{"as_of":"2026-08-21T17:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1cce9ef8432ae9338f838f3c66ff26edab6e7a56776423a2dba196c6688c23f7","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T16:58:53.510693Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2411.15204/citation-record","integrity":"/paper/2411.15204/integrity","json":"/paper/2411.15204/citation-record.json","paper":"/paper/2411.15204"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:58:53.238612Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.238612Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:0e0172759bca48829ae9ffec4a551518e4edfa91befa322f112727d79674992f","observation_id":"8abf8967-85c3-4c57-8cec-04b1837917ba","resolution":{"observed_at":"2026-08-12T16:58:53.238612Z","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":"2026-08-12T16:58:53.244175Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.244175Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:4a73384dbfe0a06650b3d6d01aff2a041ef60fc04d18407439f3573b1415d475","observation_id":"9b6c38a9-3ec9-48d8-88ee-ad68459f2c90","resolution":{"observed_at":"2026-08-12T16:58:53.244175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-12T16:58:53.249103Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.249103Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:e4db344d1cd88d25b60ce40d335a2f3e9b6b9a3a13bb4e1d6399447caa483a1c","observation_id":"08470eb9-3b69-4a9b-b74d-bc3acc9665ae","resolution":{"observed_at":"2026-08-12T16:58:53.249103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-12T16:58:53.254249Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.254249Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:a36dbf43ac10a3eef42263f6311ae0efa40e6e04e4262a26eeef367b9b95eade","observation_id":"6e0c0fa7-e573-49c1-b243-4d74ff9ca9d5","resolution":{"observed_at":"2026-08-12T16:58:53.254249Z","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":"2026-08-12T16:58:53.259076Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.259076Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:d29753edadbffc94ffd72d1e50dd28a48019387963ec3c65325b67dda07a5ab4","observation_id":"15fb0467-724a-40ef-ae73-d2fa4ff5092f","resolution":{"observed_at":"2026-08-12T16:58:53.259076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07178","last_updated":"2020-06-15T18:34:23Z","snapshot_observed_at":"2026-08-19T09:03:25.261703Z","submitted_at":"2020-06-12T13:34:46Z","title":"Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07178","snapshot_observed_at":"2026-08-12T16:58:53.263946Z","title":"Meta-reinforcement learning robust to distributional shift via model identification and experience relabeling","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.263946Z"},"links":{"cited_paper":"/paper/2006.07178","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:4e310fc3afb50fee03f99dbf75474435eccd2b98efdecbab089bd4c57de64f05","observation_id":"439b66c0-4b36-466f-b372-2661ed78be88","resolution":{"observed_at":"2026-08-12T16:58:53.263946Z","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":"2026-08-12T16:58:54.313548Z","title":"Adapting visual category models to new domains","venue":null,"work_id":"db9e6d00-3d21-41eb-af2b-df3225eca814","year":2010},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.269660Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:0d4bc597e600b7a46b6f31f664a217b4a6e9c84111e4b5e42745446aba05e92c","observation_id":"2f03669f-ae84-47ca-9b31-934e67c44736","resolution":{"observed_at":"2026-08-12T16:58:54.320635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.287353Z","title":"Measuring robustness to natural distribution shifts in image classification","venue":null,"work_id":"f6977606-f822-43b9-844c-52ef6d789f62","year":2020},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.273963Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:97f584ef38d8f083408781a60f8aa80c46972ac4b6687e86ac2a2a745ec9c266","observation_id":"6bf9bb20-e977-49d3-8c4f-8485304590f8","resolution":{"observed_at":"2026-08-12T16:58:54.292422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.278488Z","title":"Parameter-free online test-time adaptation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.278488Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:c968a811a06cf0ad3e535dc79c111b7c46fd86a550d7fc2ad0ff264a0b41ff5d","observation_id":"9357238f-1721-4d84-b4f4-12d9efd0cf19","resolution":{"observed_at":"2026-08-12T16:58:53.278488Z","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":"2026-08-12T16:58:54.263238Z","title":"Test time adaptation via conjugate pseudo- labels","venue":null,"work_id":"b2a488ac-dd35-46f4-96ea-5fe736c6a6a1","year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.283110Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:b6e7853f0706788c501f8cb23579674fbc93de7365ea14b3481e9a6aedf37052","observation_id":"77c5c666-50cc-4042-80ed-f8cb5f580e75","resolution":{"observed_at":"2026-08-12T16:58:54.267791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.248038Z","title":"Test-time