{"as_of":"2026-08-13T16:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:443d2af1c145d59b157ab62fd94b0c5c90453d2bcfc37d4122dd2c67e333a2cd","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:50:37.376021Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"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/2505.20890/citation-record","integrity":"/paper/2505.20890/integrity","json":"/paper/2505.20890/citation-record.json","paper":"/paper/2505.20890"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:50:45.949137Z","title":"R2snet: Scalable domain adaptation for object detection in cloud– based robotic ecosystems via proposal refinement","venue":null,"work_id":"91ce5dfb-a134-4366-9d0c-7f7fed196fad","year":2024},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.105479Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:9eeb2d017ca4b408e1615d0523bf533f74554e2b50c05149519ce8c287ac84a2","observation_id":"9315facc-395a-466d-99fb-b8b1f60cc64d","resolution":{"observed_at":"2026-08-07T13:50:46.062270Z","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":"2404.11769","last_updated":"2024-04-19T16:50:05Z","snapshot_observed_at":"2026-08-13T00:27:50.000600Z","submitted_at":"2024-04-17T21:52:21Z","title":"QGen: On the Ability to Generalize in Quantization Aware Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11769","snapshot_observed_at":"2026-08-07T13:50:33.161957Z","title":"Qgen: On the ability to generalize in quantization aware training","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.161957Z"},"links":{"cited_paper":"/paper/2404.11769","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:8e10d0edc37af2a01d49287357b9224ea69569cb358151311b5b258a63c94c89","observation_id":"d76594ea-07bd-4505-ad43-4a51bb764f69","resolution":{"observed_at":"2026-08-07T13:50:33.161957Z","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":"2026-08-07T13:50:45.726868Z","title":null,"venue":null,"work_id":"2698d649-42d0-43c4-83cd-d58a3e0cf6bc","year":2024},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.278498Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:4cd7d392d4a65a458d13331970585e575fec74e5853a9f2293dcf6684ba355bb","observation_id":"564db7e0-cb85-427d-bfb2-39a7dba7edd5","resolution":{"observed_at":"2026-08-07T13:50:45.843723Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-07T13:50:45.525097Z","title":"Parameter-free online test-time adaptation","venue":null,"work_id":"9ef5bf27-4305-40ef-90a4-36d17c295dd9","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.426585Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:200d470582ca559281d50f8f412feef2181e84d280505aad1b33ae7ef54254df","observation_id":"71fb53f3-5dc1-467d-83c4-e1581bd63e7f","resolution":{"observed_at":"2026-08-07T13:50:45.642093Z","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":"2026-08-07T13:50:45.383483Z","title":"Prentice-Hall, Inc., 1988","venue":null,"work_id":"9fc3afc9-a1f3-4eb4-ba01-f585168d43ed","year":1988},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.526056Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:36de3ef88ea7d1df50ec590ba4cd400d0b0a5016c32e58ee40f3a653af65cc60","observation_id":"8458ed3d-2da4-47c5-87a8-833625b3f52e","resolution":{"observed_at":"2026-08-07T13:50:45.418670Z","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":"2026-08-07T13:50:45.140634Z","title":"Pasta: Proportional amplitude spectrum training augmentation for syn-to- real domain generalization","venue":null,"work_id":"149a703b-a77b-4583-862e-eb5867b3f3d0","year":2023},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.654754Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:1fd8df7640099484d4aba7dcb9eb96cecdfa585600e88589b69e581572385e6c","observation_id":"247d30c5-9c69-47c7-80c0-bc2f11851cd4","resolution":{"observed_at":"2026-08-07T13:50:45.251426Z","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":"2026-08-07T13:50:44.967430Z","title":"Amplitude-phase recombina- tion: Rethinking robustness of convolutional neural networks in frequency domain","venue":null,"work_id":"d99dfff7-e735-41ce-b6c8-017b91ff825b","year":2021},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.736696Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:0aec5271e83139dc280380d1f002627e01743f49f8b03ad2c34ed585461546c5","observation_id":"a8222109-6bc2-48b4-9f33-9225f4444836","resolution":{"observed_at":"2026-08-07T13:50:45.059790Z","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":"2026-08-07T13:50:44.734676Z","title":"Binaryconnect: