{"as_of":"2026-08-08T12:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4c6c475d980854f034817aeda4db1d415ef3b88a741eb820b55159a0559ca5f6","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:26:12.508709Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.15194/citation-record","integrity":"/paper/2505.15194/integrity","json":"/paper/2505.15194/citation-record.json","paper":"/paper/2505.15194"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:26:16.053989Z","title":"Deep learning","venue":null,"work_id":"be2d190a-4ffb-4e88-92ad-76a16c5dccde","year":2015},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:09.119143Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:e49f555b9b49b5831355e0e39b8912fd1162dec7fecd4994f31bdf25a807794c","observation_id":"dc090aad-80a1-493f-a998-531e32b26998","resolution":{"observed_at":"2026-08-07T15:26:16.118427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:09.277294Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:09.277294Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:4a8ee86de1a75b8e9d44170596efc19538e7bd15822db487c05107da42d04a23","observation_id":"b9a79dc8-5cdd-485e-9494-5eb5d5c8b86c","resolution":{"observed_at":"2026-08-07T15:26:09.277294Z","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":"2026-08-07T15:26:15.857145Z","title":"Visualiz- ing data using t-sne","venue":null,"work_id":"4ac7cf41-e128-45cc-b73a-cc0553638e9e","year":2008},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:09.412119Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:fa56fb76db2c293cc42f6643ba907a90799fa681b3bcc1973fef8e2a7163fcbe","observation_id":"3a045717-48ac-4fd9-8b89-a846faa2ae3e","resolution":{"observed_at":"2026-08-07T15:26:15.926091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-07-06T04:04:16.777653Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-07T15:26:09.510228Z","title":"Explaining and harnessing adversarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:09.510228Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:4d2b034fdf5387b38e440cf5a273d0fe4dc8aaee359fa4733983b76efa0832f8","observation_id":"0c93c0a9-e521-475b-a4dd-bbf1b60fe33d","resolution":{"observed_at":"2026-08-07T15:26:09.510228Z","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":"2026-08-07T15:26:15.654546Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":"16ac0402-3b1c-4a51-a46b-62482b545e09","year":2018},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:09.641806Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:16b451e2810ae5524a0544b2b756016da5a7eb97f0ae962c17273a502a234023","observation_id":"9f77d11b-c5e7-4fd6-96f0-0609c022ad14","resolution":{"observed_at":"2026-08-07T15:26:15.764546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:15.488921Z","title":"Theoretically prin- cipled trade-off between robustness and accuracy","venue":null,"work_id":"a6a68104-c52b-4af1-b3dd-82e55ff1a408","year":2019},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:09.741627Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:60bea42be7d5d0a4d0afa211ab43a7d0261bb764fc6d87cfd20325108988141c","observation_id":"0d3bad74-abd6-433c-b967-1bc1d470ce0b","resolution":{"observed_at":"2026-08-07T15:26:15.573304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:15.284977Z","title":"Disentan- gling adversarial robustness and generalization","venue":null,"work_id":"dac11ab7-98ba-4c2d-9840-c1429c31c8bf","year":2019},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:09.885053Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:5f88c5a1255b8744195bc476db0c0e6aab3c18752e2b97639f06b11bdeaa0b19","observation_id":"60b241b8-c88d-4f21-af6c-98a4afd987d0","resolution":{"observed_at":"2026-08-07T15:26:15.355788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:15.110306Z","title":"Manifold mixup: Better representations by interpolat- ing hidden states","venue":null,"work_id":"e6a8a357-1196-49a4-b6f3-26297d040570","year":2019},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.002977Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:c67d33650d985f9f63d457ad5582abb86d5b4295b1e44e40daebb4ac572b4a26","observation_id":"fb284c3a-8e23-4ca5-b79d-bf153fa053e5","resolution":{"observed_at":"2026-08-07T15:26:15.208687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:14.947738Z","title":"Virtual adversarial training: a regularization method for supervised and semi-supervised learning","venue":null,"work_id":"e6bf1fc9-9396-4580-9fa4-56322e02fa1b","year":1979},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.122572Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:420db0837d9123ccab511ee11715707bb663daaac58e37dfd481e14ab782b450","observation_id":"767d798d-cfd2-4364-921e-0a62b6f7ce65","resolution":{"observed_at":"2026-08-07T15:26:15.042683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:14.787206Z","title":"Cross-modality perturbation synergy attack for person