{"as_of":"2026-08-12T13:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9d8af9220b3bc75f0c2ea1c00eeb4c8274543de1529e8d95443bc01ded1d6bbc","coverage":[{"denominator":83,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":83,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:50:16.673913Z","state":"measured"},{"denominator":83,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":83,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2501.03782/citation-record","integrity":"/paper/2501.03782/integrity","json":"/paper/2501.03782/citation-record.json","paper":"/paper/2501.03782"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-10T01:12:16.468283Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-10T21:50:16.219508Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.219508Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:17afa1a3b96ee53c69cb3ac4599c468e93fce56c9ace0e9fcc85c911d8dd9482","observation_id":"dda057f2-b555-46e6-88a2-0d466bdb7f73","resolution":{"observed_at":"2026-08-10T21:50:16.219508Z","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":"2026-08-10T21:50:16.227268Z","title":"Maxvit: Multi-axis vision transformer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.227268Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:470d8a60b3fcc19aa8acc2890b95068aff2bf8e7ef1ae6e14daee3b45effc0c7","observation_id":"eff23acc-b53b-44ca-aea1-fc3e53ccc33e","resolution":{"observed_at":"2026-08-10T21:50:16.227268Z","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":"2026-08-10T21:50:16.234330Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.234330Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:5a01d4ab6b2884c4d329bf8fe58d6c465d77d1323ba769c8eecfecf953554d2e","observation_id":"e8138482-d2e9-49e9-a492-678f3879cc10","resolution":{"observed_at":"2026-08-10T21:50:16.234330Z","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":"2026-08-10T21:50:16.240435Z","title":"Exploring plain vision transformer backbones for object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.240435Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:ba2b3261708f1ea20a7f600b9d9f666f48d550abe73b0f481c674f74ecbc522d","observation_id":"4852ba62-e124-44fa-8dfe-9dd4607673c4","resolution":{"observed_at":"2026-08-10T21:50:16.240435Z","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":"2026-08-10T21:50:21.074763Z","title":"Segvit: Semantic segmentation with plain vision transformers.Advances in Neural Information Processing Systems, 35:4971– 4982, 2022","venue":null,"work_id":"e17e9f57-9eea-4122-9875-9e9b213e4001","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.245365Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:879e60c9acf7f261de54ea6736076f6a2606d7f877b8ecba7c78aebe440c3066","observation_id":"e19124bf-dd13-4476-820e-92c494f8be46","resolution":{"observed_at":"2026-08-10T21:50:21.114779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.961493Z","title":"Autoformer: Searching transformers for visual recognition","venue":null,"work_id":"0470535f-9120-4724-ad42-5a67a4694c9f","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.250849Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:cb059105485c57fbf316cf21d6292efd3d39456326e154d7bb765fedb863ad1c","observation_id":"3b676842-4448-4531-8737-68fb8b899845","resolution":{"observed_at":"2026-08-10T21:50:20.996917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.841264Z","title":"Prenas: Preferred one-shot learning towards efficient neural architecture search","venue":null,"work_id":"06800155-8e1f-4b1d-bc30-7789e1012ad6","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.255903Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:aa8ea1bc7b944ec2993323e780b597d0d6f1f0e4cd626867ebd3a051767519c4","observation_id":"bedc928b-dbe3-4819-8007-b5381849a705","resolution":{"observed_at":"2026-08-10T21:50:20.864880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.741676Z","title":"Vitas: Vision transformer architecture search","venue":null,"work_id":"4d7a463a-14b5-4168-a587-764dbce0504b","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.261218Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:830c9625d3d637611fc5acffa91d4d67168788bdaaf5a2695e21e5847813c575","observation_id":"a5bc895b-fb10-4921-8040-673d26032db2","resolution":{"observed_at":"2026-08-10T21:50:20.757130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.691203Z","title":"Elasticvit: Conflict-aware supernet training for deploying fast vision transformer on diverse mobile devices","venue":null,"work_id":"96cdbfed-7d12-4b8c-899e-68d126d8e5f6","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.266462Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:f948fbb5592d496b26ff1a0f0bc66ac79b04d43325a9c3748d7f6146a0334616","observation_id":"efebd209-1ab8-46c9-8d1e-23df2c05dd73","resolution":{"observed_at":"2026-08-10T21:50:20.712744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.554760Z","title":"Training-free transformer architecture search","venue":null,"work_id":"e821d008-1b7b-464b-a1bb-ed645cceaf9e","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.274833Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:b8b53f46df9bde078ed5ea4bfa3129db9d28032ba68513ca6a9ad02711bb871b","observation_id":"7cbdcf7b-e1e0-4bb7-8934-6c6d64e7304f","resolution":{"observed_at":"2026-08-10T21:50:20.597320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.464753Z","title":"Training-free transformer architecture search with zero-cost proxy guided evolution","venue":null,"work_id":"ea9fde7a-21bd-49d8-81e5-31ab57447d49","year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.279703Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:625ceae2979c5b8dc5b5cbc822bf98b407231de1fe0e221c73418c77d84e54ab","observation_id":"3e9904df-59e3-48c3-b529-2ceabe4bb7fb","resolution":{"observed_at":"2026-08-10T21:50:20.482671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.401801Z","title":"Nasvit: