{"as_of":"2026-08-16T11:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e5eec52656457bf413e75fc93fe08fea8ce64843a1c10040e9d4df99088020a0","coverage":[{"denominator":71,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:31:54.320653Z","state":"measured"},{"denominator":71,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":71,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2505.12745/citation-record","integrity":"/paper/2505.12745/integrity","json":"/paper/2505.12745/citation-record.json","paper":"/paper/2505.12745"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:31:55.497912Z","title":"Ainsworth, Jonathan Hayase, and Siddhartha Srini- vasa","venue":null,"work_id":"8592f4e4-7ee4-418a-b247-1a38e56a87b4","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.001924Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:e44cf67628035a9eba6acd0ec39f29778a09b7bb50254840ad8236b21c1a4d85","observation_id":"107f3cc5-6b56-44cd-8fcb-03bf7bde8e14","resolution":{"observed_at":"2026-08-15T20:31:55.502339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.483736Z","title":"Geometric dataset dis- tances via optimal transport.Advances in Neural Information Processing Systems, 33:21428–21439, 2020","venue":null,"work_id":"f290e766-4e51-4f02-acc6-52eadd945331","year":2020},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.007132Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:4a30d1ed9e403abdd4a583a938580c46fba2f21b400d53b324cf5ab3c79cebeb","observation_id":"3151a901-2be6-4e88-801b-be22f97b20a6","resolution":{"observed_at":"2026-08-15T20:31:55.488359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.469265Z","title":"Guerrero Peña, Heitor Rapela Medeiros, Thomas Dubail, Eric Granger, and Marco Pedersoli","venue":null,"work_id":"99fefcf5-e524-4e8f-80bf-8477c27d36d1","year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.012627Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:cf6c43492dc650fb4ff226b98de933c6d87b42445df24bd314eaed6b82bf693a","observation_id":"8aa3d7c4-ce17-446a-82c3-cf0f5627a203","resolution":{"observed_at":"2026-08-15T20:31:55.473941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.455219Z","title":"Invariant risk minimization, 2019","venue":null,"work_id":"aaa0ca43-0b85-44e3-8154-07d158dcd32e","year":2019},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.017515Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:24d6c1035af4980db7519732f4a6fb043414f27a046388c5a7229d5350d8a7a2","observation_id":"8fcdaf91-10a5-4080-9cdb-f9a89387a701","resolution":{"observed_at":"2026-08-15T20:31:55.459674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.441166Z","title":"Ensemble of averages: Improving model selection and boosting performance in domain generalization.Advances in Neural Information Processing Systems, 35:8265–8277, 2022","venue":null,"work_id":"7c5c5ddf-188c-419f-b9c9-92534364c216","year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.022257Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:0ab999b7c01955568e23f886302c76a612a8770019aa2e4c244c46e8cb33c74b","observation_id":"f5c09cb6-eea2-41d6-95ce-57a925933d33","resolution":{"observed_at":"2026-08-15T20:31:55.445712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.426470Z","title":"A cookbook of self-supervised learning, 2023","venue":null,"work_id":"9f71598b-a194-40dc-ac29-18d45ae101cb","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.027077Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:2b8fdd5748a48a39f665878875ecd92be117c412cb68cf877a9188e467b0e519","observation_id":"ce605db7-b9cf-4f00-96d6-8b759e9466bd","resolution":{"observed_at":"2026-08-15T20:31:55.431411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.411867Z","title":"Knowledge distilla- tion: A good teacher is patient and consistent, 2022","venue":null,"work_id":"3c9c8d09-9e8b-4016-8608-b53ee970be1f","year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.031674Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:8649cc57dd52bcf54611fbb28fd27c23ad611d93332dfbf5305966a4ab9f726b","observation_id":"3351d500-f0db-43ea-bb47-d5cf91e71129","resolution":{"observed_at":"2026-08-15T20:31:55.416476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.397773Z","title":"Weak-to-strong generalization: Eliciting strong capabilities with weak supervision, 2023","venue":null,"work_id":"dcc077af-7276-4311-b7c4-ed34d8992fa4","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.036771Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:94c701b64f198286d63d0c4620bf631de8385e9ea783a88b592ba5779d8ef21c","observation_id":"fd80aeb4-3dba-40eb-81f0-1ca285ce19d8","resolution":{"observed_at":"2026-08-15T20:31:55.402461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.10789","last_updated":"2022-07-22T06:16:48Z","snapshot_observed_at":"2026-08-15T15:49:48.758451Z","submitted_at":"2022-03-21T08:07:46Z","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.10789","snapshot_observed_at":"2026-08-15T20:31:54.041421Z","title":"Domain