{"as_of":"2026-08-20T09:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d8cf0870d431abdae752e06b17a64cb88be38277a042cb351133789daead1fb5","coverage":[{"denominator":94,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":94,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:44:43.994992Z","state":"measured"},{"denominator":95,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":95,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-15T18:25:21.621268Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-15T18:26:26.946270Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"cited_work":{"arxiv_id":"2506.19022","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.19022","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Orthogonal projection subspace to aggregate online prior-knowledge for continual test-time adaptation","venue":null,"work_id":"aebf5336-d4b3-4a97-8b1e-be6d9abb2a00","year":2025},"citing_paper":{"arxiv_id":"2603.01400","last_updated":"2026-04-09T18:07:09Z","snapshot_observed_at":"2026-08-12T17:05:28.993798Z","submitted_at":"2026-03-02T03:06:40Z","title":"Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-15T18:25:21.621268Z"},"links":{"cited_paper":"/paper/2506.19022","citing_paper":"/paper/2603.01400"},"observation_digest":"sha256:29442a6ca019149540928fafdbc401eab3e2eb010c880f382f663faad883e946","observation_id":"dfa922e3-a8f2-4bc4-9a88-33451116a8f3","resolution":{"observed_at":"2026-05-15T18:26:26.948407Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.19022/citation-record","integrity":"/paper/2506.19022/integrity","json":"/paper/2506.19022/citation-record.json","paper":"/paper/2506.19022"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:44:42.212515Z","title":"Beit: Bert pre-training of image transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.212515Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:6452e658c937d56267252ea89042253003233dafdb8b20b9a107bac1e9867f5b","observation_id":"7314fdf8-2b03-4231-9779-1ca6bc38c7b7","resolution":{"observed_at":"2026-08-15T18:44:42.212515Z","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":"2026-08-15T18:44:42.220838Z","title":"In search for a general- izable method for source free domain adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.220838Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c701c09cb0506969242793249421495dbbf75f69cdc293996f8238510ef0f3db","observation_id":"69778c02-3b3d-4913-849c-c3e2feae3273","resolution":{"observed_at":"2026-08-15T18:44:42.220838Z","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":"2026-08-15T18:44:42.226139Z","title":"Large scale GAN training for high fidelity natural image synthesis","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.226139Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:8b9861e9c8ffd37f92e4731c92b1bebb4d4aea28181460f916abc0beb39f585d","observation_id":"3b70f7cf-b8c9-41a4-b988-3efe3f4db234","resolution":{"observed_at":"2026-08-15T18:44:42.226139Z","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":"2026-08-15T18:44:42.246428Z","title":"Angular visual hardness","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.246428Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:d05bbf444c2a2f913e470adfcbb2fa433d770b44579a2da3c5ca11a9e51b3a5d","observation_id":"6ff77939-944f-4f92-8f25-5ee6a6ac5522","resolution":{"observed_at":"2026-08-15T18:44:42.246428Z","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":"2026-08-15T18:44:42.310742Z","title":"Contrastive test-time adaptation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.310742Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:8c1059c33029afd4fd6a36de1a2bdd2592ad745cc7dccc690989e1dfe1e17649","observation_id":"e8f7889d-659c-4b68-8439-bebedb0074c6","resolution":{"observed_at":"2026-08-15T18:44:42.310742Z","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":"2026-08-15T18:44:42.359251Z","title":"Robustnet: Improving domain generalization in urban-scene segmentation via in- stance selective whitening","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.359251Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b50349e667a4036b12ef44f8e0c80147d862fc7b4b81da93606a76ec986ec0ab","observation_id":"9493bb25-588c-4c25-9286-474fea0f7d91","resolution":{"observed_at":"2026-08-15T18:44:42.359251Z","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":"2026-08-15T18:44:42.431562Z","title":"Improving test-time adaptation via shift-agnostic weight regularization and nearest source prototypes","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.431562Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:cb5c11c1d611ac0d989667035b39291b84216fb2011a7b05c1796a84f8b6bf9e","observation_id":"71100894-d8ba-4fbc-9e00-f48d89a78765","resolution":{"observed_at":"2026-08-15T18:44:42.431562Z","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":"2026-08-15T18:44:42.493176Z","title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark.https : / / github","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.493176Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:54718c84975d1a24756563fc2503d56316409c20a72f8e255712ab8853cda4fb","observation_id":"39b74ada-cb99-4935-9b6e-4454f41bb65a","resolution":{"observed_at":"2026-08-15T18:44:42.493176Z","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":"2026-08-15T18:44:42.514447Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.514447Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c5e6b9892a7340dad91cf8cd3f7a87622086f3d55ca30a65af2ac42a95b51695","observation_id":"9d9d801d-36dd-48c7-859e-1b5dd82499fe","resolution":{"observed_at":"2026-08-15T18:44:42.514447Z","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":"2026-08-15T18:44:42.530561Z","title":"Bert: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.530561Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:16979196782373b62557973af0d8640c6c036c4bcd25cb5a6e0ffba1f9c4e38b","observation_id":"d4fc8bbb-b18b-4351-b3a1-d66bb8ad066f","resolution":{"observed_at":"2026-08-15T18:44:42.530561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.04552","last_updated":"2017-11-29T14:51:40Z","snapshot_observed_at":"2026-08-13T11:54:46.030796Z","submitted_at":"2017-08-15T15:21:53Z","title":"Improved Regularization of Convolutional Neural Networks with