{"as_of":"2026-08-18T22:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0f4fdfe7b6ebddf8201a51bfab13b160d6c41b52df671fd50a7958cb737ba13f","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:55:33.722924Z","state":"measured"},{"denominator":74,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":74,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.11702/citation-record","integrity":"/paper/2505.11702/integrity","json":"/paper/2505.11702/citation-record.json","paper":"/paper/2505.11702"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:55:33.475099Z","title":"Gradient flows: in metric spaces and in the space of probability measures","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.475099Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:dde1e7ed2beba1407d5e40a2683bd8282cae5875d1ac7dcf8fcfd67f9f46d5f8","observation_id":"1ba0c117-450f-4641-8d6c-175e0b6427b5","resolution":{"observed_at":"2026-08-15T20:55:33.475099Z","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":"2026-08-15T20:55:33.479012Z","title":"Wasserstein generative adversarial networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.479012Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:26d0e512ccadde2b7029d29ef4117b1763a98396c1ccd49e3650eb0bb40ec359","observation_id":"d36a9c88-86ed-4c8a-86b8-e26aa25564c7","resolution":{"observed_at":"2026-08-15T20:55:33.479012Z","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":"2026-08-15T20:55:33.482887Z","title":"Learning representations by maximizing mutual information across views","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.482887Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:31c63563021749052a4852542b5af2ac0cf2743cbff2901040f65ed18e33d97e","observation_id":"cad896cf-5fb8-4bfe-93aa-bb6abdc774ad","resolution":{"observed_at":"2026-08-15T20:55:33.482887Z","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":"2026-08-15T20:55:34.396283Z","title":"Wasserstein distributional robustness of neural networks","venue":null,"work_id":"094aab6b-af04-4a01-87df-ba937a03a2e1","year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.486235Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a17f58a2932524ea8517aecdc32c95dc3147562d011520bb4cc4ef10222c2566","observation_id":"aeb1f28b-6fdb-4cdd-9585-02714249d56d","resolution":{"observed_at":"2026-08-15T20:55:34.400678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.489705Z","title":"Mutual information neural estimation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.489705Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:e81d6d4ad4745910e0babc89379e92e23d8f30ead96e7632f76679cbe188c1ff","observation_id":"55db2047-6098-4fe4-8e14-de3fccfef464","resolution":{"observed_at":"2026-08-15T20:55:33.489705Z","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":"2026-08-15T20:55:34.378477Z","title":"Lower bounds on adversarial robustness from optimal transport","venue":null,"work_id":"a6fed636-fbc2-4dc1-9a66-e3050e7ceea3","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.493004Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:48951c847ae8900a14d570e86d6dc748ebfcf2016400fda2ab52774d250bbb37","observation_id":"33048c72-f9ab-4a2f-bc16-c3592ed2cd54","resolution":{"observed_at":"2026-08-15T20:55:34.382644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.496675Z","title":"Measure theory, volume 1","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.496675Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c211cb2e995d295e639a26bd73b09233191a2d4c5256d8d6dabdc730515481fe","observation_id":"23ce7926-b0a8-46a4-9863-4ea022a4a307","resolution":{"observed_at":"2026-08-15T20:55:33.496675Z","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":"2026-08-15T20:55:33.499929Z","title":"Sliced and radon wasserstein barycenters of measures","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.499929Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:ca44fd13dca6f9815d2249d8cabbf1a2eeedb741cc97c1ea471a8a8c3ab61273","observation_id":"7ba3d9db-dc77-49b0-91e7-955adc0b1fd6","resolution":{"observed_at":"2026-08-15T20:55:33.499929Z","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":"2026-08-15T20:55:34.352415Z","title":"Unidimensional and evolution methods for optimal transportation","venue":null,"work_id":"994c2296-aade-48ef-a1d6-ac0f9199a17a","year":2013},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.503147Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:b1fa4622d7aff1dea39f3ab2eee1bd558ee068715dfd79c9c6431690ac7e3534","observation_id":"e85547c8-6782-435e-96b8-43cfdeb7b4b9","resolution":{"observed_at":"2026-08-15T20:55:34.355732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07642","last_updated":"2017-05-22T10:14:05Z","snapshot_observed_at":"2026-08-16T13:42:51.462871Z","submitted_at":"2017-05-22T10:14:05Z","title":"From optimal