{"as_of":"2026-08-15T01:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:54907e4c2d47f03f3e0e9057375a9e70711e74964a2b9c8ac66341923c51e4ad","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:17:59.706415Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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/2506.02882/citation-record","integrity":"/paper/2506.02882/integrity","json":"/paper/2506.02882/citation-record.json","paper":"/paper/2506.02882"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.15385","last_updated":"2024-11-16T09:02:05Z","snapshot_observed_at":"2026-08-12T22:19:13.833502Z","submitted_at":"2024-10-20T13:00:24Z","title":"LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15385","snapshot_observed_at":"2026-08-07T11:17:55.017824Z","title":"Lora-ir: Taming low-rank experts for efficient all-in-one image restoration.arXiv preprint arXiv:2410.15385, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.017824Z"},"links":{"cited_paper":"/paper/2410.15385","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:ff0e02c0346f042d37805a947020d140e7101dd19c120416b021eb1bd2b6afbf","observation_id":"cf496bde-e413-4e9e-a870-8c5e559ed9f1","resolution":{"observed_at":"2026-08-07T11:17:55.017824Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:06.077503Z","title":"Revisiting neural scaling laws in language and vision","venue":null,"work_id":"1de15cbb-7263-4b21-a7a1-00d24d5f0c85","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.072043Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:87d0780db93fc72508f0999e2ff8a86e95357b0cd25c8f2807a2c52dc4697ee4","observation_id":"5b3bad26-2330-4614-8342-0ede8ba249e9","resolution":{"observed_at":"2026-08-07T11:18:06.211504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.982933Z","title":"Generalized foggy-scene semantic segmentation by frequency decoupling","venue":null,"work_id":"0df2f457-a2b0-4a70-b7dc-f2e28f80c0ab","year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.143070Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:beecb8d860bd68c5300802b2fc808d5266c87d186147af43e8018cd25f75ec6c","observation_id":"0e02b274-b4ad-401e-85c2-d2ad45842e01","resolution":{"observed_at":"2026-08-07T11:18:06.057141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.00254","last_updated":"2025-03-31T21:58:25Z","snapshot_observed_at":"2026-08-12T03:43:38.934749Z","submitted_at":"2025-03-31T21:58:25Z","title":"ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.00254","snapshot_observed_at":"2026-08-07T11:17:55.230944Z","title":"Elalora: Elastic & learnable low-rank adaptation for efficient model fine-tuning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.230944Z"},"links":{"cited_paper":"/paper/2504.00254","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:c62981346dc0c68c363fdee800a1d2085528d3e78a34d7fdfafc6d39963915e5","observation_id":"681ae574-c6ac-4887-9846-3a72e1cd364f","resolution":{"observed_at":"2026-08-07T11:17:55.230944Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.888845Z","title":"Instance segmentation in the dark.International Journal of Computer Vision, 2023","venue":null,"work_id":"bc9be461-8e9f-47fc-a5d4-87680d2a263d","year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.308228Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:2a998d6b23201ba5b7f28bf218120738523ad6575a3485e35d5fb201241e4135","observation_id":"7126410b-cac6-4b49-9528-c72566a7d91f","resolution":{"observed_at":"2026-08-07T11:18:05.939577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.746328Z","title":"Adaptformer: Adapting vision transformers for scalable visual recognition","venue":null,"work_id":"a99cd624-aab0-4ec5-bc11-a58d956b992d","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.392854Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:6b8a6ee44bb31330e717d35747a6d739a204cb06ef4919a5c9766bdb49cfb9df","observation_id":"b56c91c6-48e7-4645-857d-a0aebb7f169f","resolution":{"observed_at":"2026-08-07T11:18:05.802853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.622479Z","title":"Rvsl: Robust vehicle similarity learning in real hazy scenes based on semi-supervised