Cutout","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.04552","snapshot_observed_at":"2026-08-15T18:44:42.541037Z","title":"Improved regular- ization of convolutional neural networks with cutout.arXiv preprint arXiv:1708.04552, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.541037Z"},"links":{"cited_paper":"/paper/1708.04552","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:1f882a27042758b16a0b788b1d019b0d562773240223f2dac0d8e2c102ffbb0f","observation_id":"de7beb9b-131e-434f-b062-7a63b657c4e9","resolution":{"observed_at":"2026-08-15T18:44:42.541037Z","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":"2026-08-15T18:44:42.545742Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.545742Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:e511803a1c898e43a66d89fa6f61601996ed6e0250515a58a94f715f1fece8b1","observation_id":"98382b21-f245-4e88-83b3-baabe67801c1","resolution":{"observed_at":"2026-08-15T18:44:42.545742Z","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":"2026-08-15T18:44:42.550298Z","title":"Switch transformers: Scaling to trillion parameter models with sim- ple and efficient sparsity.JMLR, 23(120):1–39, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.550298Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:86fd62bbc477bbe2d5f4d8a94eb1426444d056e2cb6f9963a1098685bf5396b9","observation_id":"fcae5b00-c866-4cfb-b495-89a1410bad5d","resolution":{"observed_at":"2026-08-15T18:44:42.550298Z","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":"2026-08-15T18:44:42.555085Z","title":"Decorate the newcomers: Visual domain prompt for continual test time adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.555085Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:559b10584bbf769bab8bfbd8d9b411ea3c48e550340af0ad38b85eed0d2af815","observation_id":"562a36ad-881b-48ce-ba32-908cc6ecca23","resolution":{"observed_at":"2026-08-15T18:44:42.555085Z","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":"2026-08-15T18:44:42.559766Z","title":"Test-time training with masked autoencoders","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.559766Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:7c0631788c849e6a3cd8d21c6eb2f8374036f960b5573acf3bbf21d2713cb9e7","observation_id":"14b63dbf-3508-4d37-bf47-881504cab7ed","resolution":{"observed_at":"2026-08-15T18:44:42.559766Z","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":"2026-08-15T18:44:45.750805Z","title":"Clip-adapter: Better vision-language models with feature adapters.IJCV, 132(2):581–595, 2024","venue":null,"work_id":"494c239e-b851-4ceb-9836-9d549058c5c9","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.564855Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:742c496260f70f02c0f094f74ccdbd6f23602e770159f12a00f687e86527638d","observation_id":"0ee614ab-a680-4a90-9205-8d0e65e45534","resolution":{"observed_at":"2026-08-15T18:44:45.756188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.734907Z","title":"Mimic before reconstruct: Enhancing masked autoencoders with feature mimicking.IJCV, 132(5):1546–1556, 2024","venue":null,"work_id":"9ae0f919-08cc-4796-aa91-e78c9ede076b","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.569644Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:e765ea9efdc78fb1275a27234d585691010cfdb887349e87e562fbafcade8c2b","observation_id":"28ef495a-fe61-4987-af8d-3eec37f378a7","resolution":{"observed_at":"2026-08-15T18:44:45.740125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.04831","last_updated":"2022-11-30T19:22:22Z","snapshot_observed_at":"2026-08-16T16:25:32.649525Z","submitted_at":"2022-10-10T16:45:13Z","title":"Visual Prompt Tuning for Test-time Domain Adaptation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.04831","snapshot_observed_at":"2026-08-15T18:44:42.575789Z","title":"Vi- sual prompt tuning for test-time domain adaptation.arXiv preprint arXiv:2210.04831, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.575789Z"},"links":{"cited_paper":"/paper/2210.04831","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:57a86715f71a1d985f7447be8f65923a4dcb135f5ba1fbef144f87ca29e65a01","observation_id":"8640a283-c6f8-4c43-8685-941cc2a03fb8","resolution":{"observed_at":"2026-08-15T18:44:42.575789Z","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":"2026-08-15T18:44:45.719317Z","title":"Towards a unified view of parameter-efficient transfer learning","venue":null,"work_id":"ed27b63d-68cf-444f-9880-28dcda6f5c7d","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.581188Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:0e33a33e1fac90326ff12fc0bacd024ee488a88f35b0d704065ba61fcaf3fb06","observation_id":"0b1b3080-08dd-468d-98c7-da13aaa1dd4d","resolution":{"observed_at":"2026-08-15T18:44:45.724325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:42.585984Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.585984Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:9a3c03d4e33b563a6d4776e74c6a1a0e7982b66c1f422b3a3db17bdebb8b6170","observation_id":"a092ecef-3264-483e-ad17-391036767650","resolution":{"observed_at":"2026-08-15T18:44:42.585984Z","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":"2026-08-15T18:44:45.692359Z","title":"Momentum contrast for unsupervised visual rep- resentation learning","venue":null,"work_id":"dc034df6-8152-4559-9cab-08a147a8cd52","year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.590459Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:25c277c03449e8f0deec060bbd4668ad823719d9dc6c4e2bc8a022cbbf5a9b7f","observation_id":"c450fdd9-fcd8-4485-9dbb-d6975994098c","resolution":{"observed_at":"2026-08-15T18:44:45.697618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.676683Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":"2c4f596a-96c6-4160-9e8b-af43e8fb49a1","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.595555Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:2e22aab49379a115106d3769492f23aba2a6a27585f7c26e1c91c6b51bed3166","observation_id":"b97c6023-55a9-43f9-bf3e-0732747c6077","resolution":{"observed_at":"2026-08-15T18:44:45.681845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.06049","last_updated":"2022-12-19T19:21:47Z","snapshot_observed_at":"2026-08-19T23:41:41.483796Z","submitted_at":"2022-08-11T21:58:36Z","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.06049","snapshot_observed_at":"2026-08-15T18:44:42.600290Z","title":"Milan: Masked image pretraining on language assisted representation.arXiv preprint arXiv:2208.06049,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.600290Z"},"links":{"cited_paper":"/paper/2208.06049","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:7d15a70b22e8644f2cf855de158f45d9644f12ca00a8bb8b5f069354525a0325","observation_id":"61a78edb-2d3b-4680-a5c8-cb821c9979e3","resolution":{"observed_at":"2026-08-15T18:44:42.600290Z","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":"2026-08-15T18:44:45.659393Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"dd9a7ac7-61eb-4554-a2b6-2097393d8d52","year":2019},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.605438Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b4111e87985e07d471748d0b118bfd10a0ffe14e749dba2828abe843a857679c","observation_id":"89bf63c6-6ec3-4cfb-9104-c717bc3e5b57","resolution":{"observed_at":"2026-08-15T18:44:45.665493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.643903Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"1a52fcf5-1e09-4b6d-adab-1fe90773d4b2","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.609941Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:0c455777b545b93d1e98e8086508ab24c0a45ee58911fc5d07429a2eb20b146a","observation_id":"d2119ad4-2418-4e5b-9b9d-134491218ab4","resolution":{"observed_at":"2026-08-15T18:44:45.648741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.626881Z","title":"Densely connected convolutional net- works","venue":null,"work_id":"685c7579-1b57-481c-8143-e2de72230a37","year":2017},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.614847Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b3769286d27695366ab65e8cef3266dafb45838e285f09be375fe96c8c813509","observation_id":"1ad075d5-bc6f-47ae-9768-6503adfdcdbd","resolution":{"observed_at":"2026-08-15T18:44:45.633272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.609555Z","title":"Test-time classifier ad- justment module for model-agnostic domain generalization","venue":null,"work_id":"c7458411-f428-454e-aeba-55887c5e4a04","year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.620083Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:54cdafd91048a5fef1b804ad848c40a655bc094720d0ba65031ba92e947bd7e2","observation_id":"d990dbb5-1597-4b25-b6ff-98b129ff2adf","resolution":{"observed_at":"2026-08-15T18:44:45.615930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.592669Z","title":"Vi- sual prompt tuning","venue":null,"work_id":"4f5c1fa8-98df-435d-8334-3d5d11f6b120","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.625989Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:dacdeca30f25871129a8dd0b73398c59586b11f99696c28d658036c0e9e973e8","observation_id":"9694fe5c-d29c-462c-a0ab-d3c7e906010d","resolution":{"observed_at":"2026-08-15T18:44:45.598544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.576813Z","title":"TSIT: A simple and versatile framework for image-to-image translation","venue":null,"work_id":"0e4805fd-1859-4519-8f5d-ec2a61ecce02","year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.638793Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:43c33fcc5d2648456e9e0924e7504719d22a1ab71e047d58ab812ca7f3048aa3","observation_id":"da85aace-a349-4697-9f80-3f732de3a7f0","resolution":{"observed_at":"2026-08-15T18:44:45.582097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.561067Z","title":"Novel dataset for fine-grained image categorization: Stanford dogs","venue":null,"work_id":"f84904dd-55a7-4f71-923f-038ed66460ae","year":2011},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.655314Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c868ccb5e056caaf8b509eec8095a1c971267232dc59ec0b0876ffbb0cf1331c","observation_id":"916a97dc-95b7-48f6-b349-bd0f78d4f046","resolution":{"observed_at":"2026-08-15T18:44:45.565763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.546001Z","title":"Kingma and J","venue":null,"work_id":"e9fbbf56-fb8c-4d72-859e-4d1857ad9cf4","year":2015},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.699265Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:f7f76386a0c76b5a672d4a10d4d6f8da47fd9aa2a42083d966be60d0cf0a5fa1","observation_id":"19770476-5b0d-47d6-8664-e47866c77413","resolution":{"observed_at":"2026-08-15T18:44:45.550749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.530363Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"345f91f1-566f-4e15-bfe2-ea88391f1195","year":2009},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.731006Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:59f81ce84f7edad1bfe58e1666545f3037b82009f120b21cfb641825114ba697","observation_id":"a16face4-4164-41c6-94e2-1145f5a0f662","resolution":{"observed_at":"2026-08-15T18:44:45.535698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.513684Z","title":"Universal source-free domain adaptation","venue":null,"work_id":"5f251a53-63af-4d15-bb2c-46a0643d7654","year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.759061Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:f3b61b099949ba42223812e23c2206ff3406bde11d0262f48759b3561c02c1fa","observation_id":"d451731c-91b5-4e69-b831-404413f56485","resolution":{"observed_at":"2026-08-15T18:44:45.518664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.498678Z","title":"Becotta: Input-dependent online blending of experts for continual test-time adaptation","venue":null,"work_id":"fa0f9dea-eeaf-4ecd-989d-75114679f15e","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.821970Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:4eff2bcae25fa434a9ef9a87efb892ed25b96080ab0d82eb4eb7668e3255609f","observation_id":"6c640949-77fc-46c0-a958-e5f2a3a21045","resolution":{"observed_at":"2026-08-15T18:44:45.503357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-16T20:01:36.160048Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-15T18:44:42.838618Z","title":"The power of scale for parameter-efficient prompt tuning.arXiv preprint arXiv:2104.08691, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.838618Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:e2590e700f0e358eb0f9a7c9ad80ecb50b7fe2c96a6976d63a4f821634b6ec2f","observation_id":"3319bb58-31af-4f0b-86d2-7c24ff4bc77c","resolution":{"observed_at":"2026-08-15T18:44:42.838618Z","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":"2026-08-15T18:44:45.483103Z","title":"Semantic