{"as_of":"2026-08-10T20:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0011daa6ceba3289e265200d6800c7b05b8a391e608d8846b99a1a005615f355","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T22:43:41.519591Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.15661/citation-record","integrity":"/paper/2607.15661/integrity","json":"/paper/2607.15661/citation-record.json","paper":"/paper/2607.15661"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-07-06T22:37:03.716474Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-01T22:43:39.096789Z","title":"arXiv preprint arXiv:2511.21631 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.096789Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:418b82490d6ed58ad672f7474603e9b6fe264dc163974335780faa4930a51679","observation_id":"822b6bcc-4e69-4875-87f8-091d713872c2","resolution":{"observed_at":"2026-08-01T22:43:39.096789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.187583Z","title":"In: IEEE/CVF Conference on Computer Vision and Pattern Recognition","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.187583Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:1879f2aba5aba4f158358a548e563793ecdd2aa8f3ea7d2e02338bbcbf528acd","observation_id":"3a2123b8-e0cb-4268-8954-89cc3954f00e","resolution":{"observed_at":"2026-08-01T22:43:39.187583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14238","last_updated":"2024-01-15T15:23:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-21T18:59:31Z","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.14238","snapshot_observed_at":"2026-08-01T22:43:39.245432Z","title":"arXiv preprint arXiv:2312.14238 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.245432Z"},"links":{"cited_paper":"/paper/2312.14238","citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:d0ea8ce3f72b259b6c2c7568e60c82cc5140ac6728beabfaba92d1ca03096a62","observation_id":"81064873-2035-46be-ad2f-961f2cabd500","resolution":{"observed_at":"2026-08-01T22:43:39.245432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.326302Z","title":"In: Advances in Neural Information Processing Systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.326302Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:26e4eaf93cd558862155f9cd6e044f0d384f0c2cfc79036919298c29abbe38d8","observation_id":"1c45992a-ec95-4469-a985-8d88e24fa962","resolution":{"observed_at":"2026-08-01T22:43:39.326302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.400741Z","title":"In: International Conference on Learning Representations, (2022) 10 L","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.400741Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:6705dc7670a8929a9cb5188ca4019491184ac94f92603378d6ca8518e5e035f9","observation_id":"d2def33c-0056-4f19-81fc-191969e2d257","resolution":{"observed_at":"2026-08-01T22:43:39.400741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.472819Z","title":"In: IEEE/CVF Conference on Computer Vision and Pattern Recognition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.472819Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:03a414c6bfdd3acf9a382d65c5499199f04cdeaa5fbd60331f93c6acb45d7880","observation_id":"fed5859c-c6d4-4a89-96ba-15ab5208bbf2","resolution":{"observed_at":"2026-08-01T22:43:39.472819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-01T22:43:39.527353Z","title":"arXiv preprint arXiv:2307.13269 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.527353Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:1d6b0a53d8fae07210426d5eb4a4a8934ac0f9176ece79947f478bb64319bd8b","observation_id":"4f3994e5-5d43-42dd-9295-dc031b4b8888","resolution":{"observed_at":"2026-08-01T22:43:39.527353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.613445Z","title":"In: International Conference on Learning Representations, (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.613445Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:3476b05c996ea56dae9325cb5351aede7a2831b3bc57996ec7dea4724c9f777b","observation_id":"dc91b3dd-6503-4ce3-8066-856e17a476bf","resolution":{"observed_at":"2026-08-01T22:43:39.613445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.753176Z","title":"In: International Conference on Learning Representations, (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.753176Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:180848499cd84bed00082cf459ca0f4a5d3a134a7b77e49eaad105233fe80f12","observation_id":"703c6d8d-51c7-4c0b-8205-aed75e8306ea","resolution":{"observed_at":"2026-08-01T22:43:39.753176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.877123Z","title":"IEEE Transactions on Medical Imaging pp","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.877123Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:96605dd0f4ae2eae1ced42ef472d4ef13eeea260f2b4dc265e02f05fca4ffd40","observation_id":"f0c86657-e5d2-41a4-b00a-b35702b8c344","resolution":{"observed_at":"2026-08-01T22:43:39.877123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:39.924877Z","title":"In: International Conference on Machine Learning, (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.924877Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:ac621aaacf271b515bc8795fd23c6fb3076d251d6523d735acf5670420f011e5","observation_id":"c11a9952-0ff9-41f0-8bfb-32c06a03cb9c","resolution":{"observed_at":"2026-08-01T22:43:39.924877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.055401Z","title":"In: Ad- vances in Neural Information Processing Systems","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.055401Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:9edfd58ba8fe9f281d3b7a89891b71b8e71abe89638b88c8ea088c3719b567e4","observation_id":"632bbd4c-5b87-4180-b64f-3e16a47a74e0","resolution":{"observed_at":"2026-08-01T22:43:40.055401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.205828Z","title":"In: Medical Image Computing and Computer Assisted