adaptation via self-training with nearest neighbor information","venue":null,"work_id":"121196be-4c06-45a6-8efa-c8911ae6a1f8","year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.287499Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:fa51182ac113d26f62589384178f4b1918bea45b0c6ce4b1a9387012c486885d","observation_id":"a84362cf-520d-4eb1-8a95-61288f78ded4","resolution":{"observed_at":"2026-08-12T16:58:54.253154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.231933Z","title":"Tent: Fully test-time adaptation by entropy minimization","venue":null,"work_id":"6be63757-7448-4b74-a159-322e0c35754e","year":2020},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.292401Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:a1ab1c8817619472ca1f9bc8e53e307e76fb1deb51bfb26d04026a871af5b366","observation_id":"d6c10a4a-2499-4322-8214-5f9300e3ee7a","resolution":{"observed_at":"2026-08-12T16:58:54.237042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.215879Z","title":"Delta: Degradation-free fully test-time adaptation","venue":null,"work_id":"1690cf89-f825-40d6-9b37-9c87c3a34c71","year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.297211Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:65fdf17b936afa3dcfbc8fcdd1f355b72261411d9f419e6c4b0227e1b777edff","observation_id":"cd380ff5-aa18-4398-976a-6a8fe67008a8","resolution":{"observed_at":"2026-08-12T16:58:54.221046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10963","last_updated":"2021-01-14T21:11:06Z","snapshot_observed_at":"2026-08-19T09:01:42.968993Z","submitted_at":"2020-06-19T05:08:43Z","title":"Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10963","snapshot_observed_at":"2026-08-12T16:58:53.301584Z","title":"Eval- uating prediction-time batch normalization for robustness under covariate shift","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.301584Z"},"links":{"cited_paper":"/paper/2006.10963","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:0e281697cf0475861b29ac4ae95b7c9681480f187285c687d5edc06bf5c2f356","observation_id":"748cd898-0673-48a4-bb99-262319b11a6c","resolution":{"observed_at":"2026-08-12T16:58:53.301584Z","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":"2026-08-12T16:58:53.307105Z","title":"Im- proving robustness against common corruptions by covariate shift adaptation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.307105Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:7415633574706f4eb78cad296ad9d324c74e302322fb9a6deaf9a72e79fae2b1","observation_id":"cee06f23-0da7-4607-a957-6dc58e328879","resolution":{"observed_at":"2026-08-12T16:58:53.307105Z","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":"2026-08-12T16:58:54.188749Z","title":"Pseudo-label : The simple and efficient semi-supervised learning method for deep neural networks","venue":null,"work_id":"e2b95edd-9c7f-4d1f-b764-227386d57462","year":2013},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.311886Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:2bc620b659d049efbb6a2399798bc1b365b3111dfedeb5641b15896b834ea2de","observation_id":"3a0c667e-f245-4eea-b1db-5754817de3e8","resolution":{"observed_at":"2026-08-12T16:58:54.193669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.171817Z","title":"Ods: test-time adaptation in the presence of open-world data shift","venue":null,"work_id":"2bcfe3a0-25a1-4fb7-b04d-e50325b55991","year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.316752Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:7990d5664689139c0521d7ce7ebb4c5df8167fbadab8b2ef6575d9fb13d21138","observation_id":"2acb5185-c18d-4692-8833-acd29bdd70b2","resolution":{"observed_at":"2026-08-12T16:58:54.178141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.321743Z","title":"Note: Robust continual test-time adaptation against temporal correlation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.321743Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:59717ec9e0002cacc06a30b671991f52e6c8e58bf14a4e3d4b246d88c9165795","observation_id":"bbecfc12-a38c-4e94-abc5-8ea61e9cc398","resolution":{"observed_at":"2026-08-12T16:58:53.321743Z","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":"2026-08-12T16:58:53.326717Z","title":"Towards stable test-time adaptation in dynamic wild world","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.326717Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:c9531c51f7963a4277030583e1c116c4e4d46a89dbee65b19c8db344e47dc656","observation_id":"50623d3f-a9a0-431f-b80e-160615308365","resolution":{"observed_at":"2026-08-12T16:58:53.326717Z","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":"2026-08-12T16:58:54.134143Z","title":"Learning with noisy