segmentation with generative models: Semi-supervised learning and strong out-of-domain generalization","venue":null,"work_id":"bd67afe2-c1b3-40f9-86f0-340221b6e271","year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.844085Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:fe38a8d7e9370d1d55d1e8bd96fd61a0fd79f2b970ea3154f918514834f88823","observation_id":"a69faf26-985f-4dcf-9040-10de7ab0b23d","resolution":{"observed_at":"2026-08-15T18:44:45.488133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.466818Z","title":"Expansion and shrinkage of localization for weakly- supervised semantic segmentation","venue":null,"work_id":"beed6cb1-5c1f-4f23-a4df-f5029e2e9c30","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.849220Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:a25674c1e9ac44e2c3d5843f82fc233b38bb596b23aa34cbc1ed20040fd5ad58","observation_id":"88a7dca7-bc25-4915-816c-ed6ffb3d4ef1","resolution":{"observed_at":"2026-08-15T18:44:45.471739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.449282Z","title":"Weakly supervised semantic segmentation via pro- gressive patch learning.IEEE Transactions on multimedia, 25:1686–1699, 2022","venue":null,"work_id":"2787a03b-7282-4478-adee-eafbc23b52bc","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.888724Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:ab63b00c63d5105508c06be902586a1c325a15041c8ab5b47f6a93fc9ad51426","observation_id":"b7f8bea9-e9b5-4af3-b092-901b6b811b29","resolution":{"observed_at":"2026-08-15T18:44:45.454522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.432207Z","title":"Weakly supervised semantic segmentation via self-supervised destruction learning.Neurocomputing, 561: 126821, 2023","venue":null,"work_id":"2d5ec60d-13e3-48b2-a3f9-b5b6fe1b0b3c","year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:42.958528Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:3339657a6a8cd1e88e464729c0f5da584b981d7192ddab6b082e42b97b7e0253","observation_id":"3e1e2115-918b-4230-8931-2d2caf488ee8","resolution":{"observed_at":"2026-08-15T18:44:45.438605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.412297Z","title":"Cross-modal and uncertainty-aware agglomeration for open- vocabulary 3d scene understanding","venue":null,"work_id":"6749a474-cf8d-413c-8cb5-e8aa8487330c","year":2025},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.015382Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:f011390a9adae4580a5c777b2215b3c3b0556fb0d404a21ec283ae147ff74635","observation_id":"6c1fed57-e1fe-4b75-ad54-340c398a6cd7","resolution":{"observed_at":"2026-08-15T18:44:45.418782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:43.073508Z","title":"Prefix-tuning: Optimiz- ing continuous prompts for generation.arXiv preprint arXiv:2101.00190, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.073508Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:1ab5815b415b2d0b9a51d2e8e012918bb2ab1fed2a1a3b10fa6adc8727672411","observation_id":"5d2eb44e-ff88-448d-b853-ee46d80d8179","resolution":{"observed_at":"2026-08-15T18:44:43.073508Z","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":"2026-08-15T18:44:45.395144Z","title":"Do we really need to access the source data? source hypothesis transfer for un- supervised domain adaptation","venue":null,"work_id":"c431454e-c67c-4306-b82f-2c18333480dc","year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.099964Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c7b3fca387611733db53a199863f7669873f9747e7b72bb304b3caa255819870","observation_id":"02068c04-3f21-4ac6-8288-7175c3ae3136","resolution":{"observed_at":"2026-08-15T18:44:45.401302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.376379Z","title":"Vida: Homeostatic visual domain adapter for continual test time adaptation","venue":null,"work_id":"932d2c08-e801-4833-a449-f9cd63c569d3","year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.112061Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:50eed34117b846cc722776bb7014fd716e011add62aa779b6d6628871b0a853a","observation_id":"93b21a02-cf29-4d4c-a60c-09ba6242b46a","resolution":{"observed_at":"2026-08-15T18:44:45.382029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.361234Z","title":"Continual-mae: Adaptive distribution masked autoencoders for continual test-time adaptation","venue":null,"work_id":"96bade5d-4840-4455-9d76-ad6d4fb81808","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.117480Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:9a1b4863966e1f83db1f451891f7ac0e04ee8142b8ea963bdddf8f4d28dcd1e6","observation_id":"c87f2ec1-4da0-4e78-8e85-e47e0cca1d05","resolution":{"observed_at":"2026-08-15T18:44:45.366145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.345261Z","title":"Deep hyperspherical learning","venue":null,"work_id":"c21fc3d6-0e6b-4be8-96ff-1679802fc91c","year":2017},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.124217Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:f9220d9436d33290bfdcd16f6d8aafb04090a2adb56994d46614e3936bd592cc","observation_id":"59bc20e3-22b0-4e13-91a9-d7341980d2d5","resolution":{"observed_at":"2026-08-15T18:44:45.350465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.328743Z","title":"Learning towards minimum hy- perspherical energy","venue":null,"work_id":"d827068b-8243-45ba-b99b-2555ba857400","year":2018},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.130593Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:be291b5d3ae4b5a32a1675e32104a3598defde87fb9e149099d10826134327da","observation_id":"59866ec1-e25f-4c3e-8179-73950575d492","resolution":{"observed_at":"2026-08-15T18:44:45.333774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.313133Z","title":"Decoupled net- works","venue":null,"work_id":"2be6d86f-7ad3-4839-add4-0f38815bd6c0","year":2018},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.211357Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:6e0d81621ff38cb2c82a7de6cdb3389742cc346773ba7a71861845f4b582c6b8","observation_id":"b201dc0c-10e6-4c49-bbc1-897319b0cdad","resolution":{"observed_at":"2026-08-15T18:44:45.318071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.294356Z","title":"Rehg, Liam Paull, Li Xiong, Le Song, and Adrian