{"as_of":"2026-08-22T07:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2c8074d785becabde3312054baf27f114fcb48a7c0f78615013150eb01bf59fa","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T23:48:25.354479Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2607.03810/citation-record","integrity":"/paper/2607.03810/integrity","json":"/paper/2607.03810/citation-record.json","paper":"/paper/2607.03810"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T23:48:25.354479Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:a0a2fb92204590f8ac7335a85386b565a43cca917a75c562e74bc57f32bf2ae1","observation_id":"38d005b6-645f-4a3d-9425-568fd492b652","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05587","last_updated":"2017-12-05T18:06:21Z","snapshot_observed_at":"2026-08-16T09:04:18.586776Z","submitted_at":"2017-06-17T22:48:57Z","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05587","snapshot_observed_at":"2026-07-11T23:48:25.354479Z","title":"Rethinking atrous convolution for seman- tic image segmentation.arXiv preprint arXiv:1706.05587,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"cited_paper":"/paper/1706.05587","citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:6e3516251d2606dd407c249cb255bb614a2ee6bd447326fc360b45aa495c41f1","observation_id":"22727551-23e3-4be0-9fdf-b07d5982e364","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Do- main adaptation for semantic segmentation with maximum squares loss","venue":null,"work_id":null,"year":2090},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:a59a6b03e83af2c3773f1ad8b3b192391f453370ea6332392cacd8959284490a","observation_id":"78ee19eb-1894-4efa-bbe8-09c063ed2e24","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:f9fdf4b0816effe422ced7d5dd6769298fb8a1ee0f5efa7352cea0427a6e18f1","observation_id":"53a5cdc6-eef8-4ec7-8ae5-4bbb5aa5f2a9","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"The mnist database of handwritten digit images for machine learning research.IEEE Signal Processing Maga- zine, 29(6):141–142, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:d01c0a8d5e931042566950672d9ceaad7b3bfd64ef36366abea88c2b91a9e359","observation_id":"37d7217c-d3cc-47ef-b6ea-3288e0ff6559","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Robust mean teacher for continual and gradual test-time adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:8c6b5333d35cfa245c850550d735c66af4a7a1210156ce7fdf0532970acf2caf","observation_id":"68e4336b-a30c-4db1-8ae6-27f7a2220931","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Uncertainty reduction for model adaptation in semantic segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:897fbe16e909e4a2589b6d8c1783025a4804bb1e76d83b72357bd7c6ab796cda","observation_id":"e3832f88-3579-42ee-8fba-2bd532249f93","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Back to the source: Diffusion- driven adaptation to test-time corruption","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:9862d3508bd3173ac628bfb57ed302f5fe6e301910bb1f1e4e3dfc26d880b394","observation_id":"3eb8b620-8f45-4ae8-af62-ad177be1c940","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Sim- ple copy-paste is a strong data augmentation method for in- stance segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:4a4ae02572b31eac7dfd72e3b0b5d64c97807aa93a716cf22364107082865355","observation_id":"cd64365a-07b4-4ce6-ac6a-87ced91a29c6","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:779151b51ddc7f47dfcd66424c683b53747cdcbe86b2a62a5d3527b9fd108ad3","observation_id":"d48ebf17-5c5b-436c-a6af-cec46df5b389","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Model adaptation: Historical contrastive learning for unsu- pervised domain adaptation without source data.Advances in neural information processing systems, 34:3635–3649,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:829e3b8cac3ab75b66e30268ea13f0b5fd358da6f834ab319df1e34b62833681","observation_id":"cb308698-95b9-4ddc-8844-71c615d4c0ff","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Multispectral pedestrian detection: Benchmark dataset and baseline","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:2ba5d9ca7e2f501b1cd460c7506cdd2e8de2bace4ab641f156c806a8f9ab8796","observation_id":"8d565c69-50e0-4e16-b952-2364e4ea75b8","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Video analytics dataset.https://www.ino.ca/ en/technologies/video- analyticsdataset/,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:b4a9a1cee0f030f92a98c128ea31628f0031b155aedbaf1bee948234e09d75a0","observation_id":"03af7086-971b-4277-be08-0e957592ce85","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:ede02c36f43662de5fae4a09cbcc838fab704d3b3fa41b35e99aaceadc5a5a3d","observation_id":"30b9f9b1-7c37-4ec3-8d49-db987b2ed2cf","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Deflating dataset bias us- ing synthetic data