Generalization by Mutual-Information Reg- ularization with Pre-trained Models.arXiv e-prints, art","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.041421Z"},"links":{"cited_paper":"/paper/2203.10789","citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:231a0e9afbcc516ee6f2730eb110d0f9dbbd5d8ce90cc693fb2f63dcb5ca3093","observation_id":"f8bb760d-3a78-49e7-9e72-a0f33ff93c15","resolution":{"observed_at":"2026-08-15T20:31:54.041421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03044","last_updated":"2022-04-06T18:54:48Z","snapshot_observed_at":"2026-08-14T17:34:36.101910Z","submitted_at":"2022-04-06T18:54:48Z","title":"Fusing finetuned models for better pretraining","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03044","snapshot_observed_at":"2026-08-15T20:31:54.046261Z","title":"Fusing finetuned models for better pretraining.arXiv preprint arXiv:2204.03044, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.046261Z"},"links":{"cited_paper":"/paper/2204.03044","citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:4b9982195eac8f18a22243744c73656b9215340846fb882ac2a432d46293707d","observation_id":"cdb9f414-8cb1-4aed-bcc8-1c3fe611c722","resolution":{"observed_at":"2026-08-15T20:31:54.046261Z","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":"2026-08-15T20:31:55.384052Z","title":"Randaugment: Practical automated data augmentation with a reduced search space","venue":null,"work_id":"646a741d-cc7a-4187-9b1a-3e5d236a0200","year":2020},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.051205Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:9d610020f553be391b40c5711cf94251478fd7b2d85cf4298ddb11baf997e6b4","observation_id":"532c301a-d955-44f2-95c4-aab0a04a497c","resolution":{"observed_at":"2026-08-15T20:31:55.388505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.370572Z","title":"The mnist database of handwritten digit images for machine learning research.IEEE Signal Processing Maga- zine, 29(6):141–142, 2012","venue":null,"work_id":"fff08300-8f0a-4766-8018-a5562fb19cdb","year":2012},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.056015Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:5d5ae6f408abdaac00675bc88b36400b2156d2cad1745961eb6f0e3e84290b92","observation_id":"e325f9f9-53e0-43c6-a60c-1d58e5129183","resolution":{"observed_at":"2026-08-15T20:31:55.375009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19774","last_updated":"2024-09-29T20:52:50Z","snapshot_observed_at":"2026-08-14T16:31:41.896657Z","submitted_at":"2024-09-29T20:52:50Z","title":"Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization","version":1},"cited_work":{"arxiv_id":"2409.19774","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.19774","snapshot_observed_at":"2026-08-15T20:31:54.580298Z","title":"Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization","venue":"cs.CV","work_id":"fabbf4db-bcc4-4ac2-b99d-9dfd4823eb2d","year":2024},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.060457Z"},"links":{"cited_paper":"/paper/2409.19774","citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:92cef37d46d8f537431ac17ff578922e3e6dac9422d6cb465b3a340332bb815e","observation_id":"b1b8a956-824b-4180-8c29-098c263362c7","resolution":{"observed_at":"2026-08-15T20:31:54.585468Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06296","last_updated":"2022-07-05T11:40:49Z","snapshot_observed_at":"2026-08-13T17:54:21.865215Z","submitted_at":"2021-10-12T19:28:48Z","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06296","snapshot_observed_at":"2026-08-15T20:31:54.065209Z","title":"The role of permutation invariance in lin- ear mode connectivity of neural networks.arXiv preprint arXiv:2110.06296, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.065209Z"},"links":{"cited_paper":"/paper/2110.06296","citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:b4b2faaf3befb1fdb502ffad021e3dd482263b1327ef877d3076392846ff8502","observation_id":"1184e695-3ad2-4780-874c-ad85e364148a","resolution":{"observed_at":"2026-08-15T20:31:54.065209Z","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":"2026-08-15T20:31:55.357236Z","title":"https://torchvision.mlverse.org, https://github.com/mlverse/torchvision","venue":null,"work_id":"75fc03a1-c015-4e51-8979-0ce71183911b","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.070050Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:af64fa3eddeea6bd342fe785748f4edb1d203619b443f1e1e3329ddd8df9a427","observation_id":"9ac9e451-f2fd-448c-9cd2-51158e4c91b9","resolution":{"observed_at":"2026-08-15T20:31:55.361634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.343674Z","title":"Adversarially adaptive normal- ization for single domain