transport to generative modeling: the VEGAN cookbook","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07642","snapshot_observed_at":"2026-08-15T20:55:33.507237Z","title":"From optimal transport to generative modeling: the vegan cookbook","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.507237Z"},"links":{"cited_paper":"/paper/1705.07642","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:2364d17811f4cc7696df3e94a4b6cbbd6e548c45e92e18c806f8e346218b896c","observation_id":"92e2cc34-07af-4089-8a1f-9fcaf4c0bb97","resolution":{"observed_at":"2026-08-15T20:55:33.507237Z","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":"2026-08-15T20:55:33.511531Z","title":"Unsupervised learning of visual features by contrasting cluster assignments","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.511531Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:df3932448e4854e99b62cf237504ce6d196b42ad11b3fe2cc295d3f0e064642a","observation_id":"ffd2c8a0-87c1-4077-ad9d-d5e57b9ab889","resolution":{"observed_at":"2026-08-15T20:55:33.511531Z","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":"2026-08-15T20:55:33.514690Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.514690Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:13a7f80eb308578cd44303965515a0be3c69d2b31bdac2c7da7db94046215e44","observation_id":"6a856c58-6952-4906-9cac-9584ffb490c3","resolution":{"observed_at":"2026-08-15T20:55:33.514690Z","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":"2026-08-15T20:55:33.517726Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.517726Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:13ec259f231e218a0ef2332ef5c8a1a91db0628f83d39d3ba53cf29071e00fd8","observation_id":"d42060e0-d727-446e-85c3-a72f2575638c","resolution":{"observed_at":"2026-08-15T20:55:33.517726Z","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":"2026-08-15T20:55:33.521144Z","title":"Disintegration and bayesian inversion via string diagrams","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.521144Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:ba7f5e8577b500aa7a7bfddfb6e0eb6eef0762c0746ad917eb0f409c07bbb916","observation_id":"ab2e1ef6-8695-47de-833b-5c55f72db48c","resolution":{"observed_at":"2026-08-15T20:55:33.521144Z","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":"2026-08-15T20:55:34.314970Z","title":"Pointless learning","venue":null,"work_id":"12ca45f0-d946-4b81-bc84-739c28361bea","year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.524480Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:3ca99a0b0c1b26e58964b456e49081a2843628fecc2edae849d59f96c6ee7757","observation_id":"f5e68ab6-6b7b-4943-adaf-3da99943259e","resolution":{"observed_at":"2026-08-15T20:55:34.317936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.527600Z","title":"Optimal transport for domain adaptation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.527600Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:346fc09c08cd539ac1996bd2c10951d97ea05abccb02d267ee7ce17f9a961e30","observation_id":"8c7dcfb5-2240-42f8-b785-28163ba0f84c","resolution":{"observed_at":"2026-08-15T20:55:33.527600Z","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":"2026-08-15T20:55:34.299809Z","title":"Joint distribution optimal transportation for domain adaptation","venue":null,"work_id":"381c7bba-a4e1-47e0-b2d2-9b407102154f","year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.530903Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:4df8bf09304dee11d3b7f2b40d7d88d12c6e608fc92346754d001874cbc7ed79","observation_id":"c52d6b1b-5795-4d62-b970-254b11bacbf2","resolution":{"observed_at":"2026-08-15T20:55:34.302931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.289571Z","title":"A categorical foundation for bayesian probability","venue":null,"work_id":"8deed598-1fc8-4775-af80-06883b24043d","year":2014},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.534117Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:415f8ed7eb031185ef467d821aba8430535751b5ee75da5bfeed53dc988da20a","observation_id":"b9baa01c-feeb-43c8-8e8b-bb464acccedd","resolution":{"observed_at":"2026-08-15T20:55:34.293008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.537751Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.537751Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:10e0fc146c66103e2a567b87449cd3f98cf5a6309aa5c3103565c07e618605ae","observation_id":"2ddfbb83-9cd0-404b-b34c-35251cd80852","resolution":{"observed_at":"2026-08-15T20:55:33.537751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-15T20:55:33.541621Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.541621Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:32d96c26af985e260bc154b2790b8eb48b4b9feb9ed0efbe1eefa96265218ade","observation_id":"8ff6fae6-2283-4072-a327-8de96e1fc5c5","resolution":{"observed_at":"2026-08-15T20:55:33.541621Z","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":"2026-08-15T20:55:34.272676Z","title":"Your