augmentation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:598d448240c404fb65c2bc5832f1ac7c6c86ae45fa2a0507a24dd848ba35794e","observation_id":"7aff02a8-aa00-4441-8593-217d638a4e17","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Yuille, and Li Cheng","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:99090486a58bfbaa9e724715aefc1305d171be4c9f8183867ef49cb0c0d14308","observation_id":"0a81f2df-35d5-4960-bfbc-4093da7d971f","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"YOLO by ultralytics, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:2b47ec8042730080cb36295164831b574afcac3b16badb394c2b016a07339d82","observation_id":"03d5d833-33f2-4cf9-9c0e-c1eb2097625e","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Ev-tta: Test-time adaptation for event-based object recognition","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:5636d78f34b4eaf5483164d8a4e1c877d7fe717dde13f720612877e03b8af636","observation_id":"abbe1be6-a619-47af-a97a-4043200eddaf","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Segment any- thing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:9bce8b4669b3ccb1f8109a648daf2d04b05183af59a1b46af6615b968d8f5649","observation_id":"18053736-eb52-444d-bdcb-2fe1a7975af6","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"A review of domain adap- tation without target labels.IEEE transactions on pattern analysis and machine intelligence, 43(3):766–785, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:a7fe0fba037463bfb9aab8ba6b96d94ca61c0ad138cb92cf42b0472c259d5c12","observation_id":"36f7e7d0-eda3-4dac-8153-fba3a766705b","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Rgb-t object tracking: Benchmark and baseline.Pat- tern Recognition, 96:106977, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:6988132b46ca4d4c8dc0020fa81607e61576ac1e6082ab1cf2954da8b7e3f406","observation_id":"351beb46-a816-4a8e-b469-454bf2ee6d24","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"A comprehensive survey on source-free domain adap- tation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:f7771dba5fc0d29a444ba75ca8c8dab909fef732a31e00d2a7c7409685d39470","observation_id":"83336615-a19f-48c6-a43f-c10af37bd4a9","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Multi- interactive feature learning and a full-time multi-modality benchmark for image fusion and segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:821cc433d876f7b274347e1de1b7f745ffd766e3dc534760fa463c6c879733cd","observation_id":"4229fcf1-946a-4395-bbe7-bb8263b1a7f7","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Source-free domain adaptation for semantic segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:0214102833f217e2fd95651dacf7dcd49ea88721398252a8a7155c7d1271ae06","observation_id":"a1de6794-6953-4120-afdc-668bbfaf4718","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Improved self-training for test-time adaptation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:9afaa493c7eaeafa3d336bd37609ec0a5c46f0eb07c0cf5f3894eee3dfc927c1","observation_id":"15e16146-0e1c-4a46-845a-3987fa3e928e","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:2eed307392f5fd109bbe8947e81cf1c1a64ba3da3448cc5897a656065efe7e89","observation_id":"6c30446a-29ab-4540-ae4b-cb5a7f6f8d57","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Efficient test-time model adaptation without forgetting","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:11d145899b05fb51a2dc2adf2debb11d182f1789a9352ca41dce6aba5368607c","observation_id":"705f7624-41a9-45ec-ad9f-c6ccd9cc81fe","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:3a18d6642b6fbeb3b76a43299e5085a82ca497626deebbb65d94c69da50d70d8","observation_id":"4f3e85fc-71d1-4299-a778-344b59fa1f05","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Playing for data: Ground truth from computer games","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:3ad4430485299d6c408094c51204a64afaa305d8d664913cf5872ea377115498","observation_id":"8885fecf-1051-45de-b497-f767456de7fe","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Generalization in neural networks: A broad survey.Neurocomputing, 611:128701, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:1a76ae1f12b73d1c876a8dc3aa2bf9c4262914f81dfca865bac10050cecd3d6d","observation_id":"59abdb15-c85b-41c7-98a5-db9286496362","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Acdc: The adverse conditions dataset with correspondences for se- mantic driving scene understanding","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:9002739a414ed8f5ec58ad3323169c4e61ab2036214a62ff351c38493d87ebac","observation_id":"f5d1850f-3218-47ad-b560-e6ac2bec8791","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Ecotta: Memory-efficient continual test-time adaptation via self-distilled regularization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:cde086702af89127e34856ab12e0f107957f86c48089b9c39198ddea3a7d0c8d","observation_id":"60371439-4d9b-4659-91ba-983c51f19e4d","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Source- free domain adaptation with frozen multimodal foundation