{"as_of":"2026-08-13T06:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0dd00731153a3bf16618dda2dd21efb47d5b64186d4d276b18b53eb4716876b0","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T13:30:02.423243Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.16788/citation-record","integrity":"/paper/2411.16788/integrity","json":"/paper/2411.16788/citation-record.json","paper":"/paper/2411.16788"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T13:30:03.481972Z","title":"A-star: Test-time attention segregation and retention for text-to-image synthesis","venue":null,"work_id":"bcb69cd8-ef13-43b4-82ef-e4155e3264b9","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.111711Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:4504955931d54160def5068725f6a6d597efa1dced9980204b38ca659d163eaa","observation_id":"5b3070db-41f1-4bc3-93bb-0e2ca7075635","resolution":{"observed_at":"2026-08-12T13:30:03.486851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.465493Z","title":"Language models are few-shot learners","venue":null,"work_id":"2455e803-f831-46a6-88e9-6d02165af31c","year":null},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.117002Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:3eb401a40e0c15cfad3cd474cf4f4c9fb3a9202c3903b783d15f9f13f1757141","observation_id":"91f6a91c-28bd-4290-bd46-dbbae9f3410c","resolution":{"observed_at":"2026-08-12T13:30:03.471056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.450019Z","title":"Attend-and-excite: Attention-based se- mantic guidance for text-to-image diffusion models","venue":null,"work_id":"3c14a0ce-67d4-4136-bb10-6cbbae399d21","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.121752Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:ffeabe2200f4d7def3419a99e147aaf91e1a5188988c78a2fe929dd4c724dc6b","observation_id":"9ede9d6d-136f-4d31-b74b-527b36e8c093","resolution":{"observed_at":"2026-08-12T13:30:03.454979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.434595Z","title":"Meta-causal learning for single domain generalization","venue":null,"work_id":"5d2bc60b-a470-47b4-bad1-8d812fa31cf4","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.127589Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:1c8db5d1bd450f01a73a6e1f6c2bb51a86f67547adf6bfc0bce66ed4ae1bb56c","observation_id":"befc9eac-20e0-47ad-8d22-5aebc25978b1","resolution":{"observed_at":"2026-08-12T13:30:03.439479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.418977Z","title":"Adversar- ial bayesian augmentation for single-source domain gener- alization","venue":null,"work_id":"10d9e0c2-f7af-43c6-8168-c82dd78ea4d3","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.132594Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:0c952532a7d7f017e9e9a8045ded2b1470e1b01fe31b1ba2e4d882b7a2dd6c1d","observation_id":"ec4d34dc-b83d-470e-a14d-3606613d5cfe","resolution":{"observed_at":"2026-08-12T13:30:03.423962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.403058Z","title":"Progressive random con- volutions for single domain generalization","venue":null,"work_id":"0e40a924-5b3d-442b-910a-3e9e65c0b8c8","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.138183Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:4290369eac26f60dd0ab6d8aa57a0b5d1fdb54135f9577d313f3e5644690181d","observation_id":"9d208af0-e1fb-4071-b65f-eef8c8e998db","resolution":{"observed_at":"2026-08-12T13:30:03.408347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.386973Z","title":"Randaugment: Practical automated data augmentation with a reduced search space","venue":null,"work_id":"d654813f-bc16-40bc-99dd-9cb25ae102b4","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.143080Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:3e4a1883b17253318e7585abaaa06c3614d8ed9a878f3016d6262ba7b1618050","observation_id":"31da1848-dc29-4410-8ce5-547adda09d19","resolution":{"observed_at":"2026-08-12T13:30:03.392127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.371038Z","title":"Attention consistency on visual corruptions for single-source domain generalization","venue":null,"work_id":"e0050e06-b061-458c-b563-20c33c81d995","year":2022},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.148539Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:6c602a0e2bded693b7e94baf0a45136549f1b08d9642bfd18d9694220b705483","observation_id":"bbdc2edc-f29d-43ae-9d9e-d79a2390ec70","resolution":{"observed_at":"2026-08-12T13:30:03.375958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.04552","last_updated":"2017-11-29T14:51:40Z","snapshot_observed_at":"2026-08-10T10:31:15.628197Z","submitted_at":"2017-08-15T15:21:53Z","title":"Improved Regularization of Convolutional Neural Networks with