representations are in the network: composable and parallel adaptation for large scale models","venue":null,"work_id":"85787545-826d-4630-8c39-e1ab1916df06","year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.545114Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:ce45be11b9f349092e534b97cf805747dfb17c2c4e12893eea8f4d505748726a","observation_id":"2f6e9459-d646-40d9-ac7c-224239391fe2","resolution":{"observed_at":"2026-08-15T20:55:34.276618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.261637Z","title":"Bayesian Inference for Markov Kernels Valued in Wasserstein Spaces","venue":null,"work_id":"76a66f6a-ffa8-4cfb-a48e-71ad2e2dca95","year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.548247Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:13af3e8423459d62ebe2dc76160655355a6a1b111c88a2abe77dfa26e8ac181c","observation_id":"f3cf3810-3369-4bef-b966-c65f77494f9a","resolution":{"observed_at":"2026-08-15T20:55:34.266024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.250929Z","title":"A synthetic approach to markov kernels, conditional independence and theorems on sufficient statistics","venue":null,"work_id":"b40f072f-5f69-4a9c-b797-db62278d74f0","year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.551505Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:d749ba641205a7a0c48ccb7572021cf993661e5ba6661666bc78b98ce2587c80","observation_id":"3a4c5c03-676e-42e6-b8b3-ed208b974817","resolution":{"observed_at":"2026-08-15T20:55:34.254563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.240981Z","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","venue":null,"work_id":"2fc6f628-dea0-4308-8d44-088369ee7209","year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.554787Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:ab66ad46398aff19e32df5eb09a9d4a574bd93f04ba78197e3151f2cc086293c","observation_id":"2c261036-3ab8-442e-9c80-7590954f2711","resolution":{"observed_at":"2026-08-15T20:55:34.244391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.230496Z","title":"Measuring statistical dependence with hilbert-schmidt norms","venue":null,"work_id":"9f89cbed-fb5f-4e66-b70e-46bce6f7657f","year":2005},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.558588Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:7bef381575d909ff7da02c00bad07f6a652bcb9612585f191489bee82de00683","observation_id":"fde4a796-dc15-4177-aadf-4b5dd13c4433","resolution":{"observed_at":"2026-08-15T20:55:34.234407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.561697Z","title":"Bootstrap your own latent-a new approach to self-supervised learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.561697Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:ca5dbfddb35d3029faaf4198fd327bbea4f2d51f93ba5ad29d5611686cfa9129","observation_id":"9bd3519f-11b3-4da6-8938-9d535b3a1455","resolution":{"observed_at":"2026-08-15T20:55:33.561697Z","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":"2026-08-15T20:55:33.564916Z","title":"Momentum contrast for unsupervised visual representation learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.564916Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:e80de65d3035c3e08f4254425ea774bd5a36be9a115d7e8cf73acabebf6e3114","observation_id":"ebcf8775-72d2-48ff-865f-a97d63e59229","resolution":{"observed_at":"2026-08-15T20:55:33.564916Z","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":"2026-08-15T20:55:33.567993Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.567993Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:67fae423bd125a7797c154d577dfe6301beabaceb07a85ab4f0e61ad31fbab15","observation_id":"f5abc7bb-5a2a-46e6-929d-83289a934f95","resolution":{"observed_at":"2026-08-15T20:55:33.567993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.06670","last_updated":"2019-02-22T18:38:15Z","snapshot_observed_at":"2026-08-14T18:39:08.324821Z","submitted_at":"2018-08-20T19:52:51Z","title":"Learning deep representations by mutual information estimation and maximization","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.06670","snapshot_observed_at":"2026-08-15T20:55:33.571132Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.571132Z"},"links":{"cited_paper":"/paper/1808.06670","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:1773ac42c82107e91306ac0fe40493784746dbbb843f87c54e2273dd937fb632","observation_id":"e97c7b66-6fda-4596-b35f-548bc1e14ca8","resolution":{"observed_at":"2026-08-15T20:55:33.571132Z","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":"2026-08-15T20:55:33.574599Z","title":"Learning discrete representations via information maximizing self-augmented