Neural architecture search for efficient vision transformers with gradient conflict-aware supernet training","venue":null,"work_id":"1924bbac-695e-4dc8-aec4-48d7c4cd6dc9","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.284496Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:8b800551a081a3917489e90b7af7a8d610259773abeed453c4637c1f6ad6da92","observation_id":"c63ce24a-4248-4994-8bb6-fb607c067a25","resolution":{"observed_at":"2026-08-10T21:50:20.407661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.350132Z","title":"Understanding Robustness of Transformers for Image Classification","venue":null,"work_id":"ab08d019-0603-451f-90d4-d8825bd4808b","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.289482Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:3d686fb4d270ec1998ed14bf66f13f70827806ffe53f1bef9a7e42a8eecd4e50","observation_id":"41a81093-0b82-4418-8bf4-9d040d662dd0","resolution":{"observed_at":"2026-08-10T21:50:20.355760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05211","last_updated":"2022-01-14T03:19:06Z","snapshot_observed_at":"2026-08-11T07:47:58.054053Z","submitted_at":"2021-09-11T08:01:14Z","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05211","snapshot_observed_at":"2026-08-10T21:50:16.294198Z","title":"Robustart: Benchmarking robustness on architecture design and training techniques","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.294198Z"},"links":{"cited_paper":"/paper/2109.05211","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:890b4d9b94211c56b75ac432a549dc171e75145299fcab733ad105e0dee42954","observation_id":"e8a91d09-f1c4-4921-a14c-fbfb42a3169b","resolution":{"observed_at":"2026-08-10T21:50:16.294198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.10750","last_updated":"2023-10-08T22:01:52Z","snapshot_observed_at":"2026-07-06T14:44:38.168186Z","submitted_at":"2023-01-25T18:14:49Z","title":"Out of Distribution Performance of State of Art Vision Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.10750","snapshot_observed_at":"2026-08-10T21:50:16.299891Z","title":"Out of distribution performance of state of art vision model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.299891Z"},"links":{"cited_paper":"/paper/2301.10750","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:3ea92bfc880098b85442d34d956bfd4f374d191ce45c6728f6c705aa40069ce2","observation_id":"41630af0-c157-4a13-b4a7-a8ef771b1364","resolution":{"observed_at":"2026-08-10T21:50:16.299891Z","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":"2026-08-10T21:50:20.333622Z","title":"Searching the search space of vision transformer","venue":null,"work_id":"653013e2-1eda-487d-958a-0814bd94606c","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.305355Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:78d99e6cfa67ae8a18c83f89af77bc0639b2876949de9057e5eeec219a5c9da6","observation_id":"813780c7-754b-443a-a286-d43517115a62","resolution":{"observed_at":"2026-08-10T21:50:20.338503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.283788Z","title":"Auto-prox: Training-free vision transformer architecture search via automatic proxy discovery","venue":null,"work_id":"8b0d5df3-aa6b-4214-ad3c-7e4c227a3e52","year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.309950Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:5d742e720cafcdb5c46bd753ba2347309f5b48d333dbcba6a6ea8684e57cbd87","observation_id":"e4afe3de-2464-4c0e-a803-0621076d6514","resolution":{"observed_at":"2026-08-10T21:50:20.304757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.194832Z","title":"Hr-nas: Searching efficient high-resolution neural architectures with lightweight transformers","venue":null,"work_id":"04e2216a-eb30-4796-9b2b-7519b623d985","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.314748Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:53fb62fb89b8f19d89042490e66a2431faddffd18a3784ede7a73b5492b92ded","observation_id":"041367de-f1de-4be5-aed4-c5e4621cde88","resolution":{"observed_at":"2026-08-10T21:50:20.221506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.127013Z","title":"Uninet: Unified architecture search with convolution, transformer, and mlp","venue":null,"work_id":"79b901dc-a585-4630-91d7-f4ea3f117463","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.320177Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:0d49247b82d2e17fdf98338e8e9792ec26199a85d01d77d32489a2289b47b762","observation_id":"d3261a22-aa2b-418e-92a4-348b2588a77a","resolution":{"observed_at":"2026-08-10T21:50:20.132243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:20.042899Z","title":"Bignas: Scaling up neural architecture search with big single-stage models","venue":null,"work_id":"9b5b34d4-de03-4447-9f02-1cb85207bc40","year":2020},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.326488Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2f99c9489d46fa3f573c5f6740c234b080449f447d58d101bf741e92d8f111a8","observation_id":"f8798990-757e-4e3a-8f79-44dd538f1348","resolution":{"observed_at":"2026-08-10T21:50:20.093471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.944748Z","title":"All tokens matter: Token labeling for training better vision transformers","venue":null,"work_id":"edd1d00b-916a-4324-a7b2-77c3a1ea80c6","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.331505Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:01c98c5bef12902f18a70971c6e22a5eb6be897b469221f779178689954104e6","observation_id":"5d3f950c-cb3a-4e15-a827-65c00f19797f","resolution":{"observed_at":"2026-08-10T21:50:19.973926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.794752Z","title":"Crossvit: Cross-attention multi-scale vision transformer for image classification","venue":null,"work_id":"cf93d46f-94a7-4462-ab29-e18472728cb2","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.337975Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:55d4f74454eaec7918fb00f641f732193ec2e46bb981ab044666650b5e8b8e92","observation_id":"204eed73-574c-40cc-8006-272749084177","resolution":{"observed_at":"2026-08-10T21:50:19.834755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.616964Z","title":"Pre-trained image processing transformer","venue":null,"work_id":"42097cb2-a84c-4de1-8a98-d8f929e6f3ab","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.346443Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:4e496bad085b265545542686b2b56a78953e5e8bae039e1a27fedcf4225284fe","observation_id":"3c2f6af6-dc51-41bb-bed6-ca063ca99a20","resolution":{"observed_at":"2026-08-10T21:50:19.674755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.12261","last_updated":"2019-03-28T20:56:37Z","snapshot_observed_at":"2026-08-09T13:36:49.416146Z","submitted_at":"2019-03-28T20:56:37Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.12261","snapshot_observed_at":"2026-08-10T21:50:16.352204Z","title":"Benchmarking neural network robustness to common corruptions and perturbations","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.352204Z"},"links":{"cited_paper":"/paper/1903.12261","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:e6878821c80356019644759c283aef42363077aa53c11ed86c78210f70084254","observation_id":"dc41278a-f203-4abe-9b5e-4ec5c7e68349","resolution":{"observed_at":"2026-08-10T21:50:16.352204Z","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":"2026-08-10T21:50:16.357201Z","title":"Natural adversarial examples","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.357201Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:01e371eb22932c0347e842157b07f637d61e630ed0b9a2dafa7aac4d244aa0ad","observation_id":"9740dcaf-0109-4894-911c-482a8208822c","resolution":{"observed_at":"2026-08-10T21:50:16.357201Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18775","last_updated":"2024-03-27T17:23:39Z","snapshot_observed_at":"2026-07-06T17:52:05.486230Z","submitted_at":"2024-03-27T17:23:39Z","title":"ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18775","snapshot_observed_at":"2026-08-10T21:50:16.362830Z","title":"Imagenet-d: Benchmarking neural network robustness on diffusion synthetic object","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.362830Z"},"links":{"cited_paper":"/paper/2403.18775","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:f54c1efd3c9d69b157c606662c864b95b6a5c8007679218d81d45bbf7e246ca5","observation_id":"3858147f-7060-4892-ac81-d095f7827a5e","resolution":{"observed_at":"2026-08-10T21:50:16.362830Z","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":"2026-08-10T21:50:16.368894Z","title":"The many faces of robustness: A critical analysis of out-of-distribution generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.368894Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:758bce2c719a338386dc3c24a7a730aefdbfde99d2edb62903f5e653c985fd99","observation_id":"9149b650-eb33-425c-915c-c54d6e10d5f4","resolution":{"observed_at":"2026-08-10T21:50:16.368894Z","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":"2026-08-10T21:50:16.374814Z","title":"Learning robust global representations by penalizing local predictive power","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.374814Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:e221266e8a6d5a4de228d605e6a3602153b80d6420b0a5b1662482d9f1ff66f2","observation_id":"35075d6f-8f8d-4958-a492-fc6ec6ce37b1","resolution":{"observed_at":"2026-08-10T21:50:16.374814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12231","last_updated":"2022-11-09T23:15:15Z","snapshot_observed_at":"2026-08-02T03:51:09.933624Z","submitted_at":"2018-11-29T15:04:05Z","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.12231","snapshot_observed_at":"2026-08-10T21:50:16.380516Z","title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.380516Z"},"links":{"cited_paper":"/paper/1811.12231","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:658246d64ef9932c118a73ed1fbfb244766f25c90b306a54b5db6d87060caa0e","observation_id":"c1caff34-4ba6-4e99-9835-1a029bc5acba","resolution":{"observed_at":"2026-08-10T21:50:16.380516Z","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":"2026-08-10T21:50:19.444845Z","title":"HYPO: Hyperspherical out-of-distribution generalization","venue":null,"work_id":"8d4e16e1-1c4c-4bcb-8151-374315b18126","year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.385574Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:df2b90e62cb047f1a546762710292ba05a74369796642c1ae99b0828b89a0a46","observation_id":"3923e7c0-c1b0-47b8-94af-045b33d2c0c8","resolution":{"observed_at":"2026-08-10T21:50:19.463977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02893","last_updated":"2020-03-27T19:07:58Z","snapshot_observed_at":"2026-07-06T08:05:24.076802Z","submitted_at":"2019-07-05T15:26:26Z","title":"Invariant Risk Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02893","snapshot_observed_at":"2026-08-10T21:50:16.390677Z","title":"Invariant risk minimization","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.390677Z"},"links":{"cited_paper":"/paper/1907.02893","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:ba9c761d315f77db41b20493646f14c35d8893c413904a6d62081e1aaa9e0304","observation_id":"520ea0b8-69b5-4386-93fc-2fdb652dbb8f","resolution":{"observed_at":"2026-08-10T21:50:16.390677Z","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":"2026-08-10T21:50:19.382618Z","title":"Domain