Cutout","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.04552","snapshot_observed_at":"2026-08-12T13:30:02.153390Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.153390Z"},"links":{"cited_paper":"/paper/1708.04552","citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:c83244a482039fc8542471050a7228f327725c49f962b4d8ddd2cb132f31cad0","observation_id":"95612466-91ba-4b8b-a623-baf27d933408","resolution":{"observed_at":"2026-08-12T13:30:02.153390Z","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":"2026-08-12T13:30:03.352694Z","title":"Learning to learn with variational information bottleneck for domain gener- alization","venue":null,"work_id":"51b9d6fa-ad4e-48d3-9c57-2d4de84defb8","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.159363Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:a229ebf5487215fc39f2263935641a8d04423513f20e7ee9fd13e76a23b011e8","observation_id":"11a69edb-a5dc-4c42-8acc-7e6ecd21a635","resolution":{"observed_at":"2026-08-12T13:30:03.359406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.334485Z","title":"Domain gener- alization with domain-specific aggregation modules","venue":null,"work_id":"dc0cec47-6bb1-42c7-86be-0a614ed678b1","year":2019},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.163864Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:97a4ac0701ed331a93a9ba52a61a4602536829afc10725b998b40f1ec1fb0866","observation_id":"2473acba-d3f6-460d-888c-675916eb627c","resolution":{"observed_at":"2026-08-12T13:30:03.340152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.317155Z","title":"Adversarially adaptive normalization for single domain generalization","venue":null,"work_id":"466bafb5-276f-4809-94db-c0724fd11494","year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.169185Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:9435533f73ba0c822da1403512da2406744060b621a6711f2500ac56598ea4fd","observation_id":"a6a69e2d-2dde-438b-9562-810eaf5f928c","resolution":{"observed_at":"2026-08-12T13:30:03.322550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.299104Z","title":"Unbiased met- ric learning: On the utilization of multiple datasets and web images for softening bias","venue":null,"work_id":"481413d1-9654-41d5-a7d9-11cdffb7b0be","year":2013},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.173892Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:7465990fba2576ebc8079c54af5783dba5594ea514213f3e7d25c66f29e21ddb","observation_id":"0e7f6d4c-6b6c-49e8-91c3-e802c13982f6","resolution":{"observed_at":"2026-08-12T13:30:03.304883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.282787Z","title":"Imagenet-trained cnns are biased towards texture; increas- ing shape bias improves accuracy and robustness","venue":null,"work_id":"c4b5c4eb-dc4a-494d-9171-cacb45f85091","year":null},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.178566Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:4960c58842b317b0b0b28df8089121b4dff83d54677d68d47c6b9bb9e555f845","observation_id":"60d5fddc-556c-4bed-8fda-f4829319b54d","resolution":{"observed_at":"2026-08-12T13:30:03.287860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.265917Z","title":"Domain generalization for object recog- nition with multi-task autoencoders","venue":null,"work_id":"6a5a8d08-61ad-4a62-aede-21ea2012ca13","year":2015},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.183764Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:9fdb2731e8a2de9299c85a1a21e692b5f5b2d6891526fa56e7b2ccc41bd005f1","observation_id":"279f517d-1590-45a6-9b33-d915da4677f0","resolution":{"observed_at":"2026-08-12T13:30:03.271270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.249316Z","title":"Attribute-guided adversarial training for robustness to nat- ural perturbations","venue":null,"work_id":"f508c66b-3d05-4312-92c4-1c28440f693e","year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.188696Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:24c304ea91dd5820880574c953f319d1fc737fdd9bc641c13158b462ed1e1259","observation_id":"6c02732a-27fa-4b12-add3-1cad19293c60","resolution":{"observed_at":"2026-08-12T13:30:03.254859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.231023Z","title":"In search of lost do- main generalization","venue":null,"work_id":"047fac26-0fc0-4578-b162-ef210067ea2d","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.193416Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:7a664074f61e2869a4a896298da51549e373a85b86ea1e32c92e4a9ee0397c40","observation_id":"e1b6eb0b-2268-468a-ab45-b532484e4aae","resolution":{"observed_at":"2026-08-12T13:30:03.236761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.198195Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.198195Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:fc12b01e2781fc8d3c39f56ecbb92509f625978bcd8cade97643c039321b779a","observation_id":"e942d052-ba38-481d-a62a-b92c8c1f6bec","resolution":{"observed_at":"2026-08-12T13:30:02.198195Z","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":"2026-08-12T13:30:03.203026Z","title":"Augmix: A simple data processing method to improve robustness and uncertainty","venue":null,"work_id":"dc06d214-3e5d-4a66-90d5-e3ad54bb3ac0","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.203112Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:73c4ae222b378ad6e60694dd46f526ac3303518620acdb585c69fa889b47df39","observation_id":"b71f8ca2-7c15-426b-859c-a11a6e31f962","resolution":{"observed_at":"2026-08-12T13:30:03.208112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.185947Z","title":"Pixmix: Dream- like pictures comprehensively improve safety measures","venue":null,"work_id":"1c44fc25-4438-4807-9c89-bfd5b70ece5a","year":2022},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.207787Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:a9446037631f44da08dc48c53b206d78066c99512a2b07aa093e5e671fe16ede","observation_id":"387e2b3c-2d60-4eee-a15e-952eeda29ce1","resolution":{"observed_at":"2026-08-12T13:30:03.191228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.169850Z","title":"Self-challenging improves cross-domain generalization","venue":null,"work_id":"89313936-e676-489e-9b50-0bc82342306e","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.212905Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:ed218b440d867dbde7a98432b2eae04eda4ef9a01e77916ce35649dc860a2f2b","observation_id":"120c0444-42c7-4246-bda6-599b2948b069","resolution":{"observed_at":"2026-08-12T13:30:03.174753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.153147Z","title":"Spatial transformer networks","venue":null,"work_id":"8f54b924-17e7-4a62-89cf-1570a70b9458","year":2015},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.217646Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:137ae63b88049bfd44cacb0f8cc00db2b29c40f8325525b4cd9cc2266e90313c","observation_id":"87de4f6c-ccae-4349-bb4e-b55dbc62a5da","resolution":{"observed_at":"2026-08-12T13:30:03.158390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.136874Z","title":"Concept bottleneck models","venue":null,"work_id":"e71e5293-e3d4-4af6-9f03-b0185320f10e","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.222783Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:129a85f7d998fd0b8a3607c72e583355974e4679561004dd61b7922749deffa8","observation_id":"60c7b974-dbbf-48c7-a06f-739395081a4e","resolution":{"observed_at":"2026-08-12T13:30:03.141778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.118988Z","title":"A review of domain adap- tation without target labels","venue":null,"work_id":"9bfb305f-3a48-4219-bffb-07488a0ba881","year":null},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.227477Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:f1abab8df18f5fb3c3a9abb999d01c2e77b27eb2d366f589156a9ff814751cca","observation_id":"23a84531-b876-40ee-863c-96d2887bc81b","resolution":{"observed_at":"2026-08-12T13:30:03.125228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.102228Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":"d3ba6cf7-d47c-49b6-9ebc-73c416e1b317","year":2012},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.232543Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:29a9e2f2dab091f7a2b3052d7e4aa1f974227c732efdcad2fd18d02fe8996c7b","observation_id":"401389ab-dbf9-4d62-af1a-9de827ed8764","resolution":{"observed_at":"2026-08-12T13:30:03.107449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.086922Z","title":"Deeper, broader and artier domain general- ization","venue":null,"work_id":"f0aeaa08-4168-4da9-b1c2-b9c4235696ac","year":2017},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.237422Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:d4a8daba64654f68e0993112e9a871daeb8c9e3de640da7a86b14d6f6749d986","observation_id":"6b1087ee-8669-4423-b542-a84b96c7800f","resolution":{"observed_at":"2026-08-12T13:30:03.091600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.069745Z","title":"Prompt-driven dynamic object-centric learning for single do- main generalization","venue":null,"work_id":"43c26cb4-ee28-4595-b97a-6bc5fce3dfea","year":2024},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.242567Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:9b4aa4352391ec6d651ca64a8a70b6934e31c87cc75c786eed90c5b0b81ee2d7","observation_id":"336b3682-ffa5-4245-b803-c1c71d6033a4","resolution":{"observed_at":"2026-08-12T13:30:03.074893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.053024Z","title":"Uncertainty modeling for out- of-distribution