learning","venue":null,"work_id":"18bb001d-d703-4573-ad9b-7ba0332c9500","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.473115Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:a8e9c9feca1742b9ba21d31506312aac4b86624ea3216ae9c02257e09a9eacc4","observation_id":"2ccb4bfd-6a0d-43b0-b7e7-12898b58b7ba","resolution":{"observed_at":"2026-08-07T11:18:05.680225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.526065Z","title":"RobustSAM: segment anything robustly on degraded images","venue":null,"work_id":"83a7048a-3801-486a-af38-48753ee3d906","year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.553034Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:0a9933335acd8b830b7c2c9a3b357ebd5a5285712eaae9123e39767b84ec6783","observation_id":"2eea0386-6b91-4302-81e3-aaff1ed21cd4","resolution":{"observed_at":"2026-08-07T11:18:05.553252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.372772Z","title":"Mitra, Xiaolei Huang, Philip H","venue":null,"work_id":"0aad687f-ed9f-41fc-9a2f-faa460ae7481","year":2015},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.618790Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:ca14aff66e172813e363d292120b192c9e649adb698875debb6ff5e975d8f1a7","observation_id":"3ce11227-8953-400d-bc8b-92bb451df181","resolution":{"observed_at":"2026-08-07T11:18:05.436389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14314","last_updated":"2023-05-23T17:50:33Z","snapshot_observed_at":"2026-08-13T23:56:42.354755Z","submitted_at":"2023-05-23T17:50:33Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14314","snapshot_observed_at":"2026-08-07T11:17:55.710103Z","title":"Qlora: Efficient finetuning of quantized llms.arXiv preprint arXiv:2305.14314, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.710103Z"},"links":{"cited_paper":"/paper/2305.14314","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:ed6125a1872b6403f86c4646b415126aa452012faee19bcc036ff1e0b0ca0105","observation_id":"2957dfde-6ead-442c-8d06-0d62c662f394","resolution":{"observed_at":"2026-08-07T11:17:55.710103Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.226210Z","title":"Dirty pixels: Towards end-to-end image processing and perception.ACM Transactions on Graphics (TOG), 2021","venue":null,"work_id":"6edf8abe-ef7f-45a8-b1b4-49514f520d6a","year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.775581Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:50e9b5ff8f29253c095ce6c2ce21183ecfa6ced424edf6b1303ff6be19389b10","observation_id":"78e9b36e-0e48-40fc-baf4-5de62c2dadab","resolution":{"observed_at":"2026-08-07T11:18:05.282439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:05.059511Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"94062c80-4f0e-436d-8b1e-fe1778238112","year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.869572Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:83139b17cd9d3843f986bfa3de6b05f85cb7b1fda497b26de7718556e024d8d9","observation_id":"f157d3e9-1ccf-4958-8f93-8f67d9fbda39","resolution":{"observed_at":"2026-08-07T11:18:05.138024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:17:55.922024Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23 (120):1–39, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.922024Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:49e7de6840aa43d696c43e94738a14ad2a66222130f50404b90bfa5d93c4b681","observation_id":"6686fbe0-a66f-4e0b-a779-d5e789e9ea7d","resolution":{"observed_at":"2026-08-07T11:17:55.922024Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:04.925766Z","title":"Lvis: A dataset for large vocabulary instance segmentation","venue":null,"work_id":"073cfe83-c029-40a7-9c78-2cd9bd0f35c3","year":2019},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:55.986486Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:c912e1fe689279dd0b44900bd3e111e09efc7ef9b4b20d7769374fd9645915eb","observation_id":"e1614474-21ed-4205-9d1d-0bc10cced9a2","resolution":{"observed_at":"2026-08-07T11:18:04.964439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04366","last_updated":"2022-02-02T16:39:23Z","snapshot_observed_at":"2026-08-13T17:56:57.877812Z","submitted_at":"2021-10-08T20:22:26Z","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04366","snapshot_observed_at":"2026-08-07T11:17:56.079751Z","title":"To- wards a unified view of parameter-efficient transfer