training","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.574599Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a8da70a749df2d0962159110224e2f13c3f35b7d765e109d30023875b25cbb69","observation_id":"36a47224-b1db-4c51-a916-3cb0b9b9ad8c","resolution":{"observed_at":"2026-08-15T20:55:33.574599Z","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":"2026-08-15T20:55:34.198721Z","title":"Customizing domain adapters for domain generalization","venue":null,"work_id":"c89e7933-a713-40db-b14d-17b529071d96","year":2025},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.577809Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:58e5d5367153ce9d6f67424ae362395131323154f3063e9cee92f0541fcbc56e","observation_id":"6cceaea9-a0d0-4600-972d-479d9f9cada3","resolution":{"observed_at":"2026-08-15T20:55:34.202163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.188653Z","title":"Foundations of Modern Probability","venue":null,"work_id":"9be22d8c-e393-4495-b374-e46ccb9b5969","year":2021},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.580986Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:fe2a357f8172f277859730193e107c916ef950e1d07fcaa9636e56cc53f7f553","observation_id":"78676e12-acaa-4344-92de-f45c080f032d","resolution":{"observed_at":"2026-08-15T20:55:34.192008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.177516Z","title":"Selfreg: Self-supervised contrastive regularization for domain generalization","venue":null,"work_id":"c0a8c76a-8d24-478b-bbba-bd6cd910b62a","year":2021},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.584242Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:7ab7a92f2dc7f4c7e512723f94a3d13cf2d31b52ad5bcf66df5d62e9b0213245","observation_id":"78817684-4e51-4c07-927d-eeb89871bc85","resolution":{"observed_at":"2026-08-15T20:55:34.181817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.165711Z","title":"Sliced wasserstein auto-encoders","venue":null,"work_id":"82021d62-8cd8-4290-b5cb-bc562f2f16f4","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.587720Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a84985b08b6efea7d23cdf748bf604d0eca2a98a7d02bf7434dbbddc9df2caa9","observation_id":"601d606d-46fa-4d12-acac-ce0a6261cdc0","resolution":{"observed_at":"2026-08-15T20:55:34.169892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.10054","last_updated":"2022-02-21T09:03:34Z","snapshot_observed_at":"2026-08-18T20:37:40.464812Z","submitted_at":"2022-02-21T09:03:34Z","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.10054","snapshot_observed_at":"2026-08-15T20:55:33.591168Z","title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.591168Z"},"links":{"cited_paper":"/paper/2202.10054","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:4155c2a22c63a6220fde2c7bfeb863798804da267ee7dd19b65e9e593042ed78","observation_id":"8e766a37-027b-4690-9878-aaef7d9e4984","resolution":{"observed_at":"2026-08-15T20:55:33.591168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.15312","last_updated":"2024-07-29T07:24:12Z","snapshot_observed_at":"2026-08-18T04:46:04.428429Z","submitted_at":"2024-03-22T16:04:26Z","title":"A Wasserstein perspective of Vanilla GANs","version":2},"cited_work":{"arxiv_id":"2403.15312","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.15312","snapshot_observed_at":"2026-08-15T20:55:33.833384Z","title":"A Wasserstein perspective of Vanilla GANs","venue":"math.ST","work_id":"1ce80d09-369c-46f2-950c-bd58e1b08780","year":2024},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.594671Z"},"links":{"cited_paper":"/paper/2403.15312","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:936c0c0e504965eed1108d79e6b9a4452bf15a6f52b301d82ac95cb6f3e322e3","observation_id":"71edce8a-8d7a-483a-aa42-c9764efc8e69","resolution":{"observed_at":"2026-08-15T20:55:33.839012Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.154325Z","title":"Sliced wasserstein discrepancy for unsupervised domain adaptation","venue":null,"work_id":"f8fbaf30-f7e6-4364-b2c7-c9c4c75fd130","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.598169Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c986e7f36b17ff2def8ab4e03634627b42bf37de3d5123ed6aa01533cfdb8873","observation_id":"af4a1c83-d588-4ec8-8345-2edb08b822b9","resolution":{"observed_at":"2026-08-15T20:55:34.158658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.142114Z","title":"Wasserstein smoothing: Certified robustness against wasserstein adversarial attacks","venue":null,"work_id":"fe723a6a-2acc-4f82-af3e-43129ff7d09b","year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.601296Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:26f7fbc66abb765a18afa2e561c1cc85248cf8a383e0abfac30c83c0b748f5e3","observation_id":"1c1d0aeb-5207-4aaa-ad7e-cafe4a625acc","resolution":{"observed_at":"2026-08-15T20:55:34.146421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.130647Z","title":null,"venue":null,"work_id":"ee310422-717c-4a49-9b36-8cbfd8dc5ca7","year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.604452Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a30154a63ff719ab8dbc762acea4bd7dcb3909f86bcf9b8027a64ab153a501f1","observation_id":"73f550df-f949-40b2-b302-f5e209b5cee3","resolution":{"observed_at":"2026-08-15T20:55:34.134688Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.120173Z","title":"Self-supervised