re-identification","venue":null,"work_id":"6b5a3f0c-bfa9-4c13-b87a-3b865abfea2d","year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.239600Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:135ebd09d60dc40f69be71e20aed4fa9dfc422a68a26255b21b39f7acc6577e9","observation_id":"1363ed27-9f98-4847-833f-e7cea6c406dc","resolution":{"observed_at":"2026-08-07T15:26:14.849181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:14.575920Z","title":"Beyond dropout: Robust convolutional neural networks based on local feature masking","venue":null,"work_id":"21751533-492e-4688-a27d-48f89b69b6d5","year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.380917Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:6b697e62897a493246a6f424318a8691bcc34b484f9fe71affcd7aa4917f715a","observation_id":"427a791f-880f-4fed-80d8-e877189b43ee","resolution":{"observed_at":"2026-08-07T15:26:14.664517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.08533","last_updated":"2022-06-13T14:16:14Z","snapshot_observed_at":"2026-07-06T10:34:19.340163Z","submitted_at":"2021-01-21T10:33:02Z","title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08533","snapshot_observed_at":"2026-08-07T15:26:10.541928Z","title":"Elimi- nate deviation with deviation for data augmentation and a general multi-modal data learning method","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.541928Z"},"links":{"cited_paper":"/paper/2101.08533","citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:3f14d9553fdf9958cbbaf75663b34d2831a7d24193ea7b316f59b02c89f4ec4d","observation_id":"3c9299f1-0e30-4f7f-b0e7-f53529a02d55","resolution":{"observed_at":"2026-08-07T15:26:10.541928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02431","last_updated":"2024-09-04T04:18:25Z","snapshot_observed_at":"2026-08-07T18:38:03.450135Z","submitted_at":"2024-09-04T04:18:25Z","title":"Adversarial Learning for Neural PDE Solvers with Sparse Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02431","snapshot_observed_at":"2026-08-07T15:26:10.751436Z","title":"Adversarial learning for neural pde solvers with sparse data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.751436Z"},"links":{"cited_paper":"/paper/2409.02431","citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:e915619df525e970638f34f4e8b3c1d709df2baeefe8afe2aa39b30339a2acf5","observation_id":"1b5a46c7-aa8e-4009-9b90-615643537c12","resolution":{"observed_at":"2026-08-07T15:26:10.751436Z","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":"2026-08-07T15:26:14.420719Z","title":"Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging","venue":null,"work_id":"814fbee0-9fe8-4315-9c4a-6a38fd126102","year":2023},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.868597Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:3260b390a1a7fa0be24d276cd4a311091c4cf2a440ecd25931d1e7138a387c97","observation_id":"cacb34fe-5ecf-43ba-ad48-2c0ba51a7736","resolution":{"observed_at":"2026-08-07T15:26:14.493177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:14.231133Z","title":"Learning internal representations by error prop- agation, parallel distributed processing, explorations in the microstructure of cognition, ed","venue":null,"work_id":"c7799b78-c49b-4849-8a83-0bae42980c38","year":1986},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:10.970918Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:b4cfdb8cb23186cac7ad368d7503e68bab1a1c6efb3e1b0577f53d29008a3414","observation_id":"720bf38c-f921-4499-b19e-ef2b49529db8","resolution":{"observed_at":"2026-08-07T15:26:14.314699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:11.115414Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.115414Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:4e15691b66fb060c6fe4ff4da9e04c93a6f350e064d4767f2f63739c8282d6c8","observation_id":"fe8b4729-a44d-45e0-9181-ac1480c2eae7","resolution":{"observed_at":"2026-08-07T15:26:11.115414Z","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":"2026-08-07T15:26:11.222555Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.222555Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:aa33dcbfc4d495d49b054dd743edf4104631a4af94c50d70fb469d8d85784bf0","observation_id":"b9b514dd-64e3-4f73-9626-519a5d09dd4e","resolution":{"observed_at":"2026-08-07T15:26:11.222555Z","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":"2026-08-07T15:26:14.005807Z","title":"Adversarial training for free! In Advances in Neu- ral Information Processing Systems (NeurIPS) , volume 32,","venue":null,"work_id":"7c59b558-ce3c-4ac1-949a-38dfafddc84b","year":null},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.268453Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:5ddfddd44fb65d6e84dfd4b5da93bcd8958fbb99701facdadd43cf328e90c4fc","observation_id":"4279472e-b98f-4068-8fc1-92c3764c1a5d","resolution":{"observed_at":"2026-08-07T15:26:14.114902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.916046Z","title":"Person re-identification method based on grayscale feature