labels","venue":null,"work_id":"873f7ef9-2dfb-4533-9b5d-0e75cde6e275","year":2013},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.332143Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:04b6c37d2a708459c04ca0c99f593492f82ee68856d2bdb574314960467a1c80","observation_id":"b7ded432-130a-41e6-9061-3de6034745e1","resolution":{"observed_at":"2026-08-12T16:58:54.139921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.337373Z","title":"Making deep neural networks robust to label noise: A loss correction approach","venue":null,"work_id":null,"year":1944},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.337373Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:a4b8ecddfe30dde074d6b01cf74a16e28e5c9b24032f696e66f993a3343dc1c5","observation_id":"931ddecf-ed1c-4bc1-a361-a96fa66df24f","resolution":{"observed_at":"2026-08-12T16:58:53.337373Z","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":"2026-08-12T16:58:54.108870Z","title":"Clusterability as an alternative to anchor points when learning with noisy labels","venue":null,"work_id":"92f57bd7-f197-4219-8972-b9e5103de76e","year":2021},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.342323Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:4cf48ca931063831c4a6eed924ba19893d1e1c62435991842644fd39c179cbd3","observation_id":"cd04e6dc-4b33-487c-94e7-c50d05598df2","resolution":{"observed_at":"2026-08-12T16:58:54.114009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.092218Z","title":"Domain adaptation with invariant representation learning: What transformations to learn? Advances in Neural Information Processing Systems, 34:24791–24803, 2021","venue":null,"work_id":"5fef4208-1636-4fcf-b242-4be9b8490ff3","year":2021},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.347342Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:b14940b5439b7bb61c42c86b7c9a6628e3f3ec75b74d4f05cee959cd6762f0d0","observation_id":"970a9616-f1b4-4a83-b3f8-72e8a4b3e59d","resolution":{"observed_at":"2026-08-12T16:58:54.097819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13381","last_updated":"2023-02-24T15:56:45Z","snapshot_observed_at":"2026-08-17T21:16:43.115775Z","submitted_at":"2023-01-31T03:06:47Z","title":"When Source-Free Domain Adaptation Meets Learning with Noisy Labels","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13381","snapshot_observed_at":"2026-08-12T16:58:53.352211Z","title":"When source-free domain adaptation meets learning with noisy labels","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.352211Z"},"links":{"cited_paper":"/paper/2301.13381","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:ac140856a61ced5779ada02296bd7b0dd54ab43f6cd8f9a1751941eac5ca2b72","observation_id":"3aec5f1c-72cd-4d3d-8833-04c9f1104fe5","resolution":{"observed_at":"2026-08-12T16:58:53.352211Z","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":"2026-08-12T16:58:53.358950Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.358950Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:3243a0b6a600d3be613a03f20b3fbd8c63bbf11a213a6167fe4619ced6f5f896","observation_id":"5d043280-6e22-47a3-a9fa-e39616bc862f","resolution":{"observed_at":"2026-08-12T16:58:53.358950Z","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":"2026-08-12T16:58:53.364550Z","title":"Benchmarking neural network robustness to common corruptions and perturbations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.364550Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:eda3f1bbd556a01f2d0bd10c02ccff964dc0ced49907238f3ab217bd6b54ab79","observation_id":"0db7a207-711f-403f-9fe1-064671d877ae","resolution":{"observed_at":"2026-08-12T16:58:53.364550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08810","last_updated":"2023-08-17T06:37:37Z","snapshot_observed_at":"2026-08-16T15:07:54.578191Z","submitted_at":"2023-08-17T06:37:37Z","title":"Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts","version":1},"cited_work":{"arxiv_id":"2308.08810","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.08810","snapshot_observed_at":"2026-08-12T16:58:53.633602Z","title":"Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts","venue":"cs.CV","work_id":"a83c1cac-2b49-4253-881a-b86a5d780dda","year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.369760Z"},"links":{"cited_paper":"/paper/2308.08810","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:dda0fbba7bf485b17f1482491e7c3376c8a3bb6c40d07807699d2e07030af34d","observation_id":"f36807a0-476a-4eed-ad69-e3ca06408a32","resolution":{"observed_at":"2026-08-12T16:58:53.640856Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.056350Z","title":"Improving test-time adaptation via shift-agnostic weight regularization and nearest source prototypes","venue":null,"work_id":"4a626ba1-38ed-42c0-bae4-c8dec403d56e","year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.374947Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:ec98545eb05f090dc1b17b3007da501d48efd91a1fd264738bdc64199698d84f","observation_id":"7958a4b6-8ebc-4311-8ac8-8e249965fd53","resolution":{"observed_at":"2026-08-12T16:58:54.061759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.041497Z","title":"Ttn: A domain-shift aware batch normalization in test-time adaptation","venue":null,"work_id":"f27461b3-666a-4f44-a731-fc60d8888e62","year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.379940Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:ae65426a19105b627dd043db833053ea4f2d4428a0d53295361161cf289d1bd5","observation_id":"699057d2-2108-4674-ac8d-e1f1bc90cd5e","resolution":{"observed_at":"2026-08-12T16:58:54.046076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:54.026969Z","title":"Bayesian nonparametric federated learning of neural networks","venue":null,"work_id":"cc917753-0f83-4b28-a087-6a57f7e073d2","year":2019},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.384793Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:d90a61699fb74a7ed6dfc0799777d24b4a7b010640f4816080ab3826386e9147","observation_id":"deaf8802-b752-42c7-bd85-81c4d0087e6c","resolution":{"observed_at":"2026-08-12T16:58:54.031673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00451","last_updated":"2018-06-01T17:16:56Z","snapshot_observed_at":"2026-08-16T06:32:06.888652Z","submitted_at":"2018-06-01T17:16:56Z","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00451","snapshot_observed_at":"2026-08-12T16:58:53.389514Z","title":"Do cifar-10 classifiers generalize to cifar-10? arXiv preprint arXiv:1806.00451, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.389514Z"},"links":{"cited_paper":"/paper/1806.00451","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:804a159d0fe0116b84830e38ed79aaf25c3e1342d33f073bb9c8e6763d3a16fa","observation_id":"baa300a2-4a57-4d48-bc14-1519caaa4743","resolution":{"observed_at":"2026-08-12T16:58:53.389514Z","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":"2026-08-12T16:58:54.011602Z","title":"Hospedales","venue":null,"work_id":"5f0b4e9a-5ead-49dc-911f-ce32856f1d59","year":2017},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.394531Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:1ee06b944fd83f9017a93a0124d62fff0776f74a9600033f9e306ad53a7172e6","observation_id":"c925125b-0ffb-440b-a920-2bc107497958","resolution":{"observed_at":"2026-08-12T16:58:54.016444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.399727Z","title":"Deep hashing network for unsupervised domain adaptation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.399727Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:bb009137336df41c197ae50298a7831217c46cebab2aeb75b82ca99194aac20b","observation_id":"7d8be459-de0e-4637-adf3-462eddfe7fac","resolution":{"observed_at":"2026-08-12T16:58:53.399727Z","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":"2026-08-12T16:58:53.405098Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.405098Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:8707df8c3392deadca0675afb70e42bab38a4e6ff038986efbfcb5c7470969cb","observation_id":"da23dd38-1de4-4387-88b1-f5e249d38df9","resolution":{"observed_at":"2026-08-12T16:58:53.405098Z","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":"2026-08-12T16:58:53.973263Z","title":"Neural networks: a comprehensive foundation","venue":null,"work_id":"61a1c771-3a62-44ad-bcd7-5beb89f19a08","year":1998},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.410147Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:1435202580ffa6b46b4b0432f2ea62b0f9c03ee7265cbea261dacc29a81f46df","observation_id":"90adf06e-2fdf-4418-aa8b-61885fc8dd42","resolution":{"observed_at":"2026-08-12T16:58:53.978559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.957861Z","title":"Leveraging proxy of training data for test-time adaptation","venue":null,"work_id":"22220a76-a9e4-4807-a4fa-b42fc6989da6","year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.415248Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:c749fd1f991917a8c705ecd7115fa14da4da0f8397fc585f1171f9120ca077a7","observation_id":"26c12803-8dea-4d62-a942-5d6066ed0007","resolution":{"observed_at":"2026-08-12T16:58:53.962778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.420316Z","title":"Smote: synthetic minority over-sampling technique","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.420316Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:b2f545403f9a357f5a8446fa4aa5972ae544271e6d68e300561c96aee82765ff","observation_id":"abb59019-ee86-477f-9fc7-3cbc87219521","resolution":{"observed_at":"2026-08-12T16:58:53.420316Z","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":"2026-08-12T16:58:53.933143Z","title":"Exploratory undersampling for class-imbalance