learning with kernel dependence maximization","venue":null,"work_id":"03c09647-2b0f-46ea-9e2a-0342e26f3d94","year":2021},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.607478Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:52cf0f2aec82d34fcadbcf7459bac7743e5ae7a67e6281a908a6122e2c7c0958","observation_id":"f6614d7f-e500-4f3f-89a4-72ec1d6cc321","resolution":{"observed_at":"2026-08-15T20:55:34.123661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.610818Z","title":"Self-organization in a perceptual network","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.610818Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c7fcd525eb0ebb927b3444c3eea60590ff54aef053e6527730f166a1b56b44db","observation_id":"b9e6824c-6bc0-4aa8-96c0-606f91fb87a2","resolution":{"observed_at":"2026-08-15T20:55:33.610818Z","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":"2026-08-15T20:55:34.103627Z","title":"Entropy regularized optimal transport independence criterion","venue":null,"work_id":"37ffcc86-092d-460a-b102-bc6625307590","year":2022},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.613744Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:d41cead37b8445f6f5e4c44296a62acdce0cb8828ce83f27072c3849e8b21e71","observation_id":"37602075-946b-4f19-a759-e9f2b59c5448","resolution":{"observed_at":"2026-08-15T20:55:34.107442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.093087Z","title":"Sliced-wasserstein flows: Nonparametric generative modeling via optimal transport and diffusions","venue":null,"work_id":"687539da-e528-4379-95c4-db260cba5c5b","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.617190Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:f295a79b17a165bc8ab1d07bd5dc39bdccfea93c5cc75a592e9bc7399c04cd9e","observation_id":"0cf1ed3a-f9b8-4ea1-a4c2-af281496866c","resolution":{"observed_at":"2026-08-15T20:55:34.097179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-15T20:55:33.620622Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.620622Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:d5dfeea499ce0ddcbe5d845a0aac3b50e97dd638c959c7aab13572543e7ccd97","observation_id":"b0eebd88-c2b9-44fb-a157-3543994a4453","resolution":{"observed_at":"2026-08-15T20:55:33.620622Z","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":"2026-08-15T20:55:34.082617Z","title":"Formal limitations on the measurement of mutual information","venue":null,"work_id":"df379fdf-aff6-4408-b847-d37df6136221","year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.624103Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:95a21666be117dff50f82a9a5fc3eb274f06894664286aa2a446fd2299936e0e","observation_id":"5ce2fd77-ca85-49bb-9550-440843b20a34","resolution":{"observed_at":"2026-08-15T20:55:34.086472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.071614Z","title":"Measuring dependence between random vectors via optimal transport","venue":null,"work_id":"d0881faa-5fa3-4ca8-aa56-5c911360faa7","year":2022},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.627350Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a9753439744c26c84ecabc0c6a25ffae5808ac0359ad44a376b3d99e1c7f4974","observation_id":"d68f092e-59c8-4c4d-9f86-8b2658f2a507","resolution":{"observed_at":"2026-08-15T20:55:34.075311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.04313","last_updated":"2020-09-09T14:09:47Z","snapshot_observed_at":"2026-08-18T12:52:38.028530Z","submitted_at":"2020-09-09T14:09:47Z","title":"The Earth Mover's Correlation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.04313","snapshot_observed_at":"2026-08-15T20:55:33.631178Z","title":"The earth mover's correlation","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.631178Z"},"links":{"cited_paper":"/paper/2009.04313","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c22f2322c01e298d0d8f3cd626190e4f2fd822d94a7a7c47da029629df51e1a5","observation_id":"82f71de8-a1f8-4295-9c0e-6d51a82913b5","resolution":{"observed_at":"2026-08-15T20:55:33.631178Z","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":"2026-08-15T20:55:34.060897Z","title":"Asymptotic guarantees for learning generative models with the sliced-wasserstein