generalization","venue":null,"work_id":"b6a0ad49-1d56-4123-8d5f-710a81eee98a","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.074439Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:9608e98a86f8de8e4b8a2f89efa0853e06e3c58d11427a4504870e5682f35c15","observation_id":"ba6157d3-4371-4d36-aad0-1fbd1524cead","resolution":{"observed_at":"2026-08-15T20:31:55.348257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.330083Z","title":"Unbiased met- ric learning: On the utilization of multiple datasets and web images for softening bias","venue":null,"work_id":"28a2a469-d80d-4f3a-8126-d6be69657ed4","year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.078961Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:d7e026e377d8f9887510f5f3e1cdef213ab6e4da81ff22097772552dab18029b","observation_id":"74c061c0-75d3-42f7-b262-ca49ff4ebeb6","resolution":{"observed_at":"2026-08-15T20:31:55.334568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.316217Z","title":"Linear mode connectivity and the lottery ticket hypothesis","venue":null,"work_id":"20ab025d-9663-49ed-b534-8feb6dcfbc24","year":2020},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.083627Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:7fb47cd2742f89ad765c7edf673fbec17ef06199ffefdef37847cec6adbd9cd6","observation_id":"b9cbad7f-3870-41ea-9404-8418876266ae","resolution":{"observed_at":"2026-08-15T20:31:55.320753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.302031Z","title":"Unsupervised domain adaptation by backpropagation","venue":null,"work_id":"72635252-940f-4d20-baf5-d70ef9ad9005","year":2015},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.087955Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:26f4ea5afe8bc68b64d81cba8b47d14f1ef2bcbff15b68f1ad06c2c489c4f182","observation_id":"662ef89e-080f-4d6c-ae03-342b3dfb953d","resolution":{"observed_at":"2026-08-15T20:31:55.306431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.287891Z","title":"Domain-adversarial training of neural networks.Journal of Machine Learning Research 17 (2016) 1-35, 2015","venue":null,"work_id":"75b2b69e-f6b8-4184-81c5-8a13a5d0c76c","year":2016},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.092681Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:7f1dab201a3b5b8ee69c57ea3dd4bd9dc1395cff2d383953454746f1978ad433","observation_id":"cfafda48-cdcc-467c-ae04-58b57a861a48","resolution":{"observed_at":"2026-08-15T20:31:55.292739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.273958Z","title":"Loss surfaces, mode connectivity, and fast ensembling of dnns.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":"2d3df336-7df5-4019-a52d-b15ecb310fe0","year":2018},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.097158Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:103e4a2cc5be045f7eceb8ec1bad2a01264fa1c1e68e86a25964752e12f7300d","observation_id":"40196062-047e-4898-8d65-82e20fc7a5e3","resolution":{"observed_at":"2026-08-15T20:31:55.278783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.260362Z","title":"Maybank, and Dacheng Tao","venue":null,"work_id":"94351ccf-0b8c-46d8-92e3-999dad3d42c3","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.101581Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:bfc2d1c4fe4c2913a0e0f097f65a4b1158e3ff0a076126a92d25789d42047777","observation_id":"80e3f74f-696a-4391-8eb1-062681ae1e6a","resolution":{"observed_at":"2026-08-15T20:31:55.264765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.246509Z","title":"Bootstrap your own latent-a new approach to self-supervised learning.Advances in neural information processing systems, 33:21271–21284, 2020","venue":null,"work_id":"de95c868-f86b-4fae-ac1b-c3684ccf04fe","year":2020},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.106007Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:35b9a55a44464bf338afaa46a4f1f9dc0fda0df2ac94dac28c5c223dd69a6bef","observation_id":"e11c2ba8-2546-44c1-bf3c-3ef586c0806a","resolution":{"observed_at":"2026-08-15T20:31:55.251133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.231978Z","title":"Understanding and improving the role of projection head in self-supervised learning, 2022","venue":null,"work_id":"fb8a4391-191b-4276-8d7c-fdbf9b8886b3","year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.110423Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:8e7b6c8dc56ef22fa69ffa6e1a358786ce79b084f01e4a8a195d994abea946d3","observation_id":"e8865ef0-fd1f-49c5-9357-487626a13831","resolution":{"observed_at":"2026-08-15T20:31:55.236907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.217827Z","title":"Distilling the knowledge in a neural network, 2015","venue":null,"work_id":"7939f565-6931-4698-acd3-bdb82ee53fe2","year":2015},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.114754Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:f181b0cba03bb28ae4d2c2d50541729e57a5c4561babae25a9181793539f5fc8","observation_id":"441965a0-4f60-492b-8843-d4394a183caf","resolution":{"observed_at":"2026-08-15T20:31:55.222689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.203599Z","title":"Learning