{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T4JRGUD4RZOSMNMLRDEZDVSZ45","short_pith_number":"pith:T4JRGUD4","canonical_record":{"source":{"id":"2607.15661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T06:13:13Z","cross_cats_sorted":[],"title_canon_sha256":"56a75a1ba89f401a31d73f981f705a89987375f5d460eca4232581be188e5353","abstract_canon_sha256":"5b32dc21310e75da4b589ba9ea1f9984f25b82ca72225dddabf12715a9fb5b04"},"schema_version":"1.0"},"canonical_sha256":"9f1313507c8e5d26358b88c991d659e76add9719d42ded5d15aa9d85fca59309","source":{"kind":"arxiv","id":"2607.15661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15661","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15661v1","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15661","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"T4JRGUD4RZOS","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"T4JRGUD4RZOSMNML","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"T4JRGUD4","created_at":"2026-07-20T01:19:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T4JRGUD4RZOSMNMLRDEZDVSZ45","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T06:13:13Z","cross_cats_sorted":[],"title_canon_sha256":"56a75a1ba89f401a31d73f981f705a89987375f5d460eca4232581be188e5353","abstract_canon_sha256":"5b32dc21310e75da4b589ba9ea1f9984f25b82ca72225dddabf12715a9fb5b04"},"schema_version":"1.0"},"canonical_sha256":"9f1313507c8e5d26358b88c991d659e76add9719d42ded5d15aa9d85fca59309","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:19:02.885600Z","signature_b64":"mHZldLmUZL9yKM/uXDIuJBFOC+XIzeoSvt3LLaMtAOg7d1H2rPtTuLNC/qT1uK1eSIOccQa8bkZfN1sOwAZ+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f1313507c8e5d26358b88c991d659e76add9719d42ded5d15aa9d85fca59309","last_reissued_at":"2026-07-20T01:19:02.884719Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:19:02.884719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15661","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":"2026-07-20T01:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"33Ql9n4UbxCtFSaUvnjBIIO22X+eVODgamC1N7qjW8QiWVvCS70Ety/kxWcW5NBWI568ElL53rWTRmXKHMCnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:13:36.049902Z"},"content_sha256":"0f62f158d33f98e81c143e259dceba8d6d74d21215fd1fefc399332f52943538","schema_version":"1.0","event_id":"sha256:0f62f158d33f98e81c143e259dceba8d6d74d21215fd1fefc399332f52943538"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T4JRGUD4RZOSMNMLRDEZDVSZ45","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingcong Yan, Chunlei Li, Jingliang Hu, Lei Li, Lichao Mou, Shengwu Xiong, Shilan Zhang, Xiao Xiang Zhu, Yaxiong Chen, Yilei Shi","submitted_at":"2026-07-17T06:13:13Z","abstract_excerpt":"Large vision-language models (LVLMs) can be adapted to specialized medical imaging tasks via parameter-efficient fine-tuning approaches such as low-rank adaptation (LoRA), leading to a growing ecosystem of expert models tailored to specific imaging modalities and clinical scenarios. However, deploying multiple expert LVLMs in practice incurs substantial computational and operational overhead. Model merging provides a promising solution by consolidating multiple experts into a single model without retraining, yet it remains largely unexplored in the medical domain. In this work, we present the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15661","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/2607.15661/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":"2026-07-20T01:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wb+wWDOz7Ozg1iGVM6l+cBn3oc+rJ6iiifnBIwh9zhLkhvdSvRmWmoX+P+N37lQi6G2CvKeKIIyYtFoYVRPGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:13:36.050870Z"},"content_sha256":"e33f3a883798e5a0c6393acf75fe95838bc21cd7307440bdef4a401f4e36f944","schema_version":"1.0","event_id":"sha256:e33f3a883798e5a0c6393acf75fe95838bc21cd7307440bdef4a401f4e36f944"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4JRGUD4RZOSMNMLRDEZDVSZ45/bundle.json","state_url":"https://pith