generalization","venue":null,"work_id":"73afee4f-1d46-491c-b66e-af467e5dcdba","year":2022},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.247777Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:c4d147df04c51a073251c442c7d9e13cc4431cd463b735411cf63806efabcf0b","observation_id":"93feac57-cc5d-4f2e-879b-3c986844f350","resolution":{"observed_at":"2026-08-12T13:30:03.058268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.252544Z","title":"Deep domain gener- alization via conditional invariant adversarial networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.252544Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:6011121a5ccfa281bd73e8e2e3f1bccd8a10a9ad81fd13877b7e9ad69c01be1c","observation_id":"2da79e73-a01d-43e6-987b-4cb2179504b9","resolution":{"observed_at":"2026-08-12T13:30:02.252544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.13624","last_updated":"2023-07-27T13:13:11Z","snapshot_observed_at":"2026-08-12T10:44:18.799473Z","submitted_at":"2021-08-31T05:28:42Z","title":"Towards Out-Of-Distribution Generalization: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.13624","snapshot_observed_at":"2026-08-12T13:30:02.258250Z","title":"Towards out-of-distribution generalization: A survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.258250Z"},"links":{"cited_paper":"/paper/2108.13624","citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:91b210b4822086b4d2ef271bcb422a6425b3c74e0389e93b3e84420bfea7a9a1","observation_id":"d3fe4fe6-36b1-4a86-ab43-aa302ed54daa","resolution":{"observed_at":"2026-08-12T13:30:02.258250Z","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":"2026-08-12T13:30:03.022155Z","title":"Learning transferable features with deep adaptation net- works","venue":null,"work_id":"342f88a5-69a9-4167-84d9-bb22f9c29dcb","year":2015},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.263429Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:b1393e5a817ebf015cb36dbe66211d320a4bc56d93484f203cb35e8f2b9a358b","observation_id":"b188dd93-619f-4426-8829-cf9e51ad9dc9","resolution":{"observed_at":"2026-08-12T13:30:03.027726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:03.006382Z","title":"Do concept bot- tleneck models learn as intended? International Conference on Learning Representations (ICLR), 2021","venue":null,"work_id":"c19d252e-184e-4c20-9953-a1e63cd2b470","year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.268290Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:4182d915ac647c5114882e83a64eac6807cced0f8c5f2403f777193f58aed37a","observation_id":"ea9872d1-0cb1-4990-955c-93b32e6bbac9","resolution":{"observed_at":"2026-08-12T13:30:03.011278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.987889Z","title":"Unified deep supervised domain adap- tation and generalization","venue":null,"work_id":"b3751e71-9ffd-4b8d-9116-162285390054","year":2017},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.273114Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:831ed8fc8c5652b0e573e69d7d6bcea5ef1b7f092c7bb91b92ebc28d221a9e75","observation_id":"ed782dde-80cc-49d5-bc72-b34f1b073cd5","resolution":{"observed_at":"2026-08-12T13:30:02.993273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.971490Z","title":"Domain generalization via invariant fea- ture representation","venue":null,"work_id":"9abad36a-f7cb-4cbc-add2-6380b78d5a73","year":2013},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.278634Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:da271601ce618b48209f4ab4759820f9c06d2d3c594a4ba5186f5a347b4254d8","observation_id":"b2f4941a-53be-4ac1-93bf-4f75aefb37c0","resolution":{"observed_at":"2026-08-12T13:30:02.976306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.955563Z","title":"Permuted adain: Reducing the bias towards global statistics in image clas- sification","venue":null,"work_id":"d7f9f908-f185-4498-a6e9-d5048d455b6c","year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.283704Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:27c9ef526884281c6503da9ab6e9df86f61af40c2ec8d19639d26f6c68c20cf7","observation_id":"c9d58594-e807-4687-be3a-cc5761508534","resolution":{"observed_at":"2026-08-12T13:30:02.960828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.939693Z","title":"Label-free concept bottleneck models","venue":null,"work_id":"482c6ea8-3adb-45f6-984d-9c967a2c89d6","year":null},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.288851Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:23483d9a9f6214d00d16e24e7bf5a91dcae2f59edbbaef6dd2cff6e93a5de4e3","observation_id":"73aac921-5c95-436d-8a79-840f187ff312","resolution":{"observed_at":"2026-08-12T13:30:02.944921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.923476Z","title":"Moment matching for multi-source domain