generalization for object recognition with multi-task autoencoders","venue":null,"work_id":"26ff5a29-fd41-46c2-bfdf-8c496c563f93","year":2015},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.395431Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:11fc7929fa0b7b26ac81f87537efc3a43778eb9f3f06aaf0f30029ca1e2a211e","observation_id":"13cd17ab-06e6-4362-b7d5-30253e478083","resolution":{"observed_at":"2026-08-10T21:50:19.398350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.367058Z","title":"Domain generalization using causal matching","venue":null,"work_id":"ae85c4f3-a266-409a-ae7f-34d5f8a50917","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.400220Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:ac54d4d76eef169b67acb01a3c5df4018035767d15fe8fcb0e838e2975b0d09c","observation_id":"5173e668-3ba9-4e68-950e-83e4051330ba","resolution":{"observed_at":"2026-08-10T21:50:19.371581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.339666Z","title":"Domain generalization via invariant feature representation","venue":null,"work_id":"4e5036b5-2ef9-4c07-afd8-8068a9575d09","year":2013},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.404508Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2ff53cc5358e7120dcc3bf6adfe1fad210061d06daa0fc477fdfa20888048afe","observation_id":"a77b59ee-a555-4f00-87bf-f48701d04dd6","resolution":{"observed_at":"2026-08-10T21:50:19.351314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.314236Z","title":"Fishr: Invariant gradient variances for out-of- distribution generalization","venue":null,"work_id":"c6c97b71-6422-4ff8-8651-b7c29e68bdf7","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.410540Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:51ed273c5a1c7b96924cb6914dbb5f85f24f27a4a67f7c5eb67538b771336150","observation_id":"ac9c4dd8-750b-4d56-ab68-8cdc7740404a","resolution":{"observed_at":"2026-08-10T21:50:19.326399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.267167Z","title":"Invariant models for causal transfer learning","venue":null,"work_id":"8c6bea6f-7dfe-4fe0-927c-471ac4332983","year":2018},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.415846Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:932052388951cfe65468b5b4cf0456ecbc45fc1045676f2f789e554c49831250","observation_id":"e09058fe-07f4-42f7-ba9f-7f13943ad77c","resolution":{"observed_at":"2026-08-10T21:50:19.281518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09937","last_updated":"2021-07-14T00:07:51Z","snapshot_observed_at":"2026-08-06T20:03:26.839485Z","submitted_at":"2021-04-20T12:55:37Z","title":"Gradient Matching for Domain Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09937","snapshot_observed_at":"2026-08-10T21:50:16.421275Z","title":"Gradient matching for domain generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.421275Z"},"links":{"cited_paper":"/paper/2104.09937","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:a8e95958c5400b55803230ff6cf00ba18ea4d1243f988961f1506418f5ccba3c","observation_id":"4fcb05eb-28ff-432b-8c7c-445dd8ac7b50","resolution":{"observed_at":"2026-08-10T21:50:16.421275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.08731","last_updated":"2020-04-02T05:40:29Z","snapshot_observed_at":"2026-08-02T19:28:48.954133Z","submitted_at":"2019-11-20T06:43:41Z","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.08731","snapshot_observed_at":"2026-08-10T21:50:16.427738Z","title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization.arXiv preprint arXiv:1911.08731, 2019","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.427738Z"},"links":{"cited_paper":"/paper/1911.08731","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:94c87886be4b0dbe03ad21e25a8e8ff436fa1f7f3630d728bcf4817b54baf061","observation_id":"64a4f131-b804-4314-aed1-105d8e277f20","resolution":{"observed_at":"2026-08-10T21:50:16.427738Z","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":"2026-08-10T21:50:19.164750Z","title":"Learning to generate novel domains for domain generalization","venue":null,"work_id":"4d4f819e-2c4f-4ba2-9968-d8d4d0ea07f9","year":2020},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.435250Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:f255d0452a7fb98d5a79e4ed9f8300aa2c187c1c97cf4807f0dbde87c012e560","observation_id":"e59e9aea-f456-4872-ac93-00067df16d30","resolution":{"observed_at":"2026-08-10T21:50:19.191392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.125224Z","title":"Explore and exploit the diverse knowledge in model zoo for domain generalization","venue":null,"work_id":"1889cb8a-47f8-4408-becc-ce81a57a81a7","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.441627Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:3edc37f4f2dc1a1aa7c1d808eeb8a93abace2eb67b7ec68a0a7f2e4d1e7107cd","observation_id":"d4a237f0-01eb-4a6b-a412-e9ea124338a4","resolution":{"observed_at":"2026-08-10T21:50:19.130570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.102899Z","title":"Model ratatouille: Recycling diverse models for out-of-distribution generalization","venue":null,"work_id":"ba65a5c1-c294-447b-ba8e-bff241bc9ce5","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.446763Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:f7e15a50093d7a203c73bd72923baa79287dbf19aff098bb00b5348b6744be2f","observation_id":"61ccb511-afc3-4d75-bd0e-003d817df51c","resolution":{"observed_at":"2026-08-10T21:50:19.109049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:19.075709Z","title":"Test-time style shifting: Handling arbitrary styles in domain