deep representations by mutual information estimation and maximization","venue":null,"work_id":"36c44d05-f957-4cf8-8f08-04aa20114eb6","year":2019},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.119165Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:cac8912cd4ebcf8dc7802ed557c1eb2d1bbe3106b67b01616ee399c69e231621","observation_id":"a5d9fc3a-e2fe-4bfa-a0c6-3f8530de5d51","resolution":{"observed_at":"2026-08-15T20:31:55.208189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.188972Z","title":"Towards the generalization of contrastive self-supervised learning, 2021","venue":null,"work_id":"d124da3f-fc98-4b75-8370-9526e4d331be","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.123672Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:c4e2be964cc62cb6ca56d5ec0e845b22cef45025027861fdda1f54152d70ea21","observation_id":"d67afc7c-ed4e-4c27-bfc9-486af7e3154f","resolution":{"observed_at":"2026-08-15T20:31:55.193774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05407","last_updated":"2019-02-25T14:18:11Z","snapshot_observed_at":"2026-08-14T19:36:09.254749Z","submitted_at":"2018-03-14T17:09:27Z","title":"Averaging Weights Leads to Wider Optima and Better Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05407","snapshot_observed_at":"2026-08-15T20:31:54.128133Z","title":"Averaging weights leads to wider optima and better generalization.arXiv preprint arXiv:1803.05407, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.128133Z"},"links":{"cited_paper":"/paper/1803.05407","citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:991415e196bd482f15f783f8e4a296292850d39975574aa5bec4fa560f632cd1","observation_id":"722ecd45-dfdc-4971-8bab-140c46310d57","resolution":{"observed_at":"2026-08-15T20:31:54.128133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03094","last_updated":"2024-05-06T14:32:35Z","snapshot_observed_at":"2026-08-16T01:59:24.176365Z","submitted_at":"2023-04-06T14:22:02Z","title":"PopulAtion Parameter Averaging (PAPA)","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03094","snapshot_observed_at":"2026-08-15T20:31:54.133109Z","title":"Population parameter averaging (papa).arXiv preprint arXiv:2304.03094, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.133109Z"},"links":{"cited_paper":"/paper/2304.03094","citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:0df301b485f06035a3e4bce38a0722a4c43c93a90aa0d9700dffb6adef285c4a","observation_id":"0de100b4-ee41-46b4-9f76-d96077d04381","resolution":{"observed_at":"2026-08-15T20:31:54.133109Z","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":"2026-08-15T20:31:55.173909Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":"b73275fd-41a0-4617-8780-eeaa19c7e0e3","year":2015},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.137793Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:f53a306a147e3067223ce00a7f21668679d406c8c7bd996eef8ea64dfd88ea7e","observation_id":"1f37a547-e43b-4c84-a1bf-f558ae7eb361","resolution":{"observed_at":"2026-08-15T20:31:55.178767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.157286Z","title":"Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, and Dy- lan Paiton","venue":null,"work_id":"2bc16d10-69c0-4513-bf83-439d8e310b26","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.142238Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:f115d13c27d50eccfdd3f3083b4efb5f5b9b7d65b671eb27428926178aa4ba93","observation_id":"85409e0a-e911-4f0d-af72-6051329cdb49","resolution":{"observed_at":"2026-08-15T20:31:55.162700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.142840Z","title":"Springer Berlin Heidelberg, 2011","venue":null,"work_id":"58b9f6a2-491c-42b6-8702-6b253cd7feb6","year":2008},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.146864Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:36763df038e4933081768a1bf8716e6a8e5ba2dad3bc324a6c57d55990c3baba","observation_id":"7a88cd80-979f-4dc5-8a2f-a1f838d5b229","resolution":{"observed_at":"2026-08-15T20:31:55.147353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.128177Z","title":"Similarity of neural network representations revisited","venue":null,"work_id":"bf5800af-45bb-4328-963c-93aba88ae5c6","year":2019},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.151332Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:debe7b18c36a3b8ed5864c31e303c6400eb574db8d3492e11e6a7256f755febd","observation_id":"df5df0c4-c8f5-498e-9403-a951e064df18","resolution":{"observed_at":"2026-08-15T20:31:55.132915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.113090Z","title":"Im- agenet classification with deep convolutional neural