learning.arXiv preprint arXiv:2110.04366, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.079751Z"},"links":{"cited_paper":"/paper/2110.04366","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:3c478a49ca742d4a963a816bdb892866b3ee7a88d06143f5835ccbe3836a91aa","observation_id":"40e3f879-a194-470e-a1e5-76fa5228ddfb","resolution":{"observed_at":"2026-08-07T11:17:56.079751Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:04.800713Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"1d5dd105-0b8a-40f7-ae22-1013a332330b","year":2016},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.138781Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:1bd0d6030be96cf5dd812df30b091b39cfab586f022fed07fb1694a8188e6a80","observation_id":"d65ff26a-8eda-461d-b947-3e278d19761a","resolution":{"observed_at":"2026-08-07T11:18:04.845472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:04.633828Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"cf5e8d23-5b45-4f8b-bc72-9e4c58895de7","year":2019},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.238560Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:f5fa727c6b4be7b182e3aecda3080ff402cd2aa7f569be73e072fcfec4b862a1","observation_id":"ed65dd05-4a87-4cd4-927e-1e2475376569","resolution":{"observed_at":"2026-08-07T11:18:04.694477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-07T11:17:56.322269Z","title":"Lora: Low-rank adaptation of large language models.arXiv preprint arXiv:2106.09685, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.322269Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:d18c39ac189fb7a3c19de95067990e86859cbf0f056fde68785963058d6184e4","observation_id":"2d4f002e-746f-4946-9a0c-81d8f82bed16","resolution":{"observed_at":"2026-08-07T11:17:56.322269Z","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":"2026-08-07T11:17:56.381922Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.381922Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:4cef05c9354af145cce0d9fecff19184992c6cb71455ef0d7567f56717727f0e","observation_id":"e3a1949d-cd96-4a4b-80ea-d37911f387b0","resolution":{"observed_at":"2026-08-07T11:17:56.381922Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:04.497112Z","title":"Tutel: Adaptive mixture-of-experts at scale","venue":null,"work_id":"c982b5aa-f4ed-4136-9dc6-f8e40feb6e7d","year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.451443Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:9b3daecb94f387cae1bfeef5bcc4f5022a741e1bba14cdfea43142fbe82576e7","observation_id":"d96dac15-463c-414a-94ac-10ce6eb2f64d","resolution":{"observed_at":"2026-08-07T11:18:04.538256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01144","last_updated":"2017-08-05T22:45:19Z","snapshot_observed_at":"2026-08-01T18:34:23.156273Z","submitted_at":"2016-11-03T19:48:08Z","title":"Categorical Reparameterization with Gumbel-Softmax","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01144","snapshot_observed_at":"2026-08-07T11:17:56.529530Z","title":"Categorical reparameterization with gumbel-softmax","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.529530Z"},"links":{"cited_paper":"/paper/1611.01144","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:6f1d338251fb7c4c8e6d31eeb1e7852e7f7cd6504b4e1a6f2e656306205f4500","observation_id":"523c5311-19bd-4a74-bc59-ab3a721a0b54","resolution":{"observed_at":"2026-08-07T11:17:56.529530Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:04.387883Z","title":"Visual prompt tuning","venue":null,"work_id":"0cba0bd1-f339-4c7f-b709-0a5ee668497b","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.618226Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:6c518a771c98b360d403fa14277afca2e5e73ec5d720e96c78c1134511d1b7cb","observation_id":"7c110f38-9512-416d-8889-cc88e3a01eb8","resolution":{"observed_at":"2026-08-07T11:18:04.432711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-07T11:17:56.702954Z","title":"Scaling laws for neural language models.arXiv preprint arXiv:2001.08361, 2020","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.702954Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:7f7d85fb5dfca6e40ecc2bf908120e9052640aae8b77e8609d0054b485bb5785","observation_id":"016a4201-8bf5-4d65-9ca6-95122506a135","resolution":{"observed_at":"2026-08-07T11:17:56.702954Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:04.248075Z","title":"Segment