.science/pith/T4JRGUD4RZOSMNMLRDEZDVSZ45/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4JRGUD4RZOSMNMLRDEZDVSZ45/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":"2026-08-06T06:13:36Z","links":{"resolver":"https://pith.science/pith/T4JRGUD4RZOSMNMLRDEZDVSZ45","bundle":"https://pith.science/pith/T4JRGUD4RZOSMNMLRDEZDVSZ45/bundle.json","state":"https://pith.science/pith/T4JRGUD4RZOSMNMLRDEZDVSZ45/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4JRGUD4RZOSMNMLRDEZDVSZ45/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T4JRGUD4RZOSMNMLRDEZDVSZ45","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":"5b32dc21310e75da4b589ba9ea1f9984f25b82ca72225dddabf12715a9fb5b04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T06:13:13Z","title_canon_sha256":"56a75a1ba89f401a31d73f981f705a89987375f5d460eca4232581be188e5353"},"schema_version":"1.0","source":{"id":"2607.15661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15661","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15661v1","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15661","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"T4JRGUD4RZOS","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"T4JRGUD4RZOSMNML","created_at":"2026-07-20T01:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"T4JRGUD4","created_at":"2026-07-20T01:19:02Z"}],"graph_snapshots":[{"event_id":"sha256:e33f3a883798e5a0c6393acf75fe95838bc21cd7307440bdef4a401f4e36f944","target":"graph","created_at":"2026-07-20T01:19:02Z","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/2607.15661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) can be adapted to specialized medical imaging tasks via parameter-efficient fine-tuning approaches such as low-rank adaptation (LoRA), leading to a growing ecosystem of expert models tailored to specific imaging modalities and clinical scenarios. However, deploying multiple expert LVLMs in practice incurs substantial computational and operational overhead. Model merging provides a promising solution by consolidating multiple experts into a single model without retraining, yet it remains largely unexplored in the medical domain. In this work, we present the ","authors_text":"Bingcong Yan, Chunlei Li, Jingliang Hu, Lei Li, Lichao Mou, Shengwu Xiong, Shilan Zhang, Xiao Xiang Zhu, Yaxiong Chen, Yilei Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15661","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":"sha256:0f62f158d33f98e81c143e259dceba8d6d74d21215fd1fefc399332f52943538","target":"record","created_at":"2026-07-20T01:19:02Z","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":"5b32dc21310e75da4b589ba9ea1f9984f25b82ca72225dddabf12715a9fb5b04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T06:13:13Z","title_canon_sha256":"56a75a1ba89f401a31d73f981f705a89987375f5d460eca4232581be188e5353"},"schema_version":"1.0","source":{"id":"2607.15661","kind":"arxiv","version":1}},"canonical_sha256":"9f1313507c8e5d26358b88c991d659e76add9719d42ded5d15aa9d85fca59309","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f1313507c8e5d26358b88c991d659e76add9719d42ded5d15aa9d85fca59309","first_computed_at":"2026-07-20T01:19:02.884719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T01:19:02.884719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mHZldLmUZL9yKM/uXDIuJBFOC+XIzeoSvt3LLaMtAOg7d1H2rPtTuLNC/qT1uK1eSIOccQa8bkZfN1sOwAZ+BQ==","signature_status":"signed_v1","signed_at":"2026-07-20T01:19:02.885600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f62f158d33f98e81c143e259dceba8d6d74d21215fd1fefc399332f52943538","sha256:e33f3a883798e5a0c6393acf75fe95838bc21cd7307440bdef4a401f4e36f944"],"state_sha256":"8c9e704b8c2634f390e503af9bb52ce2f5f3cec4e122afedfe1babbdc72d32cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNdVYtbJq0GRaTFX43oyH0QASO9oJAIGYg8OLsgBdwzqjzmOJ6nK9/ruBjsG1c7WP7lwMYeAcG62o10jIIsnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:13:36.056623Z","bundle_sha256":"ab5579172c7ff124a39d934a1f598d71227c54c34740c47b97eacb86fa68a394"}}