adaptation","venue":null,"work_id":"e1b7516a-82e7-46b3-be56-f8c5b8eb2872","year":2019},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.294565Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:53cf1eda83ffef48e47e3895019d3dd720847d723adaea2a4371ab745010c2fd","observation_id":"03a2b777-3820-4b3f-8dbe-e3e08bce8194","resolution":{"observed_at":"2026-08-12T13:30:02.928543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.907747Z","title":"Generalizing to unseen domains via text-guided augmenta- tion","venue":null,"work_id":"877e883c-6241-4e36-9772-f3f7923f40bf","year":null},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.299708Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:130145528e88419575168fbf309254de61831b85b5e7aea91e70736b66e15ab8","observation_id":"386d5535-7ac1-4e0b-9a6c-b584caea2c6a","resolution":{"observed_at":"2026-08-12T13:30:02.912898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.892553Z","title":"Learning to learn single domain generalization","venue":null,"work_id":"3db4083d-4897-47fd-824f-091657856af4","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.304801Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:fafc1e344409efa6084f8e0eae1f386d91fea77fb3fc5cb41122dece2a759101","observation_id":"dfd3fc45-d6e3-469a-8910-6f3de45bf238","resolution":{"observed_at":"2026-08-12T13:30:02.897380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.877472Z","title":"Modality-agnostic debiasing for single domain generalization","venue":null,"work_id":"b8171a20-9704-4181-881c-400b5a40a919","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.309704Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:9fbcef4e9d67d1bbc958cfdcbda0da24a4f4b62606fc3907133afa21dd4c0d68","observation_id":"141d2a99-975b-4911-a421-7167b3915510","resolution":{"observed_at":"2026-08-12T13:30:02.882495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.861970Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":"30959e47-8a1c-43ea-8116-19e6c6101e12","year":2022},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.314459Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:77d943a1937cfd41e3b9cf30fc654928453ff44142e80b62d700966a2e45b287","observation_id":"8cbabd05-54ae-4639-a822-4458e0f9860f","resolution":{"observed_at":"2026-08-12T13:30:02.867187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.845925Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":"59f0f40e-84af-477f-9720-aba6b1776f97","year":2017},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.319328Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:48ff16f928cb9ac1acbc74d3d4e93eeec26ed6a747c7fd39aebf6fc144f98069","observation_id":"f23af52c-56d9-49a1-9585-c904ea5f54bc","resolution":{"observed_at":"2026-08-12T13:30:02.850881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.829337Z","title":"Class-wise domain generalization: A novel framework for evaluating distributional shift","venue":null,"work_id":"4f6a6205-2f4c-47aa-a46b-ca801f1fb646","year":2022},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.323777Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:8698e82f04f8c2208dfac1c0e411e75f8f537c353312250e87086b54505654a1","observation_id":"7110ad05-6e79-4500-abaa-1598691b2a78","resolution":{"observed_at":"2026-08-12T13:30:02.835327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11207","last_updated":"2020-07-10T15:13:11Z","snapshot_observed_at":"2026-07-06T09:30:47.469703Z","submitted_at":"2020-06-19T16:20:40Z","title":"Frustratingly Simple Domain Generalization via Image Stylization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11207","snapshot_observed_at":"2026-08-12T13:30:02.329073Z","title":"Frus- tratingly simple domain generalization via image stylization","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.329073Z"},"links":{"cited_paper":"/paper/2006.11207","citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:e76d88e09796146999be129704f393de7726a178a95980579cc5488bb3cfa3f2","observation_id":"5dff4ccd-fbac-4dd5-8192-20d8ea9a336a","resolution":{"observed_at":"2026-08-12T13:30:02.329073Z","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":"2026-08-12T13:30:02.812916Z","title":"Class- imbalanced domain adaptation: An empirical odyssey","venue":null,"work_id":"ed9f08a9-7b5e-475c-8e63-0b768848eee7","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.333997Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:c57772d9cdc67b29d02ddc91869f24b71f8354adcff6bef6bc8ae81ed037d65b","observation_id":"db61579f-2ec8-4051-b1d4-606b3efa3a3d","resolution":{"observed_at":"2026-08-12T13:30:02.818297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.797216Z","title":"Emergent correspondence from image diffusion","venue":null,"work_id":"03b327f7-98a5-413a-9822-0d1dcbfa83fe","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.338746Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:9f7e9d686d248dc8061f4c3b439a69f863efa62043a352b811a4370e6904acc1","observation_id":"34b9f02a-0032-4fca-be58-56633f948247","resolution":{"observed_at":"2026-08-12T13:30:02.802262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.781320Z","title":"Unbiased