networks","venue":null,"work_id":"465c3d99-2d61-408e-a887-622983faec53","year":2012},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.155959Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:acd038f33d26c27677563703b13c2772f7f8d25cbeeaed0f3ee8cdd15ac2f341","observation_id":"fbdb63ca-1d1c-488e-b584-b1befbea270d","resolution":{"observed_at":"2026-08-15T20:31:55.118290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.098622Z","title":"Fine-tuning can distort pre- trained features and underperform out-of-distribution","venue":null,"work_id":"fd307f5d-1b50-4301-869b-ffe2f5834634","year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.160590Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:ce9db37d3ea2d2d3affa8caafc86ddd8faaecf8a6a2cd56ec03a8c1a39176e6b","observation_id":"1266d7b8-6654-403c-9b92-062c8768da1f","resolution":{"observed_at":"2026-08-15T20:31:55.103397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.165092Z","title":"Adver- sarial examples in the physical world","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.165092Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:d9e2f86f69ab63e406cd4e6554732a5fdbbb02165e21010a3c6ba390f9524017","observation_id":"ff4d4d83-dd15-4756-99bb-302e74d79381","resolution":{"observed_at":"2026-08-15T20:31:54.165092Z","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":"2026-08-15T20:31:55.073202Z","title":"Le Cun, B","venue":null,"work_id":"be37c4eb-920c-4a9c-869c-430d91a26366","year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.169920Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:ca297113e6dc1ccc0ff59d92f2322bc544cf91513018a6bf2b189264928d59f8","observation_id":"68130e5a-0519-41b4-8a4f-dc6b5724da4b","resolution":{"observed_at":"2026-08-15T20:31:55.077705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.059201Z","title":"Deeper, broader and artier domain generaliza- tion","venue":null,"work_id":"0ecc87f8-ad11-42e4-839b-7f339f08371f","year":2017},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.174510Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:6a5187e83bbf36fc4d3dd00f4ebfbb85a957df50036546cac5cf57024bef3d47","observation_id":"b1e6964e-23d1-4b00-9417-bde5f2196cde","resolution":{"observed_at":"2026-08-15T20:31:55.063744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.044298Z","title":null,"venue":null,"work_id":"51cbb420-34c6-45a6-96eb-b70cf9714244","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.178881Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:6e95f05d9c1eacedb2f1ab6c78d0f83c1c6a3beeeefb5003f66f37bd81da9419","observation_id":"d5378936-8713-46ea-910c-bf571034ee80","resolution":{"observed_at":"2026-08-15T20:31:55.049253Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.028948Z","title":"SIMPLE: Specialized model- sample matching for domain generalization","venue":null,"work_id":"9e4ecd8a-ab9f-4fad-892b-e3acdff73e09","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.183179Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:2c4bb130ec8098fc2c580626143d9252aa78a2179e4d8fd2c36f877589fe0502","observation_id":"9b587e58-4c00-4a06-b460-90310e1189b4","resolution":{"observed_at":"2026-08-15T20:31:55.033864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:55.014023Z","title":"Mechanistic mode connectiv- ity","venue":null,"work_id":"819517c3-f7ce-42b7-8bc1-eea167e69fef","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.187775Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:d7ab7d9ef833da9477d6d8ae8400cf5fc98e3b8f86bd06822f9fe2b5ade58aa7","observation_id":"6e0d5407-5610-4c56-8306-ece873350905","resolution":{"observed_at":"2026-08-15T20:31:55.018920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08977","last_updated":"2024-12-11T16:18:16Z","snapshot_observed_at":"2026-08-15T19:32:23.881430Z","submitted_at":"2023-12-14T14:26:57Z","title":"Weighted Ensemble Models Are Strong Continual Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08977","snapshot_observed_at":"2026-08-15T20:31:54.192007Z","title":"Weighted ensemble models are strong continual learners.arXiv preprint arXiv:2312.08977, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.192007Z"},"links":{"cited_paper":"/paper/2312.08977","citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:09f75c3e748ecb63e5f3f159389e1ca3eefe36e4260a1f3496962c03c7306a2f","observation_id":"ba898e27-e9c8-48ec-9ef8-062ecba80af1","resolution":{"observed_at":"2026-08-15T20:31:54.192007Z","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":"2026-08-15T20:31:54.196604Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.196604Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:aa45058f76e4a0d5c49254048bbd884af35a4d653f51e36f79de554c3dce6f49","observation_id":"34f6903d-1b1c-4140-9c6d-6da34a278575","resolution":{"observed_at":"2026-08-15T20:31:54.196604Z","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":"2026-08-15T20:31:54.988623Z","title":"What is being transferred in transfer learning?Advances