{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IGX4FC6H23Y2IEYILS5FNYHB26","short_pith_number":"pith:IGX4FC6H","canonical_record":{"source":{"id":"2505.13973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:20Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2e2d1390f023370033d07fd8f5cc6fbc757955ebe6adae1a7e11e22ab11e5699","abstract_canon_sha256":"78b1be3e543d18419a12858b2350e594511648372184bbf66a744f384cc52857"},"schema_version":"1.0"},"canonical_sha256":"41afc28bc7d6f1a413085cba56e0e1d7b5e341b11f1b63ac4868250af7512cfd","source":{"kind":"arxiv","id":"2505.13973","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13973","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13973v1","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13973","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"IGX4FC6H23Y2","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"IGX4FC6H23Y2IEYI","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"IGX4FC6H","created_at":"2026-07-05T11:05:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IGX4FC6H23Y2IEYILS5FNYHB26","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:20Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2e2d1390f023370033d07fd8f5cc6fbc757955ebe6adae1a7e11e22ab11e5699","abstract_canon_sha256":"78b1be3e543d18419a12858b2350e594511648372184bbf66a744f384cc52857"},"schema_version":"1.0"},"canonical_sha256":"41afc28bc7d6f1a413085cba56e0e1d7b5e341b11f1b63ac4868250af7512cfd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:54.123372Z","signature_b64":"67EsOHDd4GUWoG2rCNTqP/0ztgHIjFMOO5L5ILY78ZroHw1Ntj26ZsrFIHg/DuNfIOv960yXvoPZDDQJZsLMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41afc28bc7d6f1a413085cba56e0e1d7b5e341b11f1b63ac4868250af7512cfd","last_reissued_at":"2026-07-05T11:05:54.122906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:54.122906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13973","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":"2026-07-05T11:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rZrwE6RzJ9MiLR8s2dw/ysjL9AMiGzvNz+SV+6mck/BECen6yAM4EsQtYad2THGmNdRxX8zjA1Gf7Aqx9SWTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:14:02.429848Z"},"content_sha256":"9c8626dcc5e11f784578f92ff8b885bc6dad58779b2c7fcb8826775318917920","schema_version":"1.0","event_id":"sha256:9c8626dcc5e11f784578f92ff8b885bc6dad58779b2c7fcb8826775318917920"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IGX4FC6H23Y2IEYILS5FNYHB26","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Abolfazl Razi, Aris Sotiras, Peijie Qiu, Wenhui Zhu, Xin Li, Xiwen Chen, Xuanzhao Dong, Yalin Wang, Yi Su","submitted_at":"2025-05-20T06:12:20Z","abstract_excerpt":"Recently, reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs), particularly following the introduction of Group Relative Policy Optimization (GRPO). However, directly applying it to medical tasks remains challenging for achieving clinically grounded model behavior. Motivated by the need to align model response with clinical expectations, we investigate four critical dimensions that affect the effectiveness of RL-based tuning in medical visual question answering (VQA): base model initialization strategy, the role of medical semantic al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13973","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/2505.13973/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":"2026-07-05T11:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j8Trtg4YILM1ssIgVMutqBNZUqv4FphNvkpuZmu48zfsa3adGTesNZRHFEPAjEE3OBBuYc6eihjULK1wkywEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:14:02.430349Z"},"content_sha256":"bfb85b647c190a7c19770d68e04483e940934ed8c02311ba8106a356e7a1bee2","schema_version":"1.0","event_id":"sha256:bfb85b647c190a7c19770d68e04483e940934ed8c02311ba8106a356e7a1bee2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGX4FC6H23Y2IEYILS5FNYHB26/bundle.json","state_url":"https://pith.science/pith/IGX4FC6H23Y2IEYILS5FNYHB26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGX4FC6H23Y2IEYILS5FNYHB26/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":"2026-08-08T11:14:02Z","links":{"resolver":"https://pith.science/pith/IGX4FC6H23Y2IEYILS5FNYHB26","bundle":"https://pith.science/pith/IGX4FC6H23Y2IEYILS5FNYHB26/bundle.json","state":"https://pith.science/pith/IGX4FC6H23Y2IEYILS5FNYHB26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGX4FC6H23Y2IEYILS5FNYHB26/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IGX4FC6H23Y2IEYILS5FNYHB26","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":"78b1be3e543d18419a12858b2350e594511648372184bbf66a744f384cc52857","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:20Z","title_canon_sha256":"2e2d1390f023370033d07fd8f5cc6fbc757955ebe6adae1a7e11e22ab11e5699"},"schema_version":"1.0","source":{"id":"2505.13973","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13973","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13973v1","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13973","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"IGX4FC6H23Y2","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"IGX4FC6H23Y2IEYI","created_at":"2026-07-05T11:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"IGX4FC6H","created_at":"2026-07-05T11:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:bfb85b647c190a7c19770d68e04483e940934ed8c02311ba8106a356e7a1bee2","target":"graph","created_at":"2026-07-05T11:05:54Z","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/2505.13973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs), particularly following the introduction of Group Relative Policy Optimization (GRPO). However, directly applying it to medical tasks remains challenging for achieving clinically grounded model behavior. Motivated by the need to align model response with clinical expectations, we investigate four critical dimensions that affect the effectiveness of RL-based tuning in medical visual question answering (VQA): base model initialization strategy, the role of medical semantic al","authors_text":"Abolfazl Razi, Aris Sotiras, Peijie Qiu, Wenhui Zhu, Xin Li, Xiwen Chen, Xuanzhao Dong, Yalin Wang, Yi Su","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:20Z","title":"Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13973","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":"sha256:9c8626dcc5e11f784578f92ff8b885bc6dad58779b2c7fcb8826775318917920","target":"record","created_at":"2026-07-05T11:05:54Z","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":"78b1be3e543d18419a12858b2350e594511648372184bbf66a744f384cc52857","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:20Z","title_canon_sha256":"2e2d1390f023370033d07fd8f5cc6fbc757955ebe6adae1a7e11e22ab11e5699"},"schema_version":"1.0","source":{"id":"2505.13973","kind":"arxiv","version":1}},"canonical_sha256":"41afc28bc7d6f1a413085cba56e0e1d7b5e341b11f1b63ac4868250af7512cfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41afc28bc7d6f1a413085cba56e0e1d7b5e341b11f1b63ac4868250af7512cfd","first_computed_at":"2026-07-05T11:05:54.122906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:54.122906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67EsOHDd4GUWoG2rCNTqP/0ztgHIjFMOO5L5ILY78ZroHw1Ntj26ZsrFIHg/DuNfIOv960yXvoPZDDQJZsLMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:54.123372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13973","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c8626dcc5e11f784578f92ff8b885bc6dad58779b2c7fcb8826775318917920","sha256:bfb85b647c190a7c19770d68e04483e940934ed8c02311ba8106a356e7a1bee2"],"state_sha256":"e5751044ff94b4ab40f024eb729f04a611b168bba7069f62c10d5cc53547aa88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQvYlJelBwR7qzX3toPVUGR6XiTLRADOS3awcsuE/2HCeeSAQ6lgoU4JaaFM1FszoM0PXKlNh2Jhm3k7U3RaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:14:02.435630Z","bundle_sha256":"c29aa3e1eb85d24858d7cebe48a2d7c04d9b2389d73af766d5d2b64a9916cfc5"}}