learning","venue":null,"work_id":"24f46bba-8e29-4206-a0c4-dc94a12918d0","year":2008},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.425087Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:6b138d48e60667e6ced78d8395b86472cba2a3b785b5d2c6ced4f57ec4139ea7","observation_id":"098b5e1c-8ad2-42ea-9ec4-d958b740379c","resolution":{"observed_at":"2026-08-12T16:58:53.938271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.916716Z","title":"Disentangling label distribution for long-tailed visual recognition","venue":null,"work_id":"30edf699-3887-4d76-922a-30de821b5537","year":2021},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.429892Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:87348e9a5419235b303f583750342eba384bdeb12c3db3575f55114e8129571c","observation_id":"d223e1e7-7eff-4c1f-bf2a-1891f8e65811","resolution":{"observed_at":"2026-08-12T16:58:53.922140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.07314","last_updated":"2021-07-09T21:23:25Z","snapshot_observed_at":"2026-08-08T11:03:52.719052Z","submitted_at":"2020-07-14T19:27:13Z","title":"Long-tail learning via logit adjustment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.07314","snapshot_observed_at":"2026-08-12T16:58:53.434650Z","title":"Long-tail learning via logit adjustment","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.434650Z"},"links":{"cited_paper":"/paper/2007.07314","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:52593a6e2389daab20a111697caf115339a53d770854589cf4cb461464dca0c4","observation_id":"adb97b93-b759-4f6a-8cb9-bcaa9123763b","resolution":{"observed_at":"2026-08-12T16:58:53.434650Z","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":"2026-08-12T16:58:53.899907Z","title":"Rlsbench: Domain adaptation under relaxed label shift","venue":null,"work_id":"a269682d-bbce-41b9-923c-2e8a148e1caa","year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.439206Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:67db9a125d070c9eade63b96a9a2c53be10987e17488f01d1c92f62bf0461513","observation_id":"69a16708-8a99-4a7a-887b-72f7148bc99d","resolution":{"observed_at":"2026-08-12T16:58:53.905553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.882964Z","title":"80 million tiny images: A large data set for nonparametric object and scene recognition","venue":null,"work_id":"f9db306c-1610-4ed1-9152-4162300962f4","year":1958},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.443737Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:6e55d5050a99a0d85ee72601611c2047adf696b0973bb1355e5e4111dbbe6de4","observation_id":"5e9b7533-3d04-4fb6-88dd-bcb0513e476d","resolution":{"observed_at":"2026-08-12T16:58:53.888560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.448505Z","title":"On pitfalls of test-time adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.448505Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:1fba352a45155960fd033e039cc6d8ad902290c7166a5664981d3fdd9bfe97a5","observation_id":"b2d7072e-942e-4817-852b-2e7a1fea526f","resolution":{"observed_at":"2026-08-12T16:58:53.448505Z","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":"2026-08-12T16:58:53.453450Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.453450Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:a2b465a549da6e3b62e83e77d0f245576c8d70ab896fd3286425e9c7ea9289c8","observation_id":"ddc73e43-2ddd-4fc4-9cb0-efdcdd200f3b","resolution":{"observed_at":"2026-08-12T16:58:53.453450Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.08375","last_updated":"2026-04-14T12:21:53Z","snapshot_observed_at":"2026-08-14T20:09:04.632955Z","submitted_at":"2018-03-22T14:30:17Z","title":"Deep Learning using Rectified Linear Units (ReLU)","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.08375","snapshot_observed_at":"2026-08-12T16:58:53.458167Z","title":"Deep learning using rectified linear units (relu)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.458167Z"},"links":{"cited_paper":"/paper/1803.08375","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:59dcff83f2ea1c11c8b08e4ea5f55f5a05e5a976998d10c62b9ea85b64ed2f30","observation_id":"10485c08-95f7-41f9-9a79-91a3a24d0a63","resolution":{"observed_at":"2026-08-12T16:58:53.458167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-12T16:58:53.462979Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.462979Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:23466aaa7b2ae52a1ea031fbc218920f0b5479bac106e9468c5275a2bbe44d9c","observation_id":"d15a81e9-d1bf-43c0-905a-1c3302757e23","resolution":{"observed_at":"2026-08-12T16:58:53.462979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-12T16:58:53.467481Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.467481Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:dd09561d3796713f02755594f420f51a1e87907f6fe932fbb59ace0177e9567a","observation_id":"bba69381-8251-44b9-b33b-765e682caa6a","resolution":{"observed_at":"2026-08-12T16:58:53.467481Z","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":"2026-08-12T16:58:53.846361Z","title":"Test-time classifier adjustment module for model-agnostic domain