generalization","venue":null,"work_id":"0bd58f96-6ab4-4ed9-ac25-3b3d37c82ee8","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.451893Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:bd9d346fe0dda52b6d503653b774b6b48dba9c69d519b9f8cb8ace9a90d21fbc","observation_id":"fe8965fd-5fe5-43ce-8052-bad7dcb3909c","resolution":{"observed_at":"2026-08-10T21:50:19.082348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:16.458072Z","title":"Improved test-time adaptation for domain generalization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.458072Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:8634f0a15a8de29c503e4405b6a645a4ab267c33b81c6a505c5508267748d6c1","observation_id":"678e0f9b-99ac-4a05-b128-1fa6f2aeabf8","resolution":{"observed_at":"2026-08-10T21:50:16.458072Z","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":"2026-08-10T21:50:16.462585Z","title":"Reducing domain gap by reducing style bias","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.462585Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:a508a05db797065c77e4601e33406d94224914d7cad0da93ca9cc2ce45260103","observation_id":"918955a9-7bc3-4d72-ae9a-465eda3c2921","resolution":{"observed_at":"2026-08-10T21:50:16.462585Z","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":"2026-08-10T21:50:18.955110Z","title":"Self-supervised learning of adversarial example: Towards good generalizations for deepfake detection","venue":null,"work_id":"57fafcc9-4410-455f-9dc5-7807e592fb3a","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.467298Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:266b222ee9e426e3c02f17c1f5522f98b1fbdbe6bb38e2a2d573def02c8dc22d","observation_id":"fd018d75-e760-4f75-a481-c9deb0617251","resolution":{"observed_at":"2026-08-10T21:50:18.968303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.860686Z","title":"Selfreg: Self-supervised contrastive regularization for domain generalization","venue":null,"work_id":"0e15c78a-8dbd-4a18-a6c5-5803225f279b","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.472774Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2ae385aa5058ab19258b72ea1079f17d57c913ab0b7fb52f62ef05b0baa03b8b","observation_id":"fec33ed6-f147-4fbb-b104-3f325ee3e536","resolution":{"observed_at":"2026-08-10T21:50:18.884151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.814781Z","title":"A simple feature augmentation for domain generalization","venue":null,"work_id":"a57e9280-b0a3-4132-85f3-53f98a236793","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.477826Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2bb8a6a7aeb015128fe222c7aa95d4b281d1cb7666ee9e10dd630d81b3e9b5e2","observation_id":"9ba011f3-b161-4663-af04-54818e093903","resolution":{"observed_at":"2026-08-10T21:50:18.824632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.02008","last_updated":"2021-04-05T16:58:09Z","snapshot_observed_at":"2026-08-10T09:28:28.538323Z","submitted_at":"2021-04-05T16:58:09Z","title":"Domain Generalization with MixStyle","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.02008","snapshot_observed_at":"2026-08-10T21:50:16.482936Z","title":"Domain generalization with mixstyle","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.482936Z"},"links":{"cited_paper":"/paper/2104.02008","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:a9d9fcd6d6ac53ea0adfeb0be0910314ee42f5eeffccb1e6e51e7f42d4d37777","observation_id":"f1a36dbb-159a-4adc-a879-54db82f3267e","resolution":{"observed_at":"2026-08-10T21:50:16.482936Z","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":"2026-08-10T21:50:16.488447Z","title":"A fourier-based framework for domain generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.488447Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:e3de00382d4fd0a223003e1abf4d139f2c2e49359a88a7f866d21c2941e2e074","observation_id":"a43975b7-6cb4-464a-95e3-a94aa14fd60e","resolution":{"observed_at":"2026-08-10T21:50:16.488447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.00677","last_updated":"2020-01-03T01:21:27Z","snapshot_observed_at":"2026-08-11T21:33:20.628406Z","submitted_at":"2020-01-03T01:21:27Z","title":"Improve Unsupervised Domain Adaptation with Mixup Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.00677","snapshot_observed_at":"2026-08-10T21:50:16.500817Z","title":"Improve unsupervised domain adaptation with mixup training","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.500817Z"},"links":{"cited_paper":"/paper/2001.00677","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:d0885734c0de338b1f9cce9c3fa439f1aef6d1f003462564c3b17b3695e2353c","observation_id":"e0e6b428-4222-47fd-a98f-32dc0ddafc23","resolution":{"observed_at":"2026-08-10T21:50:16.500817Z","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":"2026-08-10T21:50:18.728681Z","title":"Metanorm: Learning to normalize few-shot batches across domains","venue":null,"work_id":"45cc74ca-b57a-42fe-b325-e308cab5be08","year":2020},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.505632Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:63b3bef72ac7b006625da73cfe20b5dd7fc1d7dffda7d8745faef6ee891a5f0a","observation_id":"39dab15f-17ca-4b94-be78-3bc3e98edf68","resolution":{"observed_at":"2026-08-10T21:50:18.739430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.648674Z","title":"Open domain generalization with domain-augmented meta-learning","venue":null,"work_id":"9746bef5-44d6-4cdc-8803-2135d70dbd71","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.510163Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:6a693e90d203a2748bad0641d195e7479149a974458c65f28ad1a20e95d741eb","observation_id":"eacbb832-1000-46cc-859e-be0dede24aff","resolution":{"observed_at":"2026-08-10T21:50:18.668328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.537698Z","title":"An