anything in high quality","venue":null,"work_id":"51739ed2-ded0-4379-ba88-94a1382ec83c","year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.770596Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:94d613aef07abdf9d761612d0729eae466710be277aba54e50e77abe5773ce57","observation_id":"99a37cdd-d9f2-4f42-8a1d-5c3adcf7df9d","resolution":{"observed_at":"2026-08-07T11:18:04.311760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:04.092526Z","title":"Efficient and versatile robust fine-tuning of zero-shot models","venue":null,"work_id":"dfb1e7bb-b8c8-4d39-949b-8e0e43dc6665","year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.881906Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:91840a916cb3fec4f64f74925733cd3ce68b6f1cd699d83d802f8f01e5cedbcc","observation_id":"8edd993d-312c-4a27-b259-8a0a7225828c","resolution":{"observed_at":"2026-08-07T11:18:04.155053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-07T11:17:56.950047Z","title":"Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:56.950047Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:dbefb01fe4e3a4ff9dc2d756c78c2a0b1a049df4792bbe2dbd50b63ff91fa878","observation_id":"a72f74e8-34a1-4d9d-a537-ea7755eb8e22","resolution":{"observed_at":"2026-08-07T11:17:56.950047Z","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":"2026-08-07T11:17:57.033496Z","title":"Segment anything","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.033496Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:55c77c37665f009d39ef4f4e5eb019695c557a751c252b11ed1316c767ec9ad7","observation_id":"0cda47fc-37ed-4575-b913-e68ebd2ab08d","resolution":{"observed_at":"2026-08-07T11:17:57.033496Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:03.883731Z","title":"Big transfer (bit): General visual representation learning","venue":null,"work_id":"34a01634-ab21-4019-b0f8-92afc5073101","year":2020},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.086757Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:583359bcf8f37cea014d9186ce157bb07a9f5ab3a96e4ab60767606b70a23d0a","observation_id":"db7789a5-5738-4aa8-9ab7-9a8111a85676","resolution":{"observed_at":"2026-08-07T11:18:03.970783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:03.728401Z","title":"Fifo: Learning fog-invariant features for foggy scene segmentation","venue":null,"work_id":"ff7e9175-b711-4a02-bded-2a7d2614fb4a","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.154007Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:5b34a8a66cf5817b0b57a3475d7f30ca31d42e5a5e73f658a3c6f04dffad9990","observation_id":"6afb74f5-e746-4552-a63c-b5924d1e1b91","resolution":{"observed_at":"2026-08-07T11:18:03.803273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:03.551173Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"a42a0af1-79a0-4c3a-95ad-a428359a22d9","year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.252317Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:66cba01aa50d1aac2384aa9584859cb0a8271d463546b32e96a9cf9f704e320c","observation_id":"a58ebbb1-4221-471c-80de-c9d6fd2aa25d","resolution":{"observed_at":"2026-08-07T11:18:03.622395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:03.394563Z","title":"All-In-One Image Restoration for Unknown Corruption","venue":null,"work_id":"2c566a84-6ad5-4786-9355-f3cde4c46249","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.317551Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:13ddce82dbac5beafd33fe4b3a35c587b44e8b0582f26285b0a541972333ff06","observation_id":"4fde4c19-773b-4b63-8173-11c5b4e79383","resolution":{"observed_at":"2026-08-07T11:18:03.470391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:03.106862Z","title":"Single image deraining: A comprehensive benchmark