Training deep neural networks with binary weights during propagations","venue":null,"work_id":"12f43e41-efef-4240-a0a8-196110a3db35","year":2015},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:33.868242Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:a9d2288d2cd391715d013bf28346dfc739587fd1765e7060b321c78701c56db9","observation_id":"23049aad-c2cb-498e-8f87-e830802cafdc","resolution":{"observed_at":"2026-08-07T13:50:44.862215Z","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":"2026-08-07T13:50:44.553692Z","title":"Imagenet: A large-scale hierarchi- cal image database","venue":null,"work_id":"53bfc143-10ce-4f9a-96d8-90c1b2088f3f","year":2009},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.008412Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:a177857cb2713d7b869a761e40ca671f6153c242b9efae5e83c74c7ca281d8de","observation_id":"b76fe18f-5ac7-4808-972b-933fe338b219","resolution":{"observed_at":"2026-08-07T13:50:44.627699Z","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":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-10T19:01:35.604774Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T13:50:34.125519Z","title":"Learned step size quantization.arXiv preprint arXiv:1902.08153, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.125519Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:389c17b274d32d96b2b60380cb09cec91723c7e7f5126678e83a227f7cc2dab9","observation_id":"71d6a732-72b7-470d-b92c-21e7eb3600e3","resolution":{"observed_at":"2026-08-07T13:50:34.125519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01412","last_updated":"2021-04-29T16:44:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-03T19:02:10Z","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01412","snapshot_observed_at":"2026-08-07T13:50:34.217944Z","title":"Sharpness-aware minimiza- tion for efficiently improving generalization.arXiv preprint arXiv:2010.01412, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.217944Z"},"links":{"cited_paper":"/paper/2010.01412","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:c758f3c1332fed6851696f784889d4b417d7ecf92fe421b5b1b963aa45cb457f","observation_id":"f9ab9b7d-ad7b-49e0-959d-1e8318e7f1d3","resolution":{"observed_at":"2026-08-07T13:50:34.217944Z","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":"2026-08-07T13:50:44.343804Z","title":"A survey of quantization methods for efficient neural network inference","venue":null,"work_id":"1931e5a9-1632-4c75-a5f0-d263e644d079","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.333361Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:6c2f441bc15802c3f7493516d9126bbab2095fc8eb490ec094d9894f98965368","observation_id":"4c3ec1e9-1951-4c73-9cf3-4fdb409bad05","resolution":{"observed_at":"2026-08-07T13:50:44.445107Z","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":"2026-08-07T13:50:44.076298Z","title":"Note: Robust continual test-time adaptation against temporal corre- lation.Advances in Neural Information Processing Systems, 35:27253–27266, 2022","venue":null,"work_id":"4904695d-b1f7-4b0f-89df-89c8e238309f","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.424528Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:7a683df6dbcff85ecbcf5e2605431f579c5cb82507531f7a79364b58fedac103","observation_id":"401efc12-87f8-4b1e-97aa-485413f09264","resolution":{"observed_at":"2026-08-07T13:50:44.166574Z","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":"2026-08-07T13:50:43.803295Z","title":"Sotta: Robust test-time adaptation on noisy data streams.