Weller","venue":null,"work_id":"8fc8ec58-0184-4e0d-b450-d34a649acaec","year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.318991Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:069393ffc4059eee0cb53106f81be45812c70f142238a8e6560ed35730f4d09a","observation_id":"0ca4c085-10aa-4096-ab58-b33f02185500","resolution":{"observed_at":"2026-08-15T18:44:45.299441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.279336Z","title":"Less: Label-efficient and single-stage referring 3d instance segmentation","venue":null,"work_id":"00ab2068-38b4-4ae0-8015-0d462c323e35","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.364546Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c87e17f5d357e7e1377d515369595bf0e08871f775b43ec9b9c559830d83bbeb","observation_id":"b324c0d5-26b9-47cc-8cc0-0f4cb63fd730","resolution":{"observed_at":"2026-08-15T18:44:45.284024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.262492Z","title":"Ttt++: When does self-supervised test-time training fail or thrive? InNeurIPS, pages 21808–21820, 2021","venue":null,"work_id":"ff045365-47c4-4634-9b30-9a86cc3a91f3","year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.377988Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b8b0c32cbcf3c8040461d0b79130f061be472d37a5351a1a61b3b2be98cc547f","observation_id":"86d2ce9a-110c-46a9-bc24-1a51cc0b17ce","resolution":{"observed_at":"2026-08-15T18:44:45.268087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:43.398570Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.398570Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b32319988064337554d2dd3a262171411bc3a88f37688959e5717420f4dc26d4","observation_id":"91537022-638f-4a13-afc9-de818b49192d","resolution":{"observed_at":"2026-08-15T18:44:43.398570Z","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":"2026-08-15T18:44:45.235246Z","title":"Unsupervised domain adaptation with residual trans- fer networks.NeurIPS, 29, 2016","venue":null,"work_id":"44140764-3431-46aa-9f1f-a5007ccc9117","year":2016},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.403463Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b15b9adc868e6c33d82601f2bd8314869f4c4952cd2e888ab586f44c6a584fda","observation_id":"0a7b98be-7a8c-4d5f-9eeb-8cb6745ab109","resolution":{"observed_at":"2026-08-15T18:44:45.240645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.05840","last_updated":"2024-12-31T14:46:47Z","snapshot_observed_at":"2026-08-18T23:26:14.902567Z","submitted_at":"2024-09-09T17:44:00Z","title":"MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.05840","snapshot_observed_at":"2026-08-15T18:44:43.408642Z","title":"Mmevol: Empowering multimodal large language models with evol-instruct.arXiv preprint arXiv:2409.05840, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.408642Z"},"links":{"cited_paper":"/paper/2409.05840","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:da457aabc0fdd50f308f9a2de68cecf558a079b83256cfc4bc3bfacabe038677","observation_id":"fd3909d8-c02f-4c94-b6c0-70db8a72078c","resolution":{"observed_at":"2026-08-15T18:44:43.408642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10963","last_updated":"2021-01-14T21:11:06Z","snapshot_observed_at":"2026-08-19T09:01:42.968993Z","submitted_at":"2020-06-19T05:08:43Z","title":"Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10963","snapshot_observed_at":"2026-08-15T18:44:43.460075Z","title":"Evaluating prediction-time batch normalization for robust- ness under covariate shift.arXiv preprint arXiv:2006.10963,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.460075Z"},"links":{"cited_paper":"/paper/2006.10963","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b0d203f495ef33a63b8e208e2d481aff1996d8a73bc5a40e1b6b12574baedbdb","observation_id":"b619cb1d-79aa-42ec-b472-b776d3ca3068","resolution":{"observed_at":"2026-08-15T18:44:43.460075Z","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":"2026-08-15T18:44:45.215362Z","title":"Efficient test- time model adaptation without forgetting","venue":null,"work_id":"a194a362-2459-4b23-bcf6-d25756d70a9c","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.538542Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:80a2aec25645f897a3a9e393e58950024bc060949090c5b041f3e9d3f2384f12","observation_id":"631a6444-0d31-4702-9804-10943267446e","resolution":{"observed_at":"2026-08-15T18:44:45.221789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.196219Z","title":"Towards stable test-time adaptation in dynamic wild world","venue":null,"work_id":"956cdd0d-8eee-4baa-811e-b8dc389c3c1e","year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.580329Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:4edc6150c1905fc5091a4d91e10ce94b4eb78473e77666bec35aabba1f807284","observation_id":"3ae212bb-0a39-4749-af2b-f869c2ac0d33","resolution":{"observed_at":"2026-08-15T18:44:45.202633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12036","last_updated":"2024-03-18T17:59:40Z","snapshot_observed_at":"2026-08-16T14:08:41.366278Z","submitted_at":"2024-03-18T17:59:40Z","title":"One-Step Image Translation with Text-to-Image Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12036","snapshot_observed_at":"2026-08-15T18:44:43.587072Z","title":"One-step image translation with text-to-image models.arXiv preprint arXiv:2403.12036, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.587072Z"},"links":{"cited_paper":"/paper/2403.12036","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:e0d57a1a2f629daa85a9aedb20fc6a97b2cb16a10a587795a28840e8e940834c","observation_id":"fae8349a-d410-4962-8e98-7a61fb9a2c93","resolution":{"observed_at":"2026-08-15T18:44:43.587072Z","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":"2026-08-15T18:44:43.592036Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.592036Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:dc375d507570b516a86b67858c007118de40bcfa3580bc4bfd2c2f57d5c4f430","observation_id":"3ed847b4-594b-4a4b-9002-cda4dbb2b20e","resolution":{"observed_at":"2026-08-15T18:44:43.592036Z","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":"2026-08-15T18:44:45.157674Z","title":"Adapters: A unified library for parameter-efficient and modular trans- fer