analysis","venue":null,"work_id":"f2acad31-366c-4f99-a06d-0f2b8b1a9627","year":2019},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.407659Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:2205e7fa8f9bd08eae79fdb88d5f5b3d62b98c51bf2b5a9137493b6295c2a370","observation_id":"13af6f22-22be-432d-940e-edc8a6c1cfdd","resolution":{"observed_at":"2026-08-07T11:18:03.179464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-12T12:37:28.207761Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-07T11:17:57.472037Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.472037Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:a99d3b98927eb10c8539b03aafdc731a04f80928c53f7783ababfc0122600bc7","observation_id":"b792fb63-56a3-4154-bf87-ab6be06faee9","resolution":{"observed_at":"2026-08-07T11:17:57.472037Z","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":"2026-08-07T11:17:57.581042Z","title":"Scaling & shifting your features: A new baseline for efficient model tuning.Advances in Neural Information Processing Systems, 35:109–123, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.581042Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:cb6b73874edab5d40be9d1d5210da583a150bc837623384637990899032be6ba","observation_id":"2ab061e0-77e3-4791-b696-49ffe8c5753f","resolution":{"observed_at":"2026-08-07T11:17:57.581042Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:02.902134Z","title":"Deep interactive thin object selection","venue":null,"work_id":"2142bea5-8958-4f5a-b496-a77cbb35bc96","year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.665825Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:f677a99b30da552aca9b1073a2062c74883c4c0a2e94ddca473a90e1b103d89f","observation_id":"cc58c537-d7a3-4ba4-8528-960734db9b06","resolution":{"observed_at":"2026-08-07T11:18:02.981778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15947","last_updated":"2024-12-23T08:05:14Z","snapshot_observed_at":"2026-08-06T02:31:58.372974Z","submitted_at":"2024-01-29T08:13:40Z","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15947","snapshot_observed_at":"2026-08-07T11:17:57.760977Z","title":"Moe-llava: Mixture of experts for large vision-language models.arXiv preprint arXiv:2401.15947, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.760977Z"},"links":{"cited_paper":"/paper/2401.15947","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:39977f5fcc0c92e1e2711144b38b08257bcf2737f12bcb4a5c0d523e1250c77e","observation_id":"b05e130c-fd0e-4202-b315-046e576ec5ba","resolution":{"observed_at":"2026-08-07T11:17:57.760977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10280","last_updated":"2024-08-27T15:34:49Z","snapshot_observed_at":"2026-08-12T23:01:57.620895Z","submitted_at":"2024-08-18T12:18:56Z","title":"NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10280","snapshot_observed_at":"2026-08-07T11:17:57.848691Z","title":"Nora: Nested low-rank adaptation for efficient fine-tuning large models.arXiv preprint arXiv:2408.10280, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.848691Z"},"links":{"cited_paper":"/paper/2408.10280","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:78d1059eacb10bfb107950b5b2a8a3a004f3bb534362d0b2934f4e86f5ef1af3","observation_id":"624d1b06-176e-4794-ab99-6a0eb15adf61","resolution":{"observed_at":"2026-08-07T11:17:57.848691Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:02.752695Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"cc1a9eb6-e2d0-4450-b48a-a3562d59e66b","year":2014},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.922012Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:f990f5d55d6dc37d0fa2755b814a588997284a914a2f6b5f6509033cfc38851a","observation_id":"50372993-270f-4e75-9a0e-664c7078f22f","resolution":{"observed_at":"2026-08-07T11:18:02.825049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04344","last_updated":"2024-03-27T12:44:55Z","snapshot_observed_at":"2026-08-13T11:22:43.317897Z","submitted_at":"2023-06-07T11:18:53Z","title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04344","snapshot_observed_at":"2026-08-07T11:17:57.978767Z","title":"Vida: Homeostatic visual domain adapter for continual test time adaptation.arXiv preprint arXiv:2306.04344, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:57.978767Z"},"links":{"cited_paper":"/paper/2306.04344","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:77551db9b98c9862427c7c0ef991a858c2cefcf1094f38a745f8fa9589465fa0","observation_id":"6265c30e-27f3-4374-adb6-1398719283f3","resolution":{"observed_at":"2026-08-07T11:17:57.978767Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:02.575793Z","title":"Gustafsson, Zheng