investigation of why overparam- eterization exacerbates spurious correlations","venue":null,"work_id":"7e171094-84e1-4463-b7fd-51ed800571b5","year":2020},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.515066Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:b88cf521e7efa5b6824d06efa30abfc3497d9197dc3e8a7e5fe5c2b55db5942e","observation_id":"dc047e47-a193-4468-90c7-8e5470036204","resolution":{"observed_at":"2026-08-10T21:50:18.563945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-05T23:54:27.386622Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-10T21:50:16.519800Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.519800Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:7ac2da57c6d07ab75367e62885c2a53655d4f571cb43c97c6d7f2b0dea7ea25f","observation_id":"97bd634f-2d01-4648-8b0b-f766d687a267","resolution":{"observed_at":"2026-08-10T21:50:16.519800Z","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":"2026-08-10T21:50:18.514501Z","title":"Can subnetwork structure be the key to out-of-distribution generalization? In International Conference on Machine Learning, pages 12356–12367","venue":null,"work_id":"05b86482-3eba-47a8-82d7-bccb3ec530a8","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.524602Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:376605d3a461f515149904c38e5ee3e502f9affb67d094f44f892b1291fc4534","observation_id":"46da0219-b39e-44ba-8c7e-6d199e5b9f6f","resolution":{"observed_at":"2026-08-10T21:50:18.527143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.438774Z","title":"Training debiased subnetworks with contrastive weight pruning","venue":null,"work_id":"c74edaef-5366-4ccb-9041-35454d531d5c","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.529140Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:487bcd75c69b4baf9de179583d39451731d27c889bd421c26541504f3d1c8aa4","observation_id":"de06ca7d-4348-4337-86a9-d6837dcd110d","resolution":{"observed_at":"2026-08-10T21:50:18.473559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.391734Z","title":"Nas- ood: Neural architecture search for out-of-distribution generalization","venue":null,"work_id":"009b720a-d5b7-4963-b991-6e719be9164b","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.533447Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:35436f7dc3fe6b44a13f493c9737293769a34fcb910da768a565e839731324d9","observation_id":"41bfd4a9-e13e-42e6-b512-6190e3830d1a","resolution":{"observed_at":"2026-08-10T21:50:18.405620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.373131Z","title":"Alphanet: Improved training of supernets with alpha-divergence","venue":null,"work_id":"914df7d8-452c-4546-9aaa-2a9a6cc23454","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.538645Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:c0212b47507235d9982433ff996fb69ab2ce130dcd56b760cb750446800e895a","observation_id":"3e8915f9-8bda-4de3-8802-6f3071392a10","resolution":{"observed_at":"2026-08-10T21:50:18.379488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.338155Z","title":"Attentivenas: Improving neural architecture search via attentive sampling","venue":null,"work_id":"35f18628-48a3-4de4-b696-eac3ca985f0b","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.543814Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:4ced64860b1ee1ae158de27d871a217faeae649e5a0615b4f1cf4343dd133f40","observation_id":"75e33383-0b21-4edf-812a-fac304ef9edd","resolution":{"observed_at":"2026-08-10T21:50:18.344954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.314525Z","title":"Meco: Zero-shot nas with one data and single forward pass via minimum eigenvalue of correlation","venue":null,"work_id":"b874e116-e4df-4275-999b-c6543da3fa18","year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.548816Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:b88876589d114b611cc9c3c67a3294a43643cc5b8aae163a79b3f6c161045116","observation_id":"a7cdc349-2461-423d-bcf5-3afd832fce9b","resolution":{"observed_at":"2026-08-10T21:50:18.321183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.06712","last_updated":"2023-06-11T16:02:14Z","snapshot_observed_at":"2026-07-06T15:41:16.963249Z","submitted_at":"2023-06-11T16:02:14Z","title":"Neural Architecture Design and Robustness: A Dataset","version":1},"cited_work":{"arxiv_id":"2306.06712","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.06712","snapshot_observed_at":"2026-08-10T21:50:16.801497Z","title":"Neural Architecture Design and Robustness: A Dataset","venue":"cs.LG","work_id":"b0634496-1c6b-4c76-9b1b-7375b51bb30e","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.553437Z"},"links":{"cited_paper":"/paper/2306.06712","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:7e8dd0467c0e91acebdf2979c9eb03c09106454abf8095258ced5afc2437d945","observation_id":"dff86e3a-05fc-4141-9e56-a513fd675bee","resolution":{"observed_at":"2026-08-10T21:50:16.808740Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.295897Z","title":"Generalizable lightweight proxy for robust nas against diverse perturbations","venue":null,"work_id":"baf7952f-19b4-43a3-a2ea-a6749d5cef1c","year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.557967Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2f56546678115aba2475e1f3336fd2307c626ec34780796fc4edaf937ba56d78","observation_id":"97e3dd1c-e099-4dad-a74b-1e0a8e04a603","resolution":{"observed_at":"2026-08-10T21:50:18.300945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13134","last_updated":"2024-03-19T20:10:23Z","snapshot_observed_at":"2026-07-06T17:47:22.458338Z","submitted_at":"2024-03-19T20:10:23Z","title":"Robust NAS under adversarial training: benchmark, theory, and