learning","venue":null,"work_id":"e47c8a27-0fff-49a8-8546-5425dff5f76a","year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.596875Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:690be323827f00f5d843a59bb8a5b8e60b7d95a5817a190d2ca465eae182455f","observation_id":"256688ad-d2b7-44b7-a267-2f45c65e6d1a","resolution":{"observed_at":"2026-08-15T18:44:45.165453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.131834Z","title":"Controlling text-to-image diffusion by orthogo- nal finetuning","venue":null,"work_id":"521b518f-026d-491d-8a3a-44f901ecc2f3","year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.603547Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:531dd48aa16615dc3912daedc69e9896abdf0ab4e8c61225981d6cb9ee42a402","observation_id":"6b4ee12e-b4b3-43dd-9009-6e5a9e6dfef1","resolution":{"observed_at":"2026-08-15T18:44:45.138226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.109018Z","title":"Outra- geously large neural networks: The sparsely-gated mixture- of-experts layer","venue":null,"work_id":"d933d98d-2053-41ef-9903-d6f9eb890e91","year":2017},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.633049Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:48d81b71dce33188d08280949720648cae8b2b20d350135dbd8a1c912bd6d713","observation_id":"1a147aa9-e7cd-4755-9937-d9cbac93e10b","resolution":{"observed_at":"2026-08-15T18:44:45.114851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.089239Z","title":"Mm-tta: multi-modal test-time adaptation for 3d se- mantic segmentation","venue":null,"work_id":"fe98c0b1-b00b-4b5c-a1f8-c8404f5b8529","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.676951Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:baf45d650384e7435556d7600671d6d6adcadca92dd04d919fe516dd3121cb31","observation_id":"e205f01b-d8fb-4c96-8f5f-6815a471604d","resolution":{"observed_at":"2026-08-15T18:44:45.096281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.08356","last_updated":"2023-04-15T04:03:04Z","snapshot_observed_at":"2026-08-16T16:08:11.707091Z","submitted_at":"2022-12-16T09:02:01Z","title":"Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.08356","snapshot_observed_at":"2026-08-15T18:44:43.693087Z","title":"Cd-tta: Compound domain test-time adaptation for semantic segmentation.arXiv preprint arXiv:2212.08356,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.693087Z"},"links":{"cited_paper":"/paper/2212.08356","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:2d7a9fd3c094169d8664baa6ea28222670fc72124a23e8b6771cf81c838c0183","observation_id":"522df3bf-de83-43eb-8f7f-a006d39a3722","resolution":{"observed_at":"2026-08-15T18:44:43.693087Z","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":"2026-08-15T18:44:45.068230Z","title":"Ecotta: Memory-efficient continual test-time adaptation via self-distilled regularization","venue":null,"work_id":"fb943e13-8f26-4beb-b9fb-223d21af646d","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.698355Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:ff90a93bdce2a450f20692c916d39208f0e7f66593745ca9106e2838c84df006","observation_id":"671f8ffe-8acc-4aba-ba21-909a0ed23472","resolution":{"observed_at":"2026-08-15T18:44:45.074972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.046455Z","title":"Shift: a synthetic driving dataset for continuous multi-task domain adaptation","venue":null,"work_id":"b93f5521-bbb6-4ca3-9c83-68420cd5971f","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.704144Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:6f0977207d57bed7c7d9861ce2598aa0d09ab0c0fe416e9d86db4e459ca1439a","observation_id":"4cff51ec-600a-4b6c-afbe-5f3c93f99706","resolution":{"observed_at":"2026-08-15T18:44:45.052895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:45.019506Z","title":"On orthogonality and learning recurrent networks with long term dependencies","venue":null,"work_id":"cecb4ee8-addc-4815-a7fe-6221891c0f0d","year":2017},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.708809Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c3f464537f70132463dcf412b331ede95881ba480fb9ccbe50c29fe1e4243c34","observation_id":"b260c738-8489-4e45-8e9e-8d6d845fb9fe","resolution":{"observed_at":"2026-08-15T18:44:45.029849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.994358Z","title":"Tent: Fully test-time adaptation by entropy minimization","venue":null,"work_id":"6ad10ac4-e321-4741-b75f-cb57d57d2074","year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.728838Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:144a5f9e946bdd44697a63b48a42615cee208e6df1b2195f15c50b869a198c75","observation_id":"80c91d1b-5e4f-4141-b981-606a44e4b78a","resolution":{"observed_at":"2026-08-15T18:44:45.002405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.964513Z","title":"Con- tinual test-time domain adaptation","venue":null,"work_id":"990f1c87-f2cf-482f-9b34-c0df40db8b15","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.770660Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:893431d4b24c4e053b970d066b14d72b22a0d05ce1570f752e6d3e82f38b1da1","observation_id":"18fc914f-9cba-4416-bf32-3841524157be","resolution":{"observed_at":"2026-08-15T18:44:44.975213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.947720Z","title":"Segformer: Simple and ef- ficient design for semantic segmentation with transformers","venue":null,"work_id":"c4902f43-7287-40e5-92ee-08b1d0b1c265","year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.804432Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:d32994a81dbcdff985562a9bb93439f91b1c39fccb8c99ebd67798b34a8c550f","observation_id":"7910b8d9-62bf-47d5-99fa-e0d1d4e821c1","resolution":{"observed_at":"2026-08-15T18:44:44.953044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.926506Z","title":"Simmim: A simple framework for masked image modeling","venue":null,"work_id":"3f39fc52-8071-42d4-947f-aa6c6a221fe2","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.832398Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:7664e654cd63a70be7f7588b556956b638da6f74965282d1ef7234a5ff0b83ee","observation_id":"02158468-b66a-488e-be1b-b25bc1278718","resolution":{"observed_at":"2026-08-15T18:44:44.936346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.901626Z","title":"3d weakly supervised semantic segmentation with 2d vision-language