in neural information processing systems, 33:512–523, 2020","venue":null,"work_id":"264964c5-50da-4f97-b5e2-45414766b438","year":2020},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.201185Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:e8253376483422149a79bc6c9a361f3cf939c4ad095ba85f3545ac5e1a4aca9d","observation_id":"0bdc1740-890e-4914-98c8-385bac60d3a1","resolution":{"observed_at":"2026-08-15T20:31:54.993496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.974214Z","title":"Represen- tation learning with contrastive predictive coding, 2018","venue":null,"work_id":"df9725fe-ddd2-4ace-8517-8d32f736f658","year":2018},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.205349Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:48c5b628ea968fdeb1bf4ed73bd5e6cab0cbbe23e999e499c82ef829ac912c2b","observation_id":"97395f9d-73ea-4983-8fbc-74d0f863ba6d","resolution":{"observed_at":"2026-08-15T20:31:54.978910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.959462Z","title":"Estimation of entropy and mutual information","venue":null,"work_id":"249b56e4-df36-4f00-b5ff-69e079563b1f","year":2003},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.209779Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:f86197c034a3a3c659b6899062aadf501beffb937ec44a29960a71716701178b","observation_id":"3087b260-b067-4623-970e-5734d00d89a0","resolution":{"observed_at":"2026-08-15T20:31:54.964152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.944126Z","title":"On variational bounds of mutual infor- mation","venue":null,"work_id":"fd3fa2b6-49c9-4d95-b2d5-867a968e60a7","year":2019},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.214214Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:d1cdc0c50d86206ebc7afb1009b2151f1590a984b1e7a8ca8e9dc136f7b56cbe","observation_id":"5b5bb2b4-8516-4b50-b95d-1a0d5847a4a8","resolution":{"observed_at":"2026-08-15T20:31:54.949195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.928236Z","title":"Learning to learn single domain generalization","venue":null,"work_id":"ca97ff58-a759-4098-8098-06d27fb87269","year":2020},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.218497Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:69b89fa8e416411c1a65fff7e29d9a688447e77628a75b5fd6c40323433ba5f4","observation_id":"87b08db7-9cb6-4b6a-add1-46cc7dceb822","resolution":{"observed_at":"2026-08-15T20:31:54.933389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.914187Z","title":"Designing network design spaces","venue":null,"work_id":"4b1b01a8-e643-4671-a3d9-f0e945d363c4","year":2020},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.222672Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:430bed66ab489fd995f2bb5478cd1ae41bed3ca2a28e77ef5f646f02d7c9cc56","observation_id":"2f2c6941-d199-4492-8906-0adcc6d8fade","resolution":{"observed_at":"2026-08-15T20:31:54.918628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.899833Z","title":"Diverse weight averaging for out-of-distribution generaliza- tion","venue":null,"work_id":"92ba13a0-46cd-4d1f-a9bf-a417d8f0e17b","year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.227264Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:d1db748e47277af58c176b350edfc1dbd11c14cfe68f7ca0b8c1cc8c02d591d6","observation_id":"5ad52b2c-c7da-41f0-a247-229c928e1ac1","resolution":{"observed_at":"2026-08-15T20:31:54.904593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.885050Z","title":"Model ratatouille: Re- cycling diverse models for out-of-distribution generalization","venue":null,"work_id":"63922d0c-95fd-4457-a0f4-28c7e4eb9d9c","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.231808Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:25a74b0a9916a0eb421a7d427acbe487080a402f3b89bc10df1d4713867af6f9","observation_id":"28a7e7eb-09df-4b53-a30b-b3b8d272990f","resolution":{"observed_at":"2026-08-15T20:31:54.890030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.870744Z","title":"Rethinking content and style: Exploring bias for unsuper- vised disentanglement","venue":null,"work_id":"8fa0e84c-9d59-4737-81fc-4acdec301e41","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.236374Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:775b310f770d46a81bf234e0a7cb4acb343d79a45cd9b407040f74508b276d9c","observation_id":"b9f900b2-24d7-4508-a0c1-82724b05f4bb","resolution":{"observed_at":"2026-08-15T20:31:54.875365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.240588Z","title":"Berg, and Li Fei-Fei","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.240588Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:70f32584535e98471ed117804536c4ce269b3e1caf8e7ad54f2949a4fd0ad357","observation_id":"86980ccc-5aa6-4214-8a6a-c1358a90c298","resolution":{"observed_at":"2026-08-15T20:31:54.240588Z","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":"2026-08-15T20:31:54.846005Z","title":"A