Intervention","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.205828Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:6fa6c3be9792e8570f8ed6a5ce687bd6fc005a9566bc191beda2c296364fc83e","observation_id":"7731aeef-44cc-42de-a2c4-45c85fafe993","resolution":{"observed_at":"2026-08-01T22:43:40.205828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.301623Z","title":"arXiv preprint arXiv:2509.17786 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.301623Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:6f456a7f5775da5be8a30c483a36f168f15399e5d6ed5df73b4bbcf254a39fad","observation_id":"a2443f6c-735b-4e7a-86be-20453bc4578e","resolution":{"observed_at":"2026-08-01T22:43:40.301623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.390724Z","title":"In: International Con- ference on Computational Linguistics","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.390724Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:46a9d4a099aba8da41380dc6777620da2a283b03d237c3246fd44eb234ae1f25","observation_id":"ac36cf75-b480-4010-a420-8c5e5140a578","resolution":{"observed_at":"2026-08-01T22:43:40.390724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.481255Z","title":"In: Empirical Methods in Natural Language Processing","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.481255Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:d035a15ef8daccaec89c38584493936b47deb76c20f727e5d0cdb7e4cd83cf61","observation_id":"40eebf2e-df8e-4f08-bc2e-fec3c8702a85","resolution":{"observed_at":"2026-08-01T22:43:40.481255Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.571673Z","title":"In: European Conference on Computer Vision","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.571673Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:eb03fea78f21fc2deb1bad92663bec5f6af764549efd8e2f46568937990603fd","observation_id":"98ab303c-a980-4a27-a191-abdaf7dd640b","resolution":{"observed_at":"2026-08-01T22:43:40.571673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.708527Z","title":"In: IEEE/CVF Conference on Computer Vision and Pattern Recognition","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.708527Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:a67898f191ecf163789689b99921bd54bf05a029cf516313af7ba725cd4df90a","observation_id":"1f232e13-dc20-4689-bdfb-8cc5e862a8c2","resolution":{"observed_at":"2026-08-01T22:43:40.708527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:40.854518Z","title":"In: International Conference on Learning Representations, (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:40.854518Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:6e7ec07bdc9b818d169868d4568a0658b16f4c6616d565cbc5611d453f284f32","observation_id":"46cd41fc-a67c-4f09-97af-36df12b90d75","resolution":{"observed_at":"2026-08-01T22:43:40.854518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:41.007253Z","title":"In: Advances in Neural Information Processing Systems","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:41.007253Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:1c876ff68b9caf38a0ba574769f26c0e545da5f559028d490e75ae10423a6328","observation_id":"7acd23be-31d3-46e0-810f-dc30d12fc435","resolution":{"observed_at":"2026-08-01T22:43:41.007253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:41.092031Z","title":"In: International Conference on Learning Representations, (2024) Model Merging for Medical LVLMs 11","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:41.092031Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:8e4ee1a23aecaa85cfb122056a99e9e0952cc38ae8afb9d18d5db240f7d79001","observation_id":"a42a5a33-178c-4c92-a307-9e5c39416c47","resolution":{"observed_at":"2026-08-01T22:43:41.092031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:41.170096Z","title":"In: International Conference on Machine Learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:41.170096Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:77a242c1dc26e9ddf5d96180acd787655afe5bb69f39a8b87efc0ed57ee54357","observation_id":"c69ae40c-5b70-4682-8dfa-4a5ab3bdbba1","resolution":{"observed_at":"2026-08-01T22:43:41.170096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:41.264621Z","title":"arXiv preprint arXiv:2502.17159 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:41.264621Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:04da9e0a9c0f3cb265d62166a41158464519e5d142b9191ee69d08a6fea6d9e6","observation_id":"8b42fb58-caa1-4080-ba03-72e475d003cc","resolution":{"observed_at":"2026-08-01T22:43:41.264621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:41.340608Z","title":"arXiv preprint arXiv:2509.25712 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:41.340608Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:dc909327e2dbfbd472fe6b6e288212db7c6b0b60d748042ff83df36a19d0ed2c","observation_id":"bf01c524-4f26-42f9-91e9-6d1d4814f589","resolution":{"observed_at":"2026-08-01T22:43:41.340608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:41.425181Z","title":"In: Advances in Neural Information Processing Systems","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:41.425181Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:117ebc64b337a14b216e9f055ee6023dc265cddffa716a0ce9c9a492d4e3c0cd","observation_id":"d111d893-08d0-4ff1-a35d-64b2edb09f0e","resolution":{"observed_at":"2026-08-01T22:43:41.425181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T22:43:41.519591Z","title":"In: International Conference on Learning Representations, (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:41.519591Z"},"links":{"citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:f79d10e8ba003dac7a52d342e7ea1d65ed30763f9693f3e42bdd59b53eb48bfb","observation_id":"b2f6dcce-a983-4c70-b085-305d3a4c2282","resolution":{"observed_at":"2026-08-01T22:43:41.519591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T10:19:33.721466Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":26},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2607.15661."}