9deae4dfbc292d1a285ae3d791877366354210a84f2122748f069","target":"record","created_at":"2026-07-05T10:51:08Z","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":"cb852cab1081493099ac38d81cb26a6b0731620667bf7f2505c280ca97d6d5ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T09:16:12Z","title_canon_sha256":"5af46fa9aa20b8972f092c5c0064c90d3e51c08497d22a15ab75b3b8d0346ed0"},"schema_version":"1.0","source":{"id":"2504.13950","kind":"arxiv","version":1}},"canonical_sha256":"5e75889103b9ae4ed03e27f49fd092ecfc7057903ccc22e246742a21969bc023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e75889103b9ae4ed03e27f49fd092ecfc7057903ccc22e246742a21969bc023","first_computed_at":"2026-07-05T10:51:08.630938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:08.630938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7+bXqWLPSyqZVpYm+66l6XOCNeylvN+BpDx/WWWYSdQ6jV2dVY9Gk5Ib5BlCTFw844tlraFUs8EJP3Ii0FIBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:08.631438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0b077926dc9deae4dfbc292d1a285ae3d791877366354210a84f2122748f069","sha256:029e1dde6c9f575ac6ee71c8dfa7b03521b97223daf4e9a3a0a75adc393250c1"],"state_sha256":"3d5eed5c9a0f08906d785e7d52130f6cb54424828cc067cc8c88cef874c6f717"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uWSShQ3hIPAd4gDuSgTu2LKq++4iEtaQBmbKL/6xZhzjILsQhXRZSQ7MFDDACVhAg9tRQZL+m+9/HsMyJtzNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:58:08.701664Z","bundle_sha256":"32549b83bd8ca9de80f31c4cd15969527f2f07368df5d6eb3c276a88946da81a"}}