Zhao, Jens Sjölund, and Thomas B","venue":null,"work_id":"55f38032-63b3-4674-91c0-9a86c1a62516","year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.065111Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:1083625f1a4d416a8ff4c85eb2aaecc9855d2e01f3bc6ee945b43446b957a83f","observation_id":"c67038e3-4ca0-4152-80e4-5f4d96739072","resolution":{"observed_at":"2026-08-07T11:18:02.657902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:02.403199Z","title":"Both style and fog matter: Cumulative domain adaptation for semantic foggy scene understanding","venue":null,"work_id":"f3f469d7-c201-40ea-a10c-64bbc922feb8","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.136813Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:aeede506cd42448293db62cfe6885056a871d594a641ffb9dbede1630869539b","observation_id":"54e28fee-0aa4-4e9d-9d6b-59cdc5cf74f2","resolution":{"observed_at":"2026-08-07T11:18:02.485943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00247","last_updated":"2021-01-26T12:54:33Z","snapshot_observed_at":"2026-08-11T03:47:32.551562Z","submitted_at":"2020-05-01T07:03:42Z","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00247","snapshot_observed_at":"2026-08-07T11:17:58.200905Z","title":"Adapterfusion: Non-destructive task composition for transfer learning.arXiv preprint arXiv:2005.00247, 2020","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.200905Z"},"links":{"cited_paper":"/paper/2005.00247","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:efc10271a9f09cdb1547a70b9667bc9f15bd347614d1fdc4fd1581a1d6f78014","observation_id":"1d3e11b6-d18b-494d-b2c8-e48b34f1b651","resolution":{"observed_at":"2026-08-07T11:17:58.200905Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:02.244581Z","title":"PromptIR: Prompting for all-in-one image restoration","venue":null,"work_id":"bcbc5697-b344-4bd4-be48-5efc62d7ac60","year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.274130Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:cf8b47488f67a757fa2fefc59041f8ffee8352caefdb5e8db7acd3698563661a","observation_id":"71bf7ab9-4759-4ed4-9849-6da89814a3ec","resolution":{"observed_at":"2026-08-07T11:18:02.327347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:02.095537Z","title":"ACDC: The adverse conditions dataset with correspondences for semantic driving scene understanding","venue":null,"work_id":"0e3a8ae7-6ddd-461c-bca5-df3c52e2d8fa","year":2021},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.358982Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:c00f7e00626a143e0cc1e075d805b9b1fc307b210ac7479fe28d630954dfc2dc","observation_id":"77ac5fbf-70ec-4374-9bd8-4d50002d1fc3","resolution":{"observed_at":"2026-08-07T11:18:02.156439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:01.924936Z","title":"Robustness analysis on foundational segmentation models","venue":null,"work_id":"8b4321ec-a9ad-4a82-8534-43360440a271","year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.442002Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:88e19e91ce189b96de0433fa782ce5013b71f512969fa205e136a9075ba908c6","observation_id":"60c4bf5e-8022-4d50-9373-311b8950dba6","resolution":{"observed_at":"2026-08-07T11:18:02.014452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:01.744067Z","title":"Outrageously large neural networks: The sparsely-gated mixture- of-experts layer","venue":null,"work_id":"7e8558df-c75b-40e1-a307-2a79ac64d848","year":2017},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.536372Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:cc72edfb60b626bc7333177b739aba91a8734d776f024b7554f65b1e9781910b","observation_id":"ecd782f8-8cc6-4f68-a81f-b2dab42a458d","resolution":{"observed_at":"2026-08-07T11:18:01.809983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:01.587344Z","title":"Multitask vision-language prompt tuning","venue":null,"work_id":"0f16a36e-5505-4242-b708-50e012cdadd6","year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.629480Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:5ceb1bbe3c1f3b04bd020394b4649c027b5d6fbf6bd87e599a982046455b7348","observation_id":"47280692-36af-4999-8725-82fe3b5bf8fc","resolution":{"observed_at":"2026-08-07T11:18:01.649431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:01.433158Z","title":"Streets: A novel camera network dataset for traffic flow.Advances in Neural Information Processing Systems, 2019","venue":null,"work_id":"d1b0b015-1c23-4c3b-8741-356b07a82c91","year":2019},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.709449Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:4cc7da02fe1da2319f33d0ab0dc4fae5590390967f09c685f1f8b04fc29a0cc3","observation_id":"f93ab9e8-2c4e-440f-ab4c-f796687c400e","resolution":{"observed_at":"2026-08-07T11:18:01.496685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:01.283218Z","title":"Urie: Universal image enhancement for visual recognition in the wild","venue":null,"work_id":"a09544f0-a030-4c43-ba96-9fed2ce2b6e9","year":2020},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.790629Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:52669a59fb5d0ab8914338daa7af1e5d5c3dd398426e6b45c63c95133306e618","observation_id":"b497544b-0f5e-4be4-9a3e-3266b519190e","resolution":{"observed_at":"2026-08-07T11:18:01.351304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:01.134719Z","title":"EfficientNet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":"fe1711dc-d260-46d5-a4b4-42fb2e0b49e5","year":2019},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.895652Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:d8f6910c91456ac9ce7b0fb913613483c90e059f1d44c1da76aa77454a736584","observation_id":"f8b64305-7fb7-45ec-ba26-3128534cc1ac","resolution":{"observed_at":"2026-08-07T11:18:01.202334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.13359","last_updated":"2020-05-27T13:41:39Z","snapshot_observed_at":"2026-08-13T22:35:56.132004Z","submitted_at":"2020-05-27T13:41:39Z","title":"NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.13359","snapshot_observed_at":"2026-08-07T11:17:58.958623Z","title":"Ndd20: A large-scale few-shot dol- phin dataset for coarse and fine-grained categorisation.arXiv preprint arXiv:2005.13359,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:58.958623Z"},"links":{"cited_paper":"/paper/2005.13359","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:59dd668ebcfc6ea6abf2f1a7a57abbd9560a2e1b11bf18f835b80c391dcfb0e2","observation_id":"a99311e0-9f55-42c7-a896-00d0bc7279be","resolution":{"observed_at":"2026-08-07T11:17:58.958623Z","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":"2026-08-07T11:17:59.120874Z","title":"DyLoRA: Parameter- efficient tuning of pre-trained models using dynamic search-free low-rank adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.120874Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:e36692cf42ef44760e4250ec41b9f62ac4804db2de5e8594318f725509843c2a","observation_id":"1dad2fb7-3742-46c4-98e2-f10c0388e679","resolution":{"observed_at":"2026-08-07T11:17:59.120874Z","resolver_source":null,"status":"malformed_identifier"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:00.780962Z","title":"Ugˆ 2: A video benchmark for assessing the impact of image restoration and enhancement on automatic visual recognition","venue":null,"work_id":"3d4b3bf3-ab4c-4678-aa1e-5b3c91a6d024","year":2018},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.188313Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:375d468eb3c05db89ff97fc5a77f90f2ec92ba1b2b8be9ec88ff7bd732d57769","observation_id":"23400480-b8ac-4580-9eca-dd531ba6b8e0","resolution":{"observed_at":"2026-08-07T11:18:00.855182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:17:59.249838Z","title":"AdaMix: Mixture-of-adaptations for parameter-efficient model tuning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.249838Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:01b7e26e4cc2e4d45a87339568587df67fe97bdbf9fd02ea5fe303c61102c94e","observation_id":"d18c4cfa-7977-4ed9-a654-bd8575a6e826","resolution":{"observed_at":"2026-08-07T11:17:59.249838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04151","last_updated":"2024-01-08T14:26:49Z","snapshot_observed_at":"2026-08-13T19:20:39.212857Z","submitted_at":"2024-01-08T14:26:49Z","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04151","snapshot_observed_at":"2026-08-07T11:17:59.334061Z","title":"Chain of lora: Efficient fine-tuning