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"49ce08d8-4d55-462d-b6a5-1784065202cd","year":2024},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.526487Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:2eb54d5ca16206c26634aa7580894db1d2d68d5816390dda6065f8abdf3a1b43","observation_id":"a341f2e7-3563-45af-af20-7cc1cc279e82","resolution":{"observed_at":"2026-08-07T13:50:43.997292Z","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":"2026-08-07T13:50:43.600324Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"54d33abb-e89f-4f06-9910-6886f8e7161c","year":2016},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.630829Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:4aec07f1c56e9d07184a835f67f14a74ca4e3d4556aa0891891c7b59ad80cb7f","observation_id":"cb2a48e2-7edf-4fde-9e2e-228268136e9a","resolution":{"observed_at":"2026-08-07T13:50:43.725172Z","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":"2026-08-07T13:50:43.335293Z","title":"Identity mappings in deep residual networks","venue":null,"work_id":"33e0f970-e8b3-4242-9fb3-91fa795869f1","year":2016},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.711619Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:bfaa17ef5e08e8852b7ca2712cee74a429d7df50b92584010306124ea34e8f28","observation_id":"bc74a24f-43bf-4d4d-9f7a-66fa4b0ac587","resolution":{"observed_at":"2026-08-07T13:50:43.441521Z","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":"1903.12261","last_updated":"2019-03-28T20:56:37Z","snapshot_observed_at":"2026-08-09T13:36:49.416146Z","submitted_at":"2019-03-28T20:56:37Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.12261","snapshot_observed_at":"2026-08-07T13:50:34.781054Z","title":"Benchmark- ing neural network robustness to common corruptions and perturbations.arXiv preprint arXiv:1903.12261,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.781054Z"},"links":{"cited_paper":"/paper/1903.12261","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:30e66aa7e5b1b94e6f02649323b602f9bf01785077f58e370527f38938fe95d1","observation_id":"41ff5cf6-4bcd-460d-9a12-0bbcdb7c2cf9","resolution":{"observed_at":"2026-08-07T13:50:34.781054Z","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":"2026-08-07T13:50:43.136958Z","title":"The many faces of robustness: A critical analysis of out- of-distribution generalization","venue":null,"work_id":"062ef0cc-9dee-4497-8a28-3638c8211efe","year":2021},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.856195Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:85264acf809d631c45f3a90972ebecba223ca97fb48271805e752c09cfe2a3a0","observation_id":"738d28ff-d512-45dc-a820-c1ca42a524d9","resolution":{"observed_at":"2026-08-07T13:50:43.233915Z","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":"2026-08-07T13:50:42.937583Z","title":"Searching for mobilenetv3","venue":null,"work_id":"3189694f-f1ce-4595-a277-4b8403cd2ed1","year":2019},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.941661Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:89ec6ed6a975466c7385ef8d22a89f20a4b2d4543b21113ef4e84e70afef40dd","observation_id":"44d9156d-71cb-4d20-88ee-6655b07fa552","resolution":{"observed_at":"2026-08-07T13:50:43.033191Z","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":"2026-08-07T13:50:42.751074Z","title":"Daformer: Improving network architectures and train- ing strategies for domain-adaptive semantic segmen- tation","venue":null,"work_id":"fd2c8b86-8301-4369-88ee-8c211151207b","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.979252Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:41e5f444da3f5ba2ee037826ce724527e63f75ad4c24ee7ee69aaa461610cb6a","observation_id":"f6734c4e-2338-473f-a5cb-fe66f32d5075","resolution":{"observed_at":"2026-08-07T13:50:42.842906Z","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":"2026-08-07T13:50:42.556838Z","title":"Fsdr: Frequency space domain randomiza- tion for domain generalization","venue":null,"work_id":"0e40ad85-eedf-45f6-8a39-06857b744597","year":2021},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.031614Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:d7f57e6f354dffbe813f1d042ae8435c74c43156779234f386409d03d2aaf5d6","observation_id":"e4cd9cb0-9bc8-4622-a663-1885ac791475","resolution":{"observed_at":"2026-08-07T13:50:42.648832Z","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":"2402.07059","last_updated":"2024-02-10T22:20:37Z","snapshot_observed_at":"2026-08-13T04:21:56.149660Z","submitted_at":"2024-02-10T22:20:37Z","title":"Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm Surveillance","version":1},"cited_work":{"arxiv_id":"2402.07059","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.07059","snapshot_observed_at":"2026-08-07T13:50:37.883541Z","title":"Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm Surveillance","venue":"cs.CV","work_id":"f954c5ec-f2d8-4fb0-89dd-fc635eb9e399","year":2024},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.084963Z"},"links":{"cited_paper":"/paper/2402.07059","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:608f61e40f37d2f064e3b79a9c74b8743ab331481d2c9cff4d51c0fed941fe08","observation_id":"08c472fa-627d-46b7-97f1-586c28013657","resolution":{"observed_at":"2026-08-07T13:50:38.050955Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2410.06020","last_updated":"2025-06-27T01:42:45Z","snapshot_observed_at":"2026-08-12T22:28:11.452788Z","submitted_at":"2024-10-08T13:21:48Z","title":"QT-DoG: Quantization-aware Training for Domain Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.06020","snapshot_observed_at":"2026-08-07T13:50:35.138190Z","title":"Qt- dog: Quantization-aware training for domain general- ization.arXiv preprint arXiv:2410.06020, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.138190Z"},"links":{"cited_paper":"/paper/2410.06020","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:8ae8aa6347b268b78f59aefd25353de32c0cc156cc929132fb6cd7f0d4cbd167","observation_id":"27d179e0-e744-4247-95b2-327123eb62c1","resolution":{"observed_at":"2026-08-07T13:50:35.138190Z","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":"2026-08-07T13:50:42.415925Z","title":"Neural network quantization with scale- adjusted training","venue":null,"work_id":"ab20153a-a91f-4fe7-9188-f1a9bcba94a9","year":2020},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.231825Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:1c7ab1aa1a33d11a1fd853fdc98e252edec8e5bf6ffbb603c247366204c2a0e7","observation_id":"baa27e73-ae05-4388-b688-b7c843574fe5","resolution":{"observed_at":"2026-08-07T13:50:42.476293Z","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":"2026-08-07T13:50:42.244863Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"251f78aa-5255-4c78-a972-780d2de327ed","year":2009},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.333755Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:77d1347170382bbdb64ec5eb4517c5457a0990b131e4e4ac4a2ceaac0466e788","observation_id":"b0a64e7d-c585-4b9d-b825-d6ed8061985c","resolution":{"observed_at":"2026-08-07T13:50:42.313414Z","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":"2026-08-07T13:50:42.053058Z","title":"Visualizing the loss landscape of neural nets.Advances in neural information process- ing systems, 31, 2018","venue":null,"work_id":"ee926e32-9b89-4d0b-af15-e3c34179594e","year":2018},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.422255Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:f3693c4e66a920a511f8ce05603f8b1254b42be6f01ec6fa9c189f5ee5238647","observation_id":"1ccf94bb-8f46-4823-a642-2073258e2147","resolution":{"observed_at":"2026-08-07T13:50:42.158641Z","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":"2026-08-07T13:50:41.930756Z","title":"The norm must go on: Dynamic unsupervised domain adaptation by normalization","venue":null,"work_id":"7f81ec96-ac63-4db5-bdc5-dde65c84f812","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.517931Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:dba294df9fc287df76fa84bd7cc2df41fefb6492d30029369ff23d6ed5f3874b","observation_id":"42a69a13-0f71-4f89-95a8-721125c8536a","resolution":{"observed_at":"2026-08-07T13:50:41.977312Z","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":"2006.10963","last_updated":"2021-01-14T21:11:06Z","snapshot_observed_at":"2026-08-06T05:58:45.817385Z","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":"2026-08-07T13:50:35.659801Z","title":"Evaluating prediction-time batch normal- ization for robustness under covariate shift.arXiv preprint arXiv:2006.10963, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.659801Z"},"links":{"cited_paper":"/paper/2006.10963","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:45bb7f881c77795b630a2c6f50432338251cd9ee115cb4272b36256810630966","observation_id":"8c281d2e-f855-43ee-9965-8783ff20156b","resolution":{"observed_at":"2026-08-07T13:50:35.659801Z","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":"2026-08-07T13:50:41.721820Z","title":"Efficient test-time model adaptation without