distance","venue":null,"work_id":"d51ffe9a-e370-4d34-88d2-a11da46ad4ae","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.634866Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:e63d41a5cd74184d62c8b5aad0d4e541e3eb746e336dc67ac1796d49e9649e28","observation_id":"09524049-0930-4685-9d89-4450a1bc38e2","resolution":{"observed_at":"2026-08-15T20:55:34.064624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.13570","last_updated":"2023-02-06T15:38:47Z","snapshot_observed_at":"2026-08-18T15:44:51.492024Z","submitted_at":"2022-09-27T17:46:15Z","title":"Hierarchical Sliced Wasserstein Distance","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.13570","snapshot_observed_at":"2026-08-15T20:55:33.638372Z","title":"Hierarchical sliced wasserstein distance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.638372Z"},"links":{"cited_paper":"/paper/2209.13570","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:b67939db710c6604e2b68abf3bd163af8094ac3d5fc50656a2a1681821da3705","observation_id":"6f851820-bbbf-4228-80d3-ea4314918327","resolution":{"observed_at":"2026-08-15T20:55:33.638372Z","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":"2026-08-15T20:55:34.049679Z","title":"Optimal transport model distributional robustness","venue":null,"work_id":"b0c91508-36ae-4327-9d3e-5fc2c7151020","year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.641629Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:2cd2e944959b54170c5cfd7034c0569a14fcf35994b72ddf35dc04cc9906018d","observation_id":"93040b96-195b-4dfb-8b38-f030168ffab6","resolution":{"observed_at":"2026-08-15T20:55:34.053684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.02073","last_updated":"2023-03-20T11:14:43Z","snapshot_observed_at":"2026-08-16T18:26:51.484575Z","submitted_at":"2021-05-05T14:19:28Z","title":"Transport Dependency: Optimal Transport Based Dependency Measures","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.02073","snapshot_observed_at":"2026-08-15T20:55:33.644937Z","title":"Transport dependency: Optimal transport based dependency measures","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.644937Z"},"links":{"cited_paper":"/paper/2105.02073","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:3f22daddee3d187641600d7b590ddc4c3ce1067b8c399f11d51b1a98dd5d9285","observation_id":"c2d3b3dd-0648-4cba-bdc3-28b4b727ac54","resolution":{"observed_at":"2026-08-15T20:55:33.644937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-08-14T18:53:38.574749Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-15T20:55:33.648276Z","title":"Representation learning with contrastive predictive coding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.648276Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:4b33e0a1c06e22d50714ae991263f9b4a5a93d30aa9bcd793f49625379701c2b","observation_id":"8f720718-3e10-4637-add4-4c632844a596","resolution":{"observed_at":"2026-08-15T20:55:33.648276Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-17T13:03:40.359628Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-15T20:55:33.651640Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.651640Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c94d31370e9a8069d8c38983639d6c00f1e22da6447a1c70a14404c614901cd5","observation_id":"480a1976-4997-497f-8abf-58dbab91cbff","resolution":{"observed_at":"2026-08-15T20:55:33.651640Z","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":"2026-08-15T20:55:34.038540Z","title":"Wasserstein dependency measure for representation learning","venue":null,"work_id":"8bbe8be6-31f8-4d04-9e6e-2b01ddeb4ffe","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.654860Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a9fe0733475c7c513682daecfdf5b2092910ba2d857804f008430d3a8de1c760","observation_id":"5069a6be-64a2-45a1-bf45-923573d5acbe","resolution":{"observed_at":"2026-08-15T20:55:34.042312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:34.027923Z","title":"Hausdorff and wasserstein metrics on graphs and other structured data","venue":null,"work_id":"08720dc0-0dd8-44f2-9758-9eea8f237e6b","year":2021},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.658105Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:b47f6c52080c00d674421c015ac0bb65b0025452b232e03f19f1aee12ef16c41","observation_id":"fb6d3ff1-3ba5-450a-b35c-a52a3ead624b","resolution":{"observed_at":"2026-08-15T20:55:34.032081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.661196Z","title":"On variational bounds of mutual information","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.661196Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:e53d729c4a676675c47e0d80396faf47e718ae0b1467ae2f7b632808fee34e3c","observation_id":"522ea27b-c6e8-46a2-aec8-43aa2c0003f0","resolution":{"observed_at":"2026-08-15T20:55:33.661196Z","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":"2026-08-15T20:55:34.013187Z","title":"Mass Transportation Problems: Volume 1: Theory","venue":null,"work_id":"527dadcd-2833-40a9-885f-1dcd53e65164","year":2006},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.665216Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:e45ffc7b29e73fdc992b2e1bd8fdb1ce3265d73db19f6f28c24ca5c6791bfe67","observation_id":"07e20b74-6f2f-431b-b3e8-70a276a0b5de","resolution":{"observed_at":"2026-08-15T20:55:34.016607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.668349Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.668349Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:cc4a19e1e5477170a040d4a8001ce6b4fbf1cb5a74cb88b2a00073550ed78aab","observation_id":"24439f6d-1bd9-402e-9677-11a392b5cd2a","resolution":{"observed_at":"2026-08-15T20:55:33.668349Z","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":"2026-08-15T20:55:33.672301Z","title":"Learning multiple visual domains with residual adapters","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.672301Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c6d3e4976f0cbc670d032b8d277118d685c16c091bc34dfdaa25ba4c3529511c","observation_id":"bb575514-7f52-4544-827e-c902472a32ea","resolution":{"observed_at":"2026-08-15T20:55:33.672301Z","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":"2026-08-15T20:55:33.989585Z","title":"Learning representations by maximizing mutual information in variational autoencoders","venue":null,"work_id":"c17bb4b9-405d-4c36-abde-356c4cabf570","year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.675566Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:447e012b83a09d13add080fbf12da4620cef7cdb04e2f277820c5917f9ad1890","observation_id":"156aff44-88e6-4806-9f67-74668553b292","resolution":{"observed_at":"2026-08-15T20:55:33.994388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.979162Z","title":"Kornia: an open source differentiable computer vision library for pytorch","venue":null,"work_id":"eff84ed2-5c3c-4c3c-801c-a8824483ef16","year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.678819Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:b7bfe720f6bdefcdfb677942241ba4091f9a494ff4eb5ee7accba51026c7249f","observation_id":"aac9c08c-90bb-4ca8-be68-aef2564fefc7","resolution":{"observed_at":"2026-08-15T20:55:33.982906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.682272Z","title":"Wasserstein distance guided representation learning for domain adaptation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.682272Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:565a385f854abaeec7ceef7dec8af905e5134e01efef16878c8c6e760a273536","observation_id":"d4a8d7ed-2d94-414c-8e0a-f1033c84d4f0","resolution":{"observed_at":"2026-08-15T20:55:33.682272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.01558","last_updated":"2019-12-05T10:27:44Z","snapshot_observed_at":"2026-08-14T20:16:55.687026Z","submitted_at":"2017-11-05T10:18:27Z","title":"Wasserstein Auto-Encoders","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.01558","snapshot_observed_at":"2026-08-15T20:55:33.685298Z","title":"Wasserstein auto-encoders","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.685298Z"},"links":{"cited_paper":"/paper/1711.01558","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c673b86f9cc5bd57d15d9e0e31eca5352d40a7964c837f689f7f89d1167f5ac2","observation_id":"d2c37623-6f1f-487b-ad1b-ba8c5d49f8fe","resolution":{"observed_at":"2026-08-15T20:55:33.685298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.13625","last_updated":"2020-01-23T09:08:54Z","snapshot_observed_at":"2026-08-18T17:43:35.148821Z","submitted_at":"2019-07-31T17:50:51Z","title":"On Mutual Information Maximization for Representation Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.13625","snapshot_observed_at":"2026-08-15T20:55:33.688735Z","title":"Tschannen, J","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.688735Z"},"links":{"cited_paper":"/paper/1907.13625","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:c4fe8ff4d581aae2d1337e552a27794a247eecb199c3b9eb7d4b7d0ae209c711","observation_id":"3926993d-bd33-45de-bcc6-f3367c220122","resolution":{"observed_at":"2026-08-15T20:55:33.688735Z","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":"2026-08-15T20:55:33.962954Z","title":"Topics in Optimal Transportation","venue":null,"work_id":"3b614631-0641-45db-bb3c-a332ef99a000","year":2003},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.692257Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:9af8cc057b9e39e4b6fb9f1956ac032da8f199ade331ccc5afebe9d3c6c1352d","observation_id":"750c9778-cfb5-4acf-9796-cfe32bee8c2d","resolution":{"observed_at":"2026-08-15T20:55:33.966454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.952624Z","title":null,"venue":null,"work_id":"02f7436d-9e72-4584-add1-0c4d27de4a62","year":2022},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.695569Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:6f9c4a04b80018164214c5be776bd367169b01b78889f40fbd4b37f79e3b00b3","observation_id":"426bdde7-d26a-440e-ac5e-c7a9667fe01a","resolution":{"observed_at":"2026-08-15T20:55:33.955670Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.942574Z","title":"Wasserstein