beyond","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13134","snapshot_observed_at":"2026-08-10T21:50:16.566292Z","title":"Robust nas under adversarial training: benchmark, theory, and beyond","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.566292Z"},"links":{"cited_paper":"/paper/2403.13134","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2d61cdea383603aa3608564f4ad97d4bea4145bf2dd9b05128c2cb5176e7f71f","observation_id":"cea55928-a9d6-4144-9980-b499bc453e98","resolution":{"observed_at":"2026-08-10T21:50:16.566292Z","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":"2026-08-10T21:50:18.269701Z","title":"Glit: Neural architecture search for global and local image transformer","venue":null,"work_id":"19604055-3021-4844-a8dc-7b6bd106cb2e","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.571526Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:761c4eade254f1d5a3ba3174e58ef54391351cb4a3a566caf8087f90bfdfd41b","observation_id":"46589c51-c460-4303-9dff-54a269e3cce1","resolution":{"observed_at":"2026-08-10T21:50:18.275690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.221705Z","title":"Shiftnas: Improving one-shot nas via probability shift","venue":null,"work_id":"60e06698-bffa-47eb-bc79-bbbd761b8386","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.576151Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:ba3463fd27dff06ef83233055925943ad70068d674539b9a27a14ec601a22bfa","observation_id":"0ed26918-2914-4316-bb4c-a21aad362313","resolution":{"observed_at":"2026-08-10T21:50:18.231187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.195568Z","title":"Mdl-nas: A joint multi-domain learning framework for vision transformer","venue":null,"work_id":"e5324294-4c2c-4f9e-8fc1-71eecb27c719","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.580719Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:878d70e52693d4e57dc9edb42f31ae697709c8b9801586da9cd0f764414ce6fb","observation_id":"5001420d-40f4-406b-93f8-6916b072ccdf","resolution":{"observed_at":"2026-08-10T21:50:18.204982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.172968Z","title":"Efficient multimodal fusion via interactive prompting","venue":null,"work_id":"7f5bd22c-18b7-4009-b1b5-0b7596553291","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.585560Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:8f19cd11a6363dd2b799bef44048b4b7cc61d13a857f97c3e79f010a9bdff22e","observation_id":"032aca59-8501-4b29-a763-be1818d8e16c","resolution":{"observed_at":"2026-08-10T21:50:18.179442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:16.591737Z","title":"Imagenet: Constructing a large-scale image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.591737Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:f866b335ded55dbde64f817384bf07af4ea624675992d1b74a2cbfd1b87e153c","observation_id":"f0ce1b3d-a40d-4687-8e50-33006514b136","resolution":{"observed_at":"2026-08-10T21:50:16.591737Z","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":"2026-08-10T21:50:18.123114Z","title":"Accuracy on the line: on the strong correlation between out-of- distribution and in-distribution generalization","venue":null,"work_id":"2944e084-dfbf-4158-820f-93fab0329db5","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.596496Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:e1e3cd64b2126fc6db054a6fca871ab06f2e5884b561524d54ed263fbc062e22","observation_id":"46778190-6ce2-4f03-965a-dbbf338a897e","resolution":{"observed_at":"2026-08-10T21:50:18.128319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.106687Z","title":null,"venue":null,"work_id":"fe007c8e-1670-49ad-b6f8-355dc41fffbb","year":2019},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.601475Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:a7b0a8928b276c059f60791875a6526915b5a9ee52892bf03c7b438027370522","observation_id":"1ba4234a-2064-48d2-b194-4a6289e17607","resolution":{"observed_at":"2026-08-10T21:50:18.111577Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.080563Z","title":"Id and ood performance are sometimes inversely correlated on real-world datasets","venue":null,"work_id":"34e1849a-1340-4047-8f64-a42088040daa","year":2023},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.605962Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:fb7b92db5f2d8d29a12f2ca496dadb08c1c3b11f2a1f8f0304e9bec0ceb9bac7","observation_id":"5022a401-9088-4ed2-bc96-3caef119be75","resolution":{"observed_at":"2026-08-10T21:50:18.085540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:18.059372Z","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","venue":null,"work_id":"c9e9ee0e-5a9f-4efc-a7e0-76784cc69133","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.610012Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:00449cf969ac8441c294258b9ff20ca0479044f1d4521a72518663f12de60f15","observation_id":"3e4ffce9-73b2-47bc-8363-2d7441b82cbf","resolution":{"observed_at":"2026-08-10T21:50:18.068625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02340","last_updated":"2019-02-23T07:45:29Z","snapshot_observed_at":"2026-07-06T07:06:10.289386Z","submitted_at":"2018-10-04T17:39:58Z","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02340","snapshot_observed_at":"2026-08-10T21:50:16.614326Z","title":"Snip: Single-shot network pruning based on connection sensitivity","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.614326Z"},"links":{"cited_paper":"/paper/1810.02340","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:330a264e467e3760028d87cc3fa5a84e2a250332d30334de2f6eb450ba7cb58b","observation_id":"95da7d7f-11a7-4077-a25e-de50ba064fab","resolution":{"observed_at":"2026-08-10T21:50:16.614326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-10T04:53:00.900945Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-10T21:50:16.620550Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.620550Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:6007cfa510780694541f130413190139606ba9e3ebfe3838da9f128730af2ac7","observation_id":"eacf90a0-9af4-4706-a989-d6cc9d384976","resolution":{"observed_at":"2026-08-10T21:50:16.620550Z","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":"2026-08-10T21:50:17.997877Z","title":"Dsrna: Differentiable search of robust neural architectures","venue":null,"work_id":"0a9cae85-4d52-4e94-a1b4-6afdcac27aeb","year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.625483Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:59624867d061f465f4716c01e5f9b6c70892d1af00afbcf2217fdd3519c3996b","observation_id":"5f578d16-e189-412f-ae10-d8d54fa35405","resolution":{"observed_at":"2026-08-10T21:50:18.025700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:16.629835Z","title":"A new measure of rank correlation","venue":null,"work_id":null,"year":1938},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.629835Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:1fa4f4f87f83e27ccf5de6ff0617829ca7de10bbc6082218ba3fd5baa5526172","observation_id":"8a61f717-92d7-49dc-b0fd-ad2f57bb6adf","resolution":{"observed_at":"2026-08-10T21:50:16.629835Z","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":"2026-08-10T21:50:17.884858Z","title":"Improving vision transform- ers by revisiting high-frequency components","venue":null,"work_id":"8358e236-0ecf-4848-a0a9-65f1dab4bfa2","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.634752Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2c3a74e5e3c5115814915758f6ef825934ae3313cbcb011697abbde1a76afb38","observation_id":"a9e5173c-a7d4-472f-8d30-b6896a41130c","resolution":{"observed_at":"2026-08-10T21:50:17.924761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.15670","last_updated":"2022-11-02T18:57:19Z","snapshot_observed_at":"2026-08-08T22:57:45.855434Z","submitted_at":"2021-03-29T14:48:24Z","title":"On the Adversarial Robustness of Vision Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.15670","snapshot_observed_at":"2026-08-10T21:50:16.644689Z","title":"On the adversarial robustness of vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.644689Z"},"links":{"cited_paper":"/paper/2103.15670","citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:bef87756e41f3419ef7a93a90214647ad42bbba03e46786885d03a804034b511","observation_id":"61aebfbf-21b9-405e-8f86-02513cf0fa2a","resolution":{"observed_at":"2026-08-10T21:50:16.644689Z","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":"2026-08-10T21:50:17.811296Z","title":"Can biases in imagenet models explain generalization? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22184–22194, 2024","venue":null,"work_id":"06ed7e1f-9b3d-467f-8b8c-9c8710e29ba1","year":2024},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.649653Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:2bb9046bf9ac61a10f8a510a75eef30057f71ec60e221b23762da119c05e7d99","observation_id":"aa7005ff-c627-459d-ac2c-e9647feeca29","resolution":{"observed_at":"2026-08-10T21:50:17.835816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:17.744751Z","title":"High-frequency component helps explain the generalization of convolutional neural networks","venue":null,"work_id":"7f0ce77d-ec3c-40c0-8e21-58e018d721a4","year":2020},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.655848Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:59684f4d7df3d12832d0db8d5d980b82eaddfa7a0862be2d6802be3d57941aff","observation_id":"ac892f40-5522-4188-912b-1a03918237f5","resolution":{"observed_at":"2026-08-10T21:50:17.774859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:16.660640Z","title":"Arbitrary style transfer in real-time with adaptive instance normalization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.660640Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:3f96c33668be5f497d858a522e124883060362bf27d0d1c80346e460d433e768","observation_id":"8beb5d18-f0f4-4eae-9dd4-3bec116913d4","resolution":{"observed_at":"2026-08-10T21:50:16.660640Z","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":"2026-08-10T21:50:17.554754Z","title":"cat\", \"airplane","venue":null,"work_id":"b7a073bb-f079-4d87-803d-ba28ec883eb4","year":2022},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.667451Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:a992a5ae2284c2a119dca0dedd8787502d6f7092eb1dc5c98098dcc0ca81c271","observation_id":"ca0e1e38-38b0-4173-adb2-666ed1ecda60","resolution":{"observed_at":"2026-08-10T21:50:17.596899Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T21:50:17.508478Z","title":"These examples could be distorted or unrealistic in object- background placements","venue":null,"work_id":"e3c8c822-2517-4a16-84b0-f7ecf3ce4d80","year":null},"citing_paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-10T21:50:16.673913Z"},"links":{"citing_paper":"/paper/2501.03782"},"observation_digest":"sha256:06c08264165c4306a44c89528d1e445c24accf7bebb925e7c7672edfc62cdd58","observation_id":"17be7581-cca3-47b1-9267-1bcd5d439e43","resolution":{"observed_at":"2026-08-10T21:50:17.515277Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.03782","last_updated":"2025-01-07T13:45:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T21:45:10.370048Z","submitted_at":"2025-01-07T13:45:09Z","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights"},"reference_resolution":{"displayed":83,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":1,"verified_fuzzy":51},"total_outbound_references":83},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 83 of 83 outbound references and 0 inbound Pith citation observations for arXiv:2501.03782."}