model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:0b19d7d522a700efc36afcf145606058033fdace213becd6df6cae3cdae1bab1","observation_id":"6601e9a1-314f-4f8e-9e2f-6e27f184aac1","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Vdm-da: Virtual domain modeling for source data-free domain adap- tation.IEEE Transactions on Circuits and Systems for Video Technology, 32(6):3749–3760, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:a495fabed28d366ce18f1bcd1e2c79f3168bece1eec4971d5f946001067484f6","observation_id":"468b0b87-8145-46e0-a46a-5b3eca1ae30e","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Gda: Generalized diffusion for robust test-time adaptation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:36ade5eeb516ff56c5929eb2a7e61efa09e4a565e6db7cd2ae3edd3bbf40e333","observation_id":"fe589987-0a0d-42d9-b661-1c74669ef1f8","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Yolov8: A novel object detection algorithm with enhanced performance and robust- ness","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:a3b28c33638e04ee25c051b6bfe850726b33522869cfc993f9cee9503099387f","observation_id":"ced0bfc4-3b13-4a85-8935-70834d85409c","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10726","last_updated":"2021-03-18T17:58:01Z","snapshot_observed_at":"2026-08-16T06:30:33.794820Z","submitted_at":"2020-06-18T17:55:28Z","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10726","snapshot_observed_at":"2026-07-11T23:48:25.354479Z","title":"Tent: Fully test-time adaptation by entropy minimization.arXiv preprint arXiv:2006.10726,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"cited_paper":"/paper/2006.10726","citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:14d76051963c92c9414b0586bbb89dcd81880ccb4e40e0f2924508bcb5f9127f","observation_id":"641ce8e3-a724-4471-b157-67c88f02ed61","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Continual test-time domain adaptation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:a741602ae3d0534fd1030d290c1660881a93f006b805442c77ec1e44a645ca0a","observation_id":"ea4c87a0-9395-4dea-b9ee-32bb9b9f04e3","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Feature alignment and uniformity for test time adap- tation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:15930b5f823b114d53d8d251e9911ab74b8a9f33540a04570c13892c6db923ca","observation_id":"c3e44b9b-967f-45aa-89e4-a9573d5a4e7c","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Dynamically instance- guided adaptation: A backward-free approach for test-time domain adaptive semantic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:19353c656d48bef261eec2a4243d60d344e40db7b9433efe10d603b44e4bece2","observation_id":"ba5d128b-165e-48e8-b731-5adbe25f5150","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Sam4udass: When sam meets un- supervised domain adaptive semantic segmentation in intel- ligent vehicles.IEEE Transactions on Intelligent Vehicles, 9 (2):3396–3408, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:75c4b5907e17170292bd0c9ba1447398433c94e2553c93fcd1bdf68b9fb09798","observation_id":"904dc1fe-1ed1-47f4-b612-15b57725c2b2","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Source data-free unsupervised domain adaptation for seman- tic segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:a3d5a24a73638259a72fc8fb8a156813c433b1aa56c6acc7d32ee0fc25e0c110","observation_id":"1a910baf-afea-4b61-9096-301778a75479","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","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":"2026-07-11T23:48:25.354479Z","title":"Towards better stability and adaptabil- ity: Improve online self-training for model adaptation in se- mantic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:607ee66721d72215a78274f05d9f23c536371a81fd92119fcc4f7f973cc067aa","observation_id":"34b19095-4706-4fbc-99bc-53e355b450bf","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.12156","last_updated":"2023-06-21T10:08:29Z","snapshot_observed_at":"2026-08-19T15:15:13.657700Z","submitted_at":"2023-06-21T10:08:29Z","title":"Fast Segment Anything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.12156","snapshot_observed_at":"2026-07-11T23:48:25.354479Z","title":"Fast segment any- thing.arXiv preprint arXiv:2306.12156, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-11T23:48:25.354479Z"},"links":{"cited_paper":"/paper/2306.12156","citing_paper":"/paper/2607.03810"},"observation_digest":"sha256:dfefdc953e9d9f46aa835997a2530c25e934331d77c514a12f98d3128c5021bb","observation_id":"1db77851-2c53-4e33-af7d-f4e3586a12fa","resolution":{"observed_at":"2026-07-11T23:48:25.354479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.03810","last_updated":"2026-07-04T10:32:15Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T06:31:19.985897Z","submitted_at":"2026-07-04T10:32:15Z","title":"TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":44,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":44},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2607.03810."}