forget- ting","venue":null,"work_id":"ae9ee802-f544-4871-abcc-5440c115da5e","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.724547Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:7f295b81d15587119f6725731501431360ecaf5dbd24b064d70c545e56236eed","observation_id":"21774c06-8e05-43ff-9753-eaf4c5423a12","resolution":{"observed_at":"2026-08-07T13:50:41.825030Z","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":"2302.12400","last_updated":"2023-02-24T02:03:41Z","snapshot_observed_at":"2026-08-13T12:38:22.643623Z","submitted_at":"2023-02-24T02:03:41Z","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12400","snapshot_observed_at":"2026-08-07T13:50:35.818062Z","title":"Towards stable test-time adaptation in dynamic wild world.arXiv preprint arXiv:2302.12400, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.818062Z"},"links":{"cited_paper":"/paper/2302.12400","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:80d07d0aeba7f018a7875d5e1345f25bce863815f12474302d49253b84d42a42","observation_id":"b99b8908-80b9-4145-a398-fcbc48d532e2","resolution":{"observed_at":"2026-08-07T13:50:35.818062Z","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":"2026-08-07T13:50:41.455665Z","title":"Improving robustness against common corruptions by covariate shift adaptation.Advances in neural infor- mation processing systems, 33:11539–11551, 2020","venue":null,"work_id":"16b288d2-88e6-4435-892a-16563b69313a","year":2020},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:35.925795Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:2dd9525bdd0021b94d4640609350f7b1849b279272c139c4f584b3e8255d5720","observation_id":"bedac2ce-d1ab-472d-9a52-dd17d70ee997","resolution":{"observed_at":"2026-08-07T13:50:41.557346Z","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":"2026-08-07T13:50:41.331817Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":"a2773590-2781-4775-b604-77506d9bdcf5","year":2019},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.027060Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:1db22f5835acbf5793883900897b48f3267f6e99b09509c2442dafdaccdc4fcf","observation_id":"fdc424b6-1162-4ffa-ab35-5af93da758fe","resolution":{"observed_at":"2026-08-07T13:50:41.387878Z","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":"2026-08-07T13:50:41.135975Z","title":"Visu- alizing data using t-sne.Journal of machine learning research, 9(11), 2008","venue":null,"work_id":"7a45e383-7b2d-46ce-bea0-1da3b0881c08","year":2008},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.125534Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:a6879d1012a55c8f80fa7d5c998456898e38b3e313c87c5983220a199001171f","observation_id":"ac92e604-bfb1-45e3-85a7-cf05c8a39fbf","resolution":{"observed_at":"2026-08-07T13:50:41.212623Z","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":"2006.10726","last_updated":"2021-03-18T17:58:01Z","snapshot_observed_at":"2026-07-06T09:30:32.320227Z","submitted_at":"2020-06-18T17:55:28Z","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10726","snapshot_observed_at":"2026-08-07T13:50:36.186179Z","title":"Tent: Fully test-time adaptation by entropy minimization.arXiv preprint arXiv:2006.10726, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.186179Z"},"links":{"cited_paper":"/paper/2006.10726","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:434c68d46a70b5763310d137aedaed450c80fb3651d9b871142ee743a87ae529","observation_id":"233b2473-73d7-43c2-857d-c4d8f1affe49","resolution":{"observed_at":"2026-08-07T13:50:36.186179Z","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":"2026-08-07T13:50:40.960653Z","title":"Learning robust global representations by penalizing local predictive power.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":"0beaa395-d9b2-4daa-8850-7d62a7185d91","year":2019},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.256581Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:c614a690870ffa95924188671b88f54bc315d2def6a608b3f2a0bebe81608a42","observation_id":"e272d6ce-a9fd-40fc-beae-930648f7d425","resolution":{"observed_at":"2026-08-07T13:50:41.061399Z","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":"2026-08-07T13:50:40.762797Z","title":"High-frequency component helps explain the generalization of convolutional neural networks","venue":null,"work_id":"e042e419-e177-45d7-b200-26a3e5857505","year":2020},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.344308Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:a749213911bbf8896b01d6593ede40c1418657361f119226070935645a933131","observation_id":"57194cac-fc3a-49a1-a1cd-2fe386ceff02","resolution":{"observed_at":"2026-08-07T13:50:40.849009Z","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":"2026-08-07T13:50:40.581664Z","title":"Generalizing