look at dataset bias","venue":null,"work_id":"8bd5a399-43fa-4ceb-99ec-056c9ecae0e2","year":2011},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.343174Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:7b3d3cb607b945064182e92a27aba8eb7184c6b522e96ad5ee35af908e6d9455","observation_id":"0fd4e8c5-5590-42b3-9f9f-4f5ac458a8ef","resolution":{"observed_at":"2026-08-12T13:30:02.786209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.764666Z","title":"Adversarial discriminative domain adaptation","venue":null,"work_id":"7a7ee689-b814-47f8-b1b8-85ba9ccb3120","year":null},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.347703Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:ebf057c815d2c6da4cea9a97bd787b355bf1eee281d0cee3e1528299ad0b41a0","observation_id":"a972717d-efdc-4903-a02c-97e178eae1f2","resolution":{"observed_at":"2026-08-12T13:30:02.769614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.749155Z","title":"Deep hashing network for unsupervised domain adaptation","venue":null,"work_id":"21257236-830a-4dca-99d4-6d5e82908b8d","year":2017},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.352858Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:1c3a73ba74f05560506313e450e64c8929ac3eeab5f58400ee24c7ec9ca7e280","observation_id":"521bf0f5-a11b-4930-9b95-7d697c449af8","resolution":{"observed_at":"2026-08-12T13:30:02.754029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.733398Z","title":"Generalizing to unseen domains via adversarial data augmentation","venue":null,"work_id":"cae3c6d3-5f84-497c-9a36-59e79d4a8056","year":null},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.357132Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:c18642c081b04ef815b4b4c14ad02eae1ecd1fea0cbf6cffb8c679bc53d0c7af","observation_id":"b83cc7a0-1a2f-40f6-b208-6e5edb025206","resolution":{"observed_at":"2026-08-12T13:30:02.738598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.718092Z","title":"Mcpnet: An interpretable classifier via multi-level concept prototypes","venue":null,"work_id":"fc34191b-bbf3-4a4f-a494-7f8b61b4c9de","year":2024},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.361625Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:3fac2c079dfbd4905e60a89f2bfe505ce87f887945579c42ba4d63d84ddda5a7","observation_id":"2e16454c-405e-4972-830a-837c0c3d6486","resolution":{"observed_at":"2026-08-12T13:30:02.723072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.702585Z","title":"Learning robust representations by projecting super- ficial statistics out","venue":null,"work_id":"f9ec51f5-ecc1-4acf-a125-8b7bc69fa3e3","year":2019},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.366463Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:df8f66898ba5af4303ceca30f950756dd0ceb34909fafea054c3affa7995f9f1","observation_id":"61c0b8ae-9282-4fb4-9c6b-78c43a15f103","resolution":{"observed_at":"2026-08-12T13:30:02.707446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.371165Z","title":"Generalizing to unseen domains: A survey on do- main generalization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.371165Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:3bf4b4e751aee1c689b6b61bad3b4f62ae419dc5f5089561f8ea3128ac6a1c72","observation_id":"3290866e-6b17-4c96-86ac-87baa8430e1c","resolution":{"observed_at":"2026-08-12T13:30:02.371165Z","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":"2026-08-12T13:30:02.676635Z","title":"Learning to diversify for single do- main generalization","venue":null,"work_id":"44ef9537-d82d-4ccd-a9b4-9779a250c985","year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.375603Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:c7367208e565750e2a9b99f9648a5fbdaf4564d304978c172cb82ff20b728727","observation_id":"cf6e361f-224a-4fb7-8d43-b94b52edc8a7","resolution":{"observed_at":"2026-08-12T13:30:02.681784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.661513Z","title":"A bit more bayesian: Domain-invariant learning with uncertainty","venue":null,"work_id":"291447c4-702f-4d8c-82d0-63405ce3c852","year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.380231Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:dc57252ff47ea4be2aa7923912b855db62ef42c791ea3439d9db351a707c05a3","observation_id":"91732408-af1e-4cc3-b6d9-89a9bcce62b6","resolution":{"observed_at":"2026-08-12T13:30:02.666462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.645621Z","title":"Simde: A simple domain ex- pansion approach for single-source domain