general- ization","venue":null,"work_id":"48cfe5d0-d410-4bd4-987c-8277a4f16424","year":2021},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.471864Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:820550ed185b79b78a8c3a0ed05d2a17d595415bcb382cd639eb416c5ea517d5","observation_id":"87a7fe15-a3ce-4f55-af6a-9ff98bdac947","resolution":{"observed_at":"2026-08-12T16:58:53.851764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.829768Z","title":"Class relationship embedded learning for source-free unsupervised domain adaptation","venue":null,"work_id":"ffed9fec-e06e-4227-8cdc-137ef508aec6","year":2023},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.476311Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:49f4b1d1386d83ea54cce1e886eff8d0a12dab343ea07878ba700f3abc41292e","observation_id":"3f42c3f3-3812-48b6-aa2f-b344508a1eec","resolution":{"observed_at":"2026-08-12T16:58:53.835159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.480863Z","title":"Are anchor points really indispensable in label-noise learning? Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.480863Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:7c1d3b31813d98519a8df0d48b1953a6d5d790065862d0ff20be355b13ddd700","observation_id":"1d75dfd5-6d3d-413c-84f8-3f45eb342d37","resolution":{"observed_at":"2026-08-12T16:58:53.480863Z","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":"2026-08-12T16:58:53.803214Z","title":"Dual t: Reducing estimation error for transition matrix in label-noise learning","venue":null,"work_id":"1229cabc-beff-49b2-ae3c-406bd3ab0a12","year":2020},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.484864Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:d903206bba1102a1a694dd3895fe941ac07cd3f1d62dedc438659f272f6deec0","observation_id":"9a4a622f-06e7-447e-a3af-a3e152830d8c","resolution":{"observed_at":"2026-08-12T16:58:53.808369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.489420Z","title":"Dataset distillation by matching training trajectories","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.489420Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:7529b4be6ac7cdc1f64e8691a3f7dbd0c614b13d6173a9704476422d7c7812be","observation_id":"2afff982-87bd-4627-ad02-789353ae360f","resolution":{"observed_at":"2026-08-12T16:58:53.489420Z","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":"2026-08-12T16:58:53.494088Z","title":"Universal test-time adaptation through weight ensembling, diversity weighting, and prior correction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.494088Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:8c09684773cd661a946728246176732731b6ed353ab965c922b1dddcf18622d5","observation_id":"80520cb9-483d-48c8-84e8-bb04f7ca5e60","resolution":{"observed_at":"2026-08-12T16:58:53.494088Z","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":"2026-08-12T16:58:53.767159Z","title":"An empirical study of training self-supervised vision transformers","venue":null,"work_id":"53d8c955-7b2c-480e-a2ad-e2a1e457eca0","year":2021},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.498585Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:14d43898c4ba42ecc2c3980d8f98e377412052824848e05825911cb867acc736","observation_id":"151e335b-6ba9-4b0e-9964-2e87352bb544","resolution":{"observed_at":"2026-08-12T16:58:53.772356Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.750664Z","title":"mixed domain","venue":null,"work_id":"f7dfb979-7cf2-4d23-8ed0-e8681d0e8841","year":null},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.504973Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:738de4d0b99ec9e763d12e08e73384bf9049bc1ca7ff62209f90660a0829a105","observation_id":"3e50f209-6d11-4727-8a56-86548f8aa926","resolution":{"observed_at":"2026-08-12T16:58:53.755714Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T16:58:53.733168Z","title":"This demonstrates the efficiency of DART’s intermediate-time training, significantly enhancing its scalability for practical use","venue":null,"work_id":"ad181294-4dc6-438a-b7d6-779d72b3aaf2","year":null},"citing_paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T16:58:53.510693Z"},"links":{"citing_paper":"/paper/2411.15204"},"observation_digest":"sha256:5b8935df806b1c19e030e77191ee5b36e61d33b72edf1455ce13baf4b11c40e0","observation_id":"f9312802-c0cc-469b-b7d4-b72721a5b926","resolution":{"observed_at":"2026-08-12T16:58:53.738661Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.15204","last_updated":"2025-02-05T01:47:29Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T09:02:18.233162Z","submitted_at":"2024-11-20T05:58:52Z","title":"Label Distribution Shift-Aware Prediction Refinement for Test-Time Adaptation"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":3,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":1,"verified_fuzzy":24},"total_outbound_references":56},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2411.15204."}