to unseen do- mains: A survey on domain generalization.IEEE transactions on knowledge and data engineering, 35 (8):8052–8072, 2022","venue":null,"work_id":"97222e1d-0db2-45af-b00d-9bdf1cfd19a4","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.427016Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:1f9e64e6e70c63820b0d76fc2dbb5dc7a8b098b8a2fd46aed07801a4a3600b6f","observation_id":"24996819-0854-44ce-bff9-be1b7d778355","resolution":{"observed_at":"2026-08-07T13:50:40.691591Z","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":"2026-08-07T13:50:40.434188Z","title":"Continual test-time domain adaptation","venue":null,"work_id":"4af8f8fc-533d-4156-aa20-4ab9f591f160","year":null},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.525140Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:4cedf0b93d302f926f8ba7de8b62e17dcb68dca2e67a145348bd1b7f155f6fdd","observation_id":"6eae89a0-08d2-4fa9-9d87-6e1cbc1e6bbc","resolution":{"observed_at":"2026-08-07T13:50:40.496558Z","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":"2026-08-07T13:50:40.251642Z","title":"Efficienttrain: Exploring generalized curriculum learning for training visual backbones","venue":null,"work_id":"ad061d30-8750-49e4-b53f-3b095f723a36","year":2023},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.586281Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:394143706de56f33e2d1ca464ae11b076e21bc7cb49f4e3508b7d427af7a0830","observation_id":"954f1646-94f2-48dc-910f-041b698b5673","resolution":{"observed_at":"2026-08-07T13:50:40.357153Z","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":"2026-08-07T13:50:40.032120Z","title":"Learning in the fre- quency domain","venue":null,"work_id":"443d2eab-a4ee-48f2-8b1f-3ae520a2b727","year":2020},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.652244Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:41723130ad7771203c4980982e586cae486081aa367878fc52910277224099eb","observation_id":"1f161f55-d58b-4962-9ec0-5b040dee582a","resolution":{"observed_at":"2026-08-07T13:50:40.121278Z","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":"2026-08-07T13:50:39.859999Z","title":"A fourier-based framework for do- main generalization","venue":null,"work_id":"1ab66a40-ff8c-4129-93f0-3ea51b605d68","year":2021},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.712568Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:4b052b4db29581ae9f6b51ad57ae13d9bc1447c8d2f594565f600141da690f62","observation_id":"38fd1400-4879-4964-8cbc-5d893c7c9cf2","resolution":{"observed_at":"2026-08-07T13:50:39.953592Z","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":"2026-08-07T13:50:39.653502Z","title":"Fda: Fourier do- main adaptation for semantic segmentation","venue":null,"work_id":"57032605-47a3-47a3-879f-7b581dd99f27","year":2020},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.759090Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:9e105f97d5f878adccf8be0798d1e33621a63cb985fe9a87aba3faa393de54d9","observation_id":"91d81ea0-c600-42b5-87ba-c0632e56b1af","resolution":{"observed_at":"2026-08-07T13:50:39.724400Z","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":"2026-08-07T13:50:39.382910Z","title":"A fourier per- 10 spective on model robustness in computer vision.Ad- vances in Neural Information Processing Systems, 32,","venue":null,"work_id":"2830eb58-1779-4570-aa7c-7de13de30e63","year":null},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.816236Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:412db86aa2fcbc6674fa59026ac12dbc01ce6098b9d1fe342771f5da64ae312a","observation_id":"3c92e95a-3ffa-4b3f-8efb-a6754a9a2a7b","resolution":{"observed_at":"2026-08-07T13:50:39.499708Z","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":"2026-08-07T13:50:39.169044Z","title":"Adapt-net: A unified ob- ject detection framework for mobile augmented real- ity.IEEE Access, 2024","venue":null,"work_id":"fcd78ef4-da3d-4951-8b0a-9631b8cd0e81","year":2024},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.888268Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:e4010675c7ad8f79d98798d2e51e10b83f306ab1c9a4d4573083c0f1a2c06e85","observation_id":"6c15b53c-08ad-473d-9106-f5ebe26fa752","resolution":{"observed_at":"2026-08-07T13:50:39.310784Z","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":"2026-08-07T13:50:38.830477Z","title":"Lq-nets: Learned quantization for highly accurate and compact deep neural networks","venue":null,"work_id":"1e263056-aae4-4552-a6ea-743112f5fef3","year":2018},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:36.980101Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:b674cfecf758d14413ff6d77d9aa8149df46b4c862f545c9acb56e13c7676943","observation_id":"2397c9a8-6363-41c8-9c02-1292942af991","resolution":{"observed_at":"2026-08-07T13:50:39.005760Z","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":"2206.05916","last_updated":"2022-06-13T06:11:21Z","snapshot_observed_at":"2026-08-13T15:25:09.517825Z","submitted_at":"2022-06-13T06:11:21Z","title":"Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.05916","snapshot_observed_at":"2026-08-07T13:50:37.074587Z","title":"Why quantization improves generalization: Ntk of binary weight neural networks.arXiv preprint arXiv:2206.05916, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:37.074587Z"},"links":{"cited_paper":"/paper/2206.05916","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:e10b16d6f2d73baa917f75912fa2453ab75146cd0ead5ade8e80a8f54dcdfa12","observation_id":"ecb783f7-0580-49a8-964a-2311f51648a5","resolution":{"observed_at":"2026-08-07T13:50:37.074587Z","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":"2026-08-07T13:50:38.480478Z","title":"Memo: Test time robustness via adaptation and aug- mentation.Advances in neural information processing systems, 35:38629–38642, 2022","venue":null,"work_id":"2e7c0869-619b-409f-af80-e417acd24226","year":2022},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:37.144641Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:65f3f371a13e373e4099897bf5b3ac9299850d7b22d2b0ddbe312e43dd90005a","observation_id":"80965089-71c0-414a-8e4e-aedd0a79155b","resolution":{"observed_at":"2026-08-07T13:50:38.628098Z","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":"2026-08-07T13:50:38.233462Z","title":"A review of single-source deep unsupervised visual domain adaptation.IEEE Trans- actions on Neural Networks and Learning Systems, 33 (2):473–493, 2020","venue":null,"work_id":"2f19ec5d-6d0c-4bfd-8e4d-1a6e4b830b40","year":2020},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:37.228798Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:9fb6f075b7cbbbfce96ae88f3d1769601ab64e9df5c40520fc17138b336db92f","observation_id":"01277e7c-aeae-4cfa-a935-b2b01de49df6","resolution":{"observed_at":"2026-08-07T13:50:38.362315Z","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":"1606.06160","last_updated":"2018-02-02T01:43:54Z","snapshot_observed_at":"2026-07-06T05:00:35.763958Z","submitted_at":"2016-06-20T15:02:31Z","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06160","snapshot_observed_at":"2026-08-07T13:50:37.294125Z","title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients.arXiv preprint arXiv:1606.06160,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:37.294125Z"},"links":{"cited_paper":"/paper/1606.06160","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:5cee5222cc49bc01df4d018cf95263c8b0d2cbd574b521f6a1864823a989a09f","observation_id":"c308a2ff-d656-4949-b78d-e10094e49960","resolution":{"observed_at":"2026-08-07T13:50:37.294125Z","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":"6521.0019","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:50:37.625720Z","title":"Experimental Details We use pre-activation [16] based ResNet [15] models","venue":null,"work_id":"493c6dc2-9e7b-4243-8d8d-893540a8cb91","year":null},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:37.376021Z"},"links":{"citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:66b0c3b55b4ca8b6425b08b818ae8f2c02d6218d421a0198ce7a07b93d22c1fe","observation_id":"aee9d3d7-99df-475a-a473-f0e7093e3365","resolution":{"observed_at":"2026-08-07T13:50:37.707409Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2505.20890","last_updated":"2025-05-27T08:33:04Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T03:31:33.154341Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":50},"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 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2505.20890."}