unified approach to domain incremental learning with memory: Theory and algorithm","venue":null,"work_id":"212980b2-d975-4af1-b75f-c5c93666e399","year":2024},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.245241Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:e25ba8a69d1339c21a874f4076255ece7ab28dcee3756c0b5bbe33da5b65db58","observation_id":"fd6a909a-4cb4-4962-8225-2f861b50da67","resolution":{"observed_at":"2026-08-15T20:31:54.850742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.832306Z","title":"Esti- mating and maximizing mutual information for knowledge distillation","venue":null,"work_id":"76c06957-f63d-4758-8109-6522d1ba25b9","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.249748Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:c8e74880fb250ed88600214e02cc9394e362fabf334b54c4e6de15dd48f21325","observation_id":"e37b2388-b90f-4b3f-97c4-0416ecba37bd","resolution":{"observed_at":"2026-08-15T20:31:54.836708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.818691Z","title":null,"venue":null,"work_id":"3866d72d-c859-4129-8c35-e72916169904","year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.254159Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:93c657119d4b055b120ecb2837a5f0b7fc62ebe7816713bd5bbb71e8e99eb466","observation_id":"27d2ee07-cad8-4fb0-aaf5-c2fd3fad2613","resolution":{"observed_at":"2026-08-15T20:31:54.823012Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.804391Z","title":"A note on connecting barlow twins with negative-sample-free contrastive learning, 2021","venue":null,"work_id":"cdbdc4f8-b4b1-42ac-b3a5-d568e705bb5e","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.258760Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:139056c19f0f780b3f10904798fe7ec2b6c8d5533ce23efbd442429ac58e7be1","observation_id":"c8b6205d-7ca0-4466-9aff-f7d094968eab","resolution":{"observed_at":"2026-08-15T20:31:54.808982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.789945Z","title":"Deep hashing network for unsupervised domain adaptation","venue":null,"work_id":"d4ff980e-ff28-4e44-9618-a3cbe6ba47b6","year":2017},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.262970Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:99f98c663cca99f87257a150adbd950dd360e5833cacceaf2d02b215a1850b85","observation_id":"bbd603ec-5a8a-4f47-b04d-8f424836222e","resolution":{"observed_at":"2026-08-15T20:31:54.794521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.775182Z","title":"Generalizing to unseen domains via adversarial data augmentation, 2018","venue":null,"work_id":"743d61fb-ad72-4379-9f47-59ba41bf08c1","year":2018},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.267017Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:ca13cc9d1f45d73b8a7f670c545f52c749c4e3c8ee48b72db0e3a12475cc4c46","observation_id":"b4a518cb-1eea-4d40-9aed-a6dd6ee4fe62","resolution":{"observed_at":"2026-08-15T20:31:54.780074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.760919Z","title":"Generalizing to unseen domains via adversarial data augmentation.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":"940fd2c1-f74d-4bfd-9d76-3255bae58824","year":2018},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.271461Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:ae39e1856705663ea787e73d356f870aae0733e546986e16fbf708dc046eba8e","observation_id":"2b6176ed-f635-4989-bcae-0e20795a9fd7","resolution":{"observed_at":"2026-08-15T20:31:54.765550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.746540Z","title":"Self-supervised learning with data aug- mentations provably isolates content from style.Advances in neural information processing systems, 34:16451–16467,","venue":null,"work_id":"2d113c0b-e5a9-4542-9e5f-97591ef2c263","year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.275709Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:866c1ef635e8969939626585f20b957c577ed09384554e9bd2cfc7227c2c1470","observation_id":"21bb2794-48fa-4067-8982-a8d3ce6a7751","resolution":{"observed_at":"2026-08-15T20:31:54.751246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.731876Z","title":"Meta convolutional neural networks for single domain generalization","venue":null,"work_id":"1bfa240d-774d-4d59-8847-2708371ce3ce","year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.280737Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:47db65889314ca835d4a8fd107614f7509a9326c3e4d9467a77005f8e5d47d23","observation_id":"fb5e6692-c11e-4618-a582-6015f38e65f6","resolution":{"observed_at":"2026-08-15T20:31:54.736609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.717586Z","title":null,"venue":null,"work_id":"760a7454-272f-435c-9144-37019afd5548","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.284956Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:6be45356f76f09550a5fc3e6feadd3c2b16bd6d31ba4244a31540d3c9e1083ae","observation_id":"fb911c60-1459-4cb1-8917-5620b271a7d6","resolution":{"observed_at":"2026-08-15T20:31:54.722022Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.701518Z","title":"A comprehensive survey of continual learning: Theory, method and application.