generalization","venue":null,"work_id":"2f2e346a-9271-47c2-a40b-8fdad18a2bfc","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.385474Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:04c91ac42fc778fb835a18625af6385093b56f3046bd2cf8d6756b6e797280f7","observation_id":"d6df2a17-23b1-4688-82d7-21e0da6d6841","resolution":{"observed_at":"2026-08-12T13:30:02.650747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.629592Z","title":"Language in a bottle: Language model guided concept bottlenecks for in- terpretable image classification","venue":null,"work_id":"a605b8f6-747c-4750-8962-413576e14ab8","year":2023},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.390319Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:493fa80b812e32ba3048f5f2fca25e350177fb51b86d0852cb1c638c6052003f","observation_id":"a01abe31-1053-470b-9076-62fb606668d9","resolution":{"observed_at":"2026-08-12T13:30:02.634664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.613639Z","title":"Not just pretty pictures: Toward interventional data augmentation using text-to-image generators","venue":null,"work_id":"e725bc4a-b0c7-4f2d-8079-773cd5a66c45","year":2024},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.394861Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:9bd38f2c7d55985287466bce128f98b5c1ed4ebf37f279fa1a06e40abf24db5d","observation_id":"d978ead3-f054-4a18-990e-973c4f25aa4f","resolution":{"observed_at":"2026-08-12T13:30:02.618791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.596916Z","title":"Cutmix: Regu- larization strategy to train strong classifiers with localizable features","venue":null,"work_id":"d8c0879f-1af1-401a-8aad-65158c204550","year":2019},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.399711Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:c2725f1fbeac56904b728166df0d74735bda15e0f5bcc87542c7c39aac2352b1","observation_id":"ef8d0cd8-39b9-4001-82ba-a8794bf75ef9","resolution":{"observed_at":"2026-08-12T13:30:02.602430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.580255Z","title":"Dauphin, and David Lopez-Paz","venue":null,"work_id":"4fd30372-749d-4098-8ea1-4d965238e29b","year":2018},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.404604Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:a36c1ef21997ce73ff80f1331c36513d36eaa0e8e5041c001575ead73a01a3d0","observation_id":"c0ac0697-de44-4bf7-9078-152416afe3d3","resolution":{"observed_at":"2026-08-12T13:30:02.585064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.563494Z","title":"Towards principled disentanglement for domain generalization","venue":null,"work_id":"92c7a53e-3de2-4e3d-baf0-0b935f19bb2b","year":2022},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.409356Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:0b0b929e36ab49b9d61207c89fa9f9fa85c87e8daf3e6d459c69785be92150a0","observation_id":"a3487d31-8eb8-4214-b794-84fa383a58c0","resolution":{"observed_at":"2026-08-12T13:30:02.568882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.547417Z","title":"Maximum-entropy adversarial data augmentation for im- proved generalization and robustness","venue":null,"work_id":"1d7d2b0d-bd3c-45ef-a668-12e80d655a6c","year":2020},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.413997Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:e915ec72f28fe6afcc3e059642987406f4f6edea12ee483cb695d362bdb352aa","observation_id":"582822da-e72d-4990-bd7c-cf7978cc593c","resolution":{"observed_at":"2026-08-12T13:30:02.552674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.530508Z","title":"Do- main generalization with mixstyle","venue":null,"work_id":"5f328d42-a7de-4ed1-82b1-1b3621db03e9","year":2021},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.418743Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:80611323341819b2f5700e708bd24e5c58074d5d3b9a4ce097f0a0d2f96f9ae3","observation_id":"ed4c394a-f7f1-4fdd-80e8-036145a40c3f","resolution":{"observed_at":"2026-08-12T13:30:02.536658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T13:30:02.512627Z","title":"Mixstyle neural networks for domain generalization and adaptation","venue":null,"work_id":"df41f870-1d54-402b-9e80-4e58ea1013a1","year":2024},"citing_paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T13:30:02.423243Z"},"links":{"citing_paper":"/paper/2411.16788"},"observation_digest":"sha256:b90f3e902d1b7cd4df957935bcb9998917843a0ef3ab9fac86409e9481d85416","observation_id":"07bb6394-15d8-4b7f-a8de-c2df5c89b507","resolution":{"observed_at":"2026-08-12T13:30:02.519441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.16788","last_updated":"2025-04-05T07:08:18Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T13:21:35.563669Z","submitted_at":"2024-11-25T08:46:37Z","title":"TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":58},"total_outbound_references":64},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2411.16788."}