guidance","venue":null,"work_id":"50b2f11d-069a-4b71-b496-450478480b88","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.837742Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:6a773c1427b3b09671bd212e8815935ac4828a2e9e5ad8c0db5ae70821b3f7c1","observation_id":"f1080993-b871-473b-b288-7286ed9cfd5b","resolution":{"observed_at":"2026-08-15T18:44:44.909376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.871092Z","title":"Generalized source-free domain adaptation","venue":null,"work_id":"c2971827-d601-464c-b2f5-d55eb6778492","year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.842533Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:ea495906babf04f85c6114707d5ad7340f874f41be26d44925cad8e3195abf4b","observation_id":"6e3bcfe1-2af4-4646-8823-6f5851881e38","resolution":{"observed_at":"2026-08-15T18:44:44.879672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.849985Z","title":"Exploring sparse visual prompt for domain adaptive dense prediction","venue":null,"work_id":"622b6ab3-7235-45b3-a9f3-fd25cbc309c5","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.847305Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:701f12976cecdd8a22341f59b4769ca25ea0127e480bff766862039c284a3814","observation_id":"618a3366-f822-492e-9428-44b6884fe391","resolution":{"observed_at":"2026-08-15T18:44:44.857369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.830360Z","title":"Robust test-time adaptation in dynamic scenarios","venue":null,"work_id":"a479d4ca-6323-462d-82eb-395ed3c65433","year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.852028Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:6c01bde15bcad743040efb14a9304387e6a13ffb74f1d8f4108ec9044539a1d9","observation_id":"d0734716-a488-493f-8d93-7f31f59f31cc","resolution":{"observed_at":"2026-08-15T18:44:44.836422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.806703Z","title":"Cutmix: Regu- larization strategy to train strong classifiers with localizable features","venue":null,"work_id":"a3a13a6c-97e2-4cf0-ad69-3eb0a2d638c2","year":2019},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.857198Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:fee453d16510ff606d7475e992acbf5e4dd2e35fa93845c5806502c55185af8e","observation_id":"668d8d0b-c222-4eee-916f-7ab17b57e6fc","resolution":{"observed_at":"2026-08-15T18:44:44.812783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.786475Z","title":"Generalized source- free domain-adaptive segmentation via reliable knowledge propagation","venue":null,"work_id":"a7b7712f-1134-4985-8656-bd564a917c4d","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.862230Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:737ea57634eb3954099913dc8da087430666e0a46f3b138e9e0b824fb17e8494","observation_id":"dfd0b74b-73d8-406c-948f-4e8be5ccadb5","resolution":{"observed_at":"2026-08-15T18:44:44.791966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.762341Z","title":"Boosting novel category dis- covery over domains with soft contrastive learning and all in one classifier","venue":null,"work_id":"2684cea0-1330-4eb4-bcef-d936b6c6c577","year":2023},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.866965Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:f00efaa62731d52b17135a9e9ab451131d8f181f7520fc67a3f95527413a2373","observation_id":"68d90005-937b-4bb4-885f-fb0dd3dee2f8","resolution":{"observed_at":"2026-08-15T18:44:44.768296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.742188Z","title":"S2 transformer for image captioning","venue":null,"work_id":"f4754950-cb63-4b5a-a14e-268936d42ffd","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.871148Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:9ebbd1adf5a6e8dc8696dbb33c5b3f1812a1bbf8e8b656e7d5530a6f68f134a3","observation_id":"2139aac7-f89d-4aab-850e-e622618e2299","resolution":{"observed_at":"2026-08-15T18:44:44.749487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.721510Z","title":"mixup: Beyond empirical risk minimiza- tion","venue":null,"work_id":"b0f84959-578d-436c-8569-a9e81cfe8b69","year":2018},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.876773Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:1f3641513f60c2ea40a8f99b571f05cdf5cfd608d00537a1c2d8610e4039ff96","observation_id":"5eef3e0a-6f5c-47d6-9fb1-c0d30640eb3f","resolution":{"observed_at":"2026-08-15T18:44:44.730211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.694524Z","title":"Mpt: Multi-grained prompt tuning for text-video retrieval","venue":null,"work_id":"9df97c21-eb55-4d5e-83e7-e873294d9331","year":2024},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.884552Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:d1f7634fca0d4d3c8fe795fb00f4765a3bbb6a31ad87fc3e47da6dc2303bbc1d","observation_id":"0f8b8ced-6e01-473b-b0ea-ec3079400a6c","resolution":{"observed_at":"2026-08-15T18:44:44.706423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.676077Z","title":"Tip-adapter: Training-free clip-adapter for better vision- language modeling","venue":null,"work_id":"63d2ae2e-eb09-4c74-bb62-69706b908adc","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.889677Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:357d5d729d4eb1b96b755752551e279c7c58fdecffd249c4d27f247172d24f88","observation_id":"28fc86cd-3134-40eb-a3aa-0addd8bb2891","resolution":{"observed_at":"2026-08-15T18:44:44.681152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.659546Z","title":"Auxadapt: Stable and efficient test-time adaptation for temporally consistent video semantic segmentation","venue":null,"work_id":"06c0597f-6377-434c-b215-3913709715db","year":2022},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.896266Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:08dbd85c2501a2d994c2f4ad3398aecf62c40973b95f55515a3f824102b7d54f","observation_id":"67c64fd5-9975-46b8-90b6-0284ea9d7abc","resolution":{"observed_at":"2026-08-15T18:44:44.664280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.643793Z","title":"Fishertune: Fisher- guided robust tuning of vision foundation models for domain generalized segmentation","venue":null,"work_id":"968c7559-b93b-45ab-9c8c-c71e7c32b3b9","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.901233Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:64f52aee81a7a5c8474844b7899bbb4e1b4a7095e4bfe6665e30409f79ef35b3","observation_id":"15e4c08e-d011-4d7a-9b35-a73942fa55bc","resolution":{"observed_at":"2026-08-15T18:44:44.648515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.624435Z","title":"Random