of language models via residual learning.arXiv preprint arXiv:2401.04151, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.334061Z"},"links":{"cited_paper":"/paper/2401.04151","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:76eb74d31d5ea44fbe78002752670bd239b568923b38b7a779097acaebe9f530","observation_id":"5b6b1f12-c26b-44b4-ad24-37fe461fe5ab","resolution":{"observed_at":"2026-08-07T11:17:59.334061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08345","last_updated":"2024-08-27T05:08:00Z","snapshot_observed_at":"2026-08-13T15:51:53.194755Z","submitted_at":"2024-08-15T17:58:10Z","title":"5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08345","snapshot_observed_at":"2026-08-07T11:17:59.404572Z","title":"5%>100%: Breaking performance shackles of full fine-tuning on visual recognition tasks, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.404572Z"},"links":{"cited_paper":"/paper/2408.08345","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:6a718a5a68f092aab93d862c241c6329837c2fea62b79e44a6bf810fe747ef58","observation_id":"f853e7d2-ded4-45b9-bc21-be75e1a55a5f","resolution":{"observed_at":"2026-08-07T11:17:59.404572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.04687","last_updated":"2020-04-08T09:25:06Z","snapshot_observed_at":"2026-08-14T19:16:08.121001Z","submitted_at":"2018-05-12T09:24:21Z","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.04687","snapshot_observed_at":"2026-08-07T11:17:59.471177Z","title":"Bdd100k: A diverse driving video database with scalable annotation tooling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.471177Z"},"links":{"cited_paper":"/paper/1805.04687","citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:4851de5c389ebcc273162d68ad25a8cb69d0e71e5590d1df127a4b7d4d735643","observation_id":"7e83bbbf-eb31-4730-b34a-315f8da8bed7","resolution":{"observed_at":"2026-08-07T11:17:59.471177Z","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":"2026-08-07T11:17:59.535727Z","title":"Scaling vision transform- ers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.535727Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:52581997ca3c340d36b9feda02d4968aaf72b15520a9bb55cdff578bda24716f","observation_id":"6d186925-7e21-4ffa-b9bd-cce896bfbf15","resolution":{"observed_at":"2026-08-07T11:17:59.535727Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:00.543545Z","title":"Adaptive budget allocation for parameter-efficient fine-tuning","venue":null,"work_id":"304cefae-5a33-4007-8f06-9dbf3ae758f5","year":2023},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.599264Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:678b207aa411bf188582cac7cef262377f0a0695c7369a1eaf28324f7476e21b","observation_id":"5a383ceb-e20e-4bd9-9940-5559c0c353b0","resolution":{"observed_at":"2026-08-07T11:18:00.660934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:00.364357Z","title":"Mixture-of-experts with expert choice routing.Advances in Neural Information Processing Systems, 35:7103–7114, 2022","venue":null,"work_id":"a51c1b0d-f350-4b4e-9789-fbe1faa6c032","year":2022},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.706415Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:b244525897349316b962c2948bb83dcd8179a00f5c47562e5b56ba4438913ab7","observation_id":"52848613-87d2-47fa-8f1f-8d39b3fad717","resolution":{"observed_at":"2026-08-07T11:18:00.460518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:18:00.938006Z","title":null,"venue":null,"work_id":"ba93e7f1-34fb-49b1-9654-dcfd85987ab5","year":null},"citing_paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T11:17:59.050615Z"},"links":{"citing_paper":"/paper/2506.02882"},"observation_digest":"sha256:22c471de69d3879839195bdf3968e46189f5744189b3f661a19249b3679f69c1","observation_id":"0b31834b-b701-4aee-87d9-9ca153a29f17","resolution":{"observed_at":"2026-08-07T11:18:00.994526Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.02882","last_updated":"2025-06-05T09:05:13Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T13:49:40.090437Z","submitted_at":"2025-06-03T13:47:59Z","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":36},"total_outbound_references":61},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2506.02882."}