adversarial examples via projected sinkhorn iterations","venue":null,"work_id":"fca288d9-63f1-4ffc-904c-94c97a6bf4c5","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.698928Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a97d9df9b40ade6ddbe9490d2a1c30d90bc95b1dc86030b8ec542634ef1cbc10","observation_id":"66f84c7e-a5b2-4989-b4d5-3b41b75e90bd","resolution":{"observed_at":"2026-08-15T20:55:33.946086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.931173Z","title":"Robust fine-tuning of zero-shot models","venue":null,"work_id":"3a1bf18a-01cc-4b82-9df4-4ec032529d6f","year":2022},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.702236Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a75108e5a8b60fa38fd0e09782dac6d0f8acbbdda049b1e889413bfaa2a3658d","observation_id":"fcdee3d3-90b1-40d7-ac59-b855c3bbb875","resolution":{"observed_at":"2026-08-15T20:55:33.935480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.920901Z","title":"Sliced wasserstein generative models","venue":null,"work_id":"785e5a1e-f9c3-4b3a-aa64-35dd6d726555","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.706207Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:8af498eca323db71918dde23df4b5418a2980b1988c746a961d5dba89167d2cf","observation_id":"08ac99dd-aa75-48f1-85cd-31b409f4b857","resolution":{"observed_at":"2026-08-15T20:55:33.924118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.911242Z","title":"Stronger and faster wasserstein adversarial attacks","venue":null,"work_id":"54f5c561-03fa-4c27-b8d7-e8abcf3132e3","year":2020},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.709674Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:a91c340ce4c5e933c9c059cd00be58edcbd5266cb17745e30a093a96d7c1a4ea","observation_id":"70b0a922-8eda-4b0e-a844-392e40284a50","resolution":{"observed_at":"2026-08-15T20:55:33.914520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.12818","last_updated":"2019-12-30T05:31:28Z","snapshot_observed_at":"2026-08-18T17:15:24.568624Z","submitted_at":"2019-12-30T05:31:28Z","title":"Disentangled Representation Learning with Wasserstein Total Correlation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.12818","snapshot_observed_at":"2026-08-15T20:55:33.713090Z","title":"Disentangled representation learning with wasserstein total correlation","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.713090Z"},"links":{"cited_paper":"/paper/1912.12818","citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:f63d115acf0c5bc88d9fe8016e83ec3beb18b841bd5d4790a18038ad063ca522","observation_id":"00b0e212-80f1-4c66-81cb-7effd847717d","resolution":{"observed_at":"2026-08-15T20:55:33.713090Z","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":"2026-08-15T20:55:33.901235Z","title":"Parameter-efficient fine-tuning for pre-trained vision models: A survey","venue":null,"work_id":"272aed8f-4063-43e1-9793-69f0ad9ac2f8","year":2024},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.716660Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:5508e63407d1b6224379f31377525429718dd0985cd57a4284c59f2fc786d181","observation_id":"d38d7d9b-6351-4ec6-bd60-9336df122e3d","resolution":{"observed_at":"2026-08-15T20:55:33.904781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.892000Z","title":"Side adapter network for open-vocabulary semantic segmentation","venue":null,"work_id":"0e5805d5-02e8-45d3-a8f1-8c5df8856ebe","year":2023},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.719912Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:bae7b55e208a63d866d0854650645dd6de758e067bff03e53c9063a70dd145f8","observation_id":"100fa268-89d9-4e9f-b2fa-a0cb5d693c3d","resolution":{"observed_at":"2026-08-15T20:55:33.895175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:55:33.882255Z","title":"Infovae: Balancing learning and inference in variational autoencoders","venue":null,"work_id":"b246a6b4-aa65-4ef6-ab45-b2c61910a513","year":2019},"citing_paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance","version":3},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-15T20:55:33.722924Z"},"links":{"citing_paper":"/paper/2505.11702"},"observation_digest":"sha256:2f9191d94cbc1ffb0e1daf0bab710ba172448b4ecf24fb10e35e440a65d6d0aa","observation_id":"e5422ee8-479d-4422-88ba-f868d0836e06","resolution":{"observed_at":"2026-08-15T20:55:33.885778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.11702","last_updated":"2026-06-08T20:27:12Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T12:14:46.484553Z","submitted_at":"2025-05-16T21:11:51Z","title":"Post-Training Augmentation Invariance"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":74},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 0 inbound Pith citation observations for arXiv:2505.11702."}