erasing data augmentation","venue":null,"work_id":"ae601553-5045-44ed-9415-74cbe38cdea1","year":2020},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.906712Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c2a342072234496465dc6a08a48d427c4564dc84f5627d92f93fc5d5335fae3f","observation_id":"446fd346-8a12-472e-ad1c-2d622ae040d9","resolution":{"observed_at":"2026-08-15T18:44:44.632163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04260","last_updated":"2022-02-03T21:26:25Z","snapshot_observed_at":"2026-08-16T17:50:47.632734Z","submitted_at":"2021-10-08T17:15:47Z","title":"Taming Sparsely Activated Transformer with Stochastic Experts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04260","snapshot_observed_at":"2026-08-15T18:44:43.912081Z","title":"Taming sparsely activated transformer with stochastic experts.arXiv preprint arXiv:2110.04260, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.912081Z"},"links":{"cited_paper":"/paper/2110.04260","citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:550a1b35ce01f85a653de803e5fbea2b182c08390392ae25d095068e71a3f960","observation_id":"a8b4d82a-8da6-4d42-ba48-29c7ac74bfcf","resolution":{"observed_at":"2026-08-15T18:44:43.912081Z","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":"2026-08-15T18:44:44.601707Z","title":"First, based on previous studies [4, 45, 47], the angles of weights in neural networks capture most informative char- acteristics","venue":null,"work_id":"f06642e1-cf59-4cb5-a1ef-a7a460bcb4d9","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.917074Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:628e05d622b92b24901b6697125b5d4deacd7f787b10edfe4d0def99fe783867","observation_id":"74336fe3-c688-45a7-8c4c-94c1026cc371","resolution":{"observed_at":"2026-08-15T18:44:44.608853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.580300Z","title":null,"venue":null,"work_id":"acf60535-6025-44a0-86c2-06f3bd178037","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.921728Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:728c3d89fc7cdf8d9630fb044b36d66d21afeb91bee4784caf89227b5c3fe7b6","observation_id":"c3f0dc6c-6860-42bf-b119-1d0c00586fe2","resolution":{"observed_at":"2026-08-15T18:44:44.587418Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.557033Z","title":"As shown in Tab","venue":null,"work_id":"8bb6f0e6-5484-4f8d-a208-b55becca835f","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.928237Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:7d29acb36414564d0303368c2dfb5ff3aff9804fef4f7e77fb1c88dc73a56ff7","observation_id":"25bb3d28-e4da-4bc8-b0a3-812d6ef76664","resolution":{"observed_at":"2026-08-15T18:44:44.562028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.475078Z","title":null,"venue":null,"work_id":"3ef0d931-6ca6-482f-b28a-ff0e0bb408f8","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.933165Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:c4c5c59fba704627d1ae1737874932dafbfa72a535d006a509d869c53bbc906a","observation_id":"5acf217c-be5b-4ddc-a180-1378fcf7a9cd","resolution":{"observed_at":"2026-08-15T18:44:44.542251Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.371430Z","title":"In our main paper, we ablate the experimental results with differ- entgrid sizesand masking ratioα","venue":null,"work_id":"1c847da3-be9b-4816-a9b9-f83c6f742f5f","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.937801Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:a79f75b82bb93ba22b1076d62d2adf046ef674904de7cfe23db42813bade6309","observation_id":"5a201ccf-f187-4b1a-ba3e-f961cece00a2","resolution":{"observed_at":"2026-08-15T18:44:44.422411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.281946Z","title":"We obtain 59.6% mIoU and 59.7% mIoU for reimple-BECoTTAM and BECoTTAM w masking, respectively","venue":null,"work_id":"09fdcae2-4a22-4c3c-b712-799a2647210e","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.943257Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:d662690d85c955a0a29087a7706dc8b839b360906d3c7c015d42f41eee8a9b30","observation_id":"8388cfe3-a843-457a-abc6-4439a5ed0bb7","resolution":{"observed_at":"2026-08-15T18:44:44.302987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.260008Z","title":"We adopt the same comparative environment with one single Nvidia A6000 48GB","venue":null,"work_id":"57b408b8-a6da-436d-bfa0-0cb2246ec555","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.951165Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:b595847e79179b4120285789ce9164f33caa11fa78a52fb684f09e29cb2d7adc","observation_id":"d4e58b25-7997-4c2a-872b-1452623d092e","resolution":{"observed_at":"2026-08-15T18:44:44.265566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.241977Z","title":"Our implemen- tal hyper-parameters are shown in Tab: 9","venue":null,"work_id":"fe283afa-8b84-4632-bfb2-38598aae00bc","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.973492Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:0301e027b94dee4aad475269673bf5147876761ebd7c8957c2f234bb51ee89aa","observation_id":"a57c74c2-7d4b-4cd8-81cf-998cc04c234a","resolution":{"observed_at":"2026-08-15T18:44:44.247258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T18:44:44.224343Z","title":"However, it requires detailed hyperparameters choices, in- cluding the rankrin OPS, the maskinggrid size sand masking ratioαin IMS, and loss weight tuningλin Lorth","venue":null,"work_id":"8bbb2086-f390-42ef-aa03-7a0aff40121c","year":null},"citing_paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-15T18:44:43.994992Z"},"links":{"citing_paper":"/paper/2506.19022"},"observation_digest":"sha256:d08fea4f6b014910cac1a6b74f7067be3900703329fb836329ecb8d893ebd4f9","observation_id":"3dbe20e8-45c3-4087-b987-350f5fbf4004","resolution":{"observed_at":"2026-08-15T18:44:44.231067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.19022","last_updated":"2025-06-23T18:17:39Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T18:03:25.468845Z","submitted_at":"2025-06-23T18:17:39Z","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation"},"reference_resolution":{"displayed":94,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":0,"verified_fuzzy":65},"total_outbound_references":94},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 1 inbound Pith citation observation for arXiv:2506.19022."}