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024","venue":null,"work_id":"ef658d41-bce2-4440-adaa-01cc0bdd7442","year":2024},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.289141Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:5a592503d3f7aafe8ff1446752f1d07c4838f8b4c0559558b0dc3f31e7210886","observation_id":"48d30c12-fc69-442e-a8c6-b53b6af38b39","resolution":{"observed_at":"2026-08-15T20:31:54.707178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.685867Z","title":"Learning to diversify for single domain generalization","venue":null,"work_id":"b87b8fab-c016-4375-be68-682d69a92d87","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.293385Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:70f7503a0286d44fb19aaefe3dbb853dee553f49c56be78a3a0efcb1c1f25043","observation_id":"08e078a6-f6b4-4a6b-b3c0-822dc19c3db1","resolution":{"observed_at":"2026-08-15T20:31:54.690388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.670595Z","title":"Wolpert and W.G","venue":null,"work_id":"4f21de20-27fa-42da-8f2f-7729cacb288c","year":1997},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.297554Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:9f183e63d9469dca9689981204ddacbb6f4b1f26082985cf88003210c4460bde","observation_id":"ee742c21-b7a6-4951-a668-f68654578501","resolution":{"observed_at":"2026-08-15T20:31:54.675200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.655829Z","title":"Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt","venue":null,"work_id":"d9282c61-9cb8-44dd-be80-d2c97dc4b470","year":2022},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.301554Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:5db37713c1bec4edf6d9b54d9188e5cad7392f988e7b21348df64938052ed1ff","observation_id":"b1fb2688-ef4b-4b74-ae64-be24be15fcd8","resolution":{"observed_at":"2026-08-15T20:31:54.660632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.641123Z","title":"Simde: A simple domain expansion approach for single-source domain generalization","venue":null,"work_id":"2eb9f1f3-889a-4d23-ad29-6d9f761ad7b9","year":2023},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.306423Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:6b8409c9090329cf786acc7d530037cd4462c3cf837740b7ed1b7dfce3dfdbdd","observation_id":"651cf350-1940-4462-aae7-245c7e1b4160","resolution":{"observed_at":"2026-08-15T20:31:54.645819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T20:31:54.626414Z","title":"Barlow twins: Self-supervised learning via redundancy reduction","venue":null,"work_id":"2e3ba2a9-905c-49de-afbb-33eec71b3ccd","year":2021},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.310893Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:7e3aa00d556e0b90f3954a94994c759d2672863c88bf3076fa9610fa2bf3cf0a","observation_id":"369ff001-20e7-453e-92d3-c01750c1eb02","resolution":{"observed_at":"2026-08-15T20:31:54.630968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"6647.4068","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:31:54.494938Z","title":"Can parameter-averaging proxy model snapshots without regular- ization create a robust regulator?","venue":null,"work_id":"7be2718e-dd64-48df-8233-6318a4001c33","year":2024},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.315296Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:957382ff036d9d833088d66deaaf697d1c90878a7c37043ce525aa34371f9217","observation_id":"5ec7ba2f-d00b-48d9-b948-0a4ff8fbae61","resolution":{"observed_at":"2026-08-15T20:31:54.503332Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"9015.8522","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:31:54.414752Z","title":"Y\" indicates the convolution method, and the","venue":null,"work_id":"fe57764d-5f15-40f3-a1e3-520c8a738d9d","year":null},"citing_paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T20:31:54.320653Z"},"links":{"citing_paper":"/paper/2505.12745"},"observation_digest":"sha256:2895ae48bbd53e53e228a9dba5b790bf38caf5e923c24e6171d8fa4d990e4ef7","observation_id":"80297ad0-6279-4fd8-907a-bce13b89f91f","resolution":{"observed_at":"2026-08-15T20:31:54.423194Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.12745","last_updated":"2025-05-19T06:01:11Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T20:25:18.233601Z","submitted_at":"2025-05-19T06:01:11Z","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization"},"reference_resolution":{"displayed":71,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":2,"verified_fuzzy":56},"total_outbound_references":71},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 0 inbound Pith citation observations for arXiv:2505.12745."}