enhance- ment","venue":null,"work_id":"515e811a-6bba-4a47-aa06-81e4f251be73","year":2021},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.318389Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:6962962c14d6cd8b31cb75ac63a258f734ce8313f84a32121644f9006a48b70c","observation_id":"c337afa6-d5d4-4fa7-b8ae-0008ef499df7","resolution":{"observed_at":"2026-08-07T15:26:13.947768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.17977","last_updated":"2024-09-26T15:52:34Z","snapshot_observed_at":"2026-08-03T15:23:25.760282Z","submitted_at":"2024-09-26T15:52:34Z","title":"Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.17977","snapshot_observed_at":"2026-08-07T15:26:11.365820Z","title":"Cross-modality attack boosted by gradient-evolutionary multiform optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.365820Z"},"links":{"cited_paper":"/paper/2409.17977","citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:97e81d3e6c266fb464b74bf0dbaf71283c272d729736b083ae04e68efbb8f0b0","observation_id":"c3d5281b-4ce8-45c5-aed2-66a750107ec5","resolution":{"observed_at":"2026-08-07T15:26:11.365820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.10512","last_updated":"2024-01-19T06:04:48Z","snapshot_observed_at":"2026-07-06T17:17:44.177514Z","submitted_at":"2024-01-19T06:04:48Z","title":"Exploring Color Invariance through Image-Level Ensemble Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.10512","snapshot_observed_at":"2026-08-07T15:26:11.410269Z","title":"Ex- ploring color invariance through image-level ensemble learn- ing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.410269Z"},"links":{"cited_paper":"/paper/2401.10512","citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:58e1ab1786412c8be3fbfa04140a81c8bb480ad07dbc44a73e1156039dd66691","observation_id":"9eb0a4e2-b9f3-48a1-8266-c9a2e23095b9","resolution":{"observed_at":"2026-08-07T15:26:11.410269Z","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":"2026-08-07T15:26:13.746373Z","title":"Beyond augmentation: Empowering model robustness under extreme capture environments","venue":null,"work_id":"afdacb1d-c8ad-446e-9003-3e82cac8b148","year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.452399Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:50984487a0cc4496e67fbcefaa9c0efdbd6f568928234eb1a9a69d743fb85446","observation_id":"2d31c457-2ee4-49b3-9fc1-9fb9eb1cce24","resolution":{"observed_at":"2026-08-07T15:26:13.813346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.605438Z","title":"Cross-task attack: A self-supervision generative framework based on attention shift","venue":null,"work_id":"9a00d515-364d-4693-bdb4-049134637a08","year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.517152Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:adbd462092fa16c2b524ecd1aed606c980b23638b431db079f7da8c31c1014c6","observation_id":"0141ae8c-2e29-42c2-9eb6-60ad99f948a1","resolution":{"observed_at":"2026-08-07T15:26:13.655390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.520856Z","title":"A theory of learning from different domains","venue":null,"work_id":"6550adb3-f866-4ad7-8e37-d0d678bd1338","year":2010},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.661049Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:803c560a6f87aadde6b5f9fa02e6994fe8dfe21d7e56ef5f096ec66914ce4009","observation_id":"b73816df-21aa-4c4b-ae00-1c554b754875","resolution":{"observed_at":"2026-08-07T15:26:13.593870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.443794Z","title":"Managing ex- treme ai risks amid rapid progress","venue":null,"work_id":"45889376-3be7-4320-a54b-39d90d191e69","year":2024},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.716967Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:be576b35ea94e830560e4ffdcede1abc8e2c964f3ce4894ee6471eaa9957d111","observation_id":"0d321ca7-62f3-4581-89d9-7f68183453d5","resolution":{"observed_at":"2026-08-07T15:26:13.479717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.355212Z","title":"Moment matching for multi-source domain adaptation","venue":null,"work_id":"f988b2cd-0cd2-413d-a586-2982d5b80097","year":null},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.777776Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:3c30eea816944c731807374d9bfa9c19d859af125a38776332ada141f0c55da3","observation_id":"b53345b9-ad44-4d7d-be17-62a897dd7e27","resolution":{"observed_at":"2026-08-07T15:26:13.391282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06924","last_updated":"2017-11-29T04:04:18Z","snapshot_observed_at":"2026-08-07T12:49:34.214845Z","submitted_at":"2017-10-18T20:20:49Z","title":"VisDA: The Visual Domain Adaptation Challenge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06924","snapshot_observed_at":"2026-08-07T15:26:11.859680Z","title":"Visda: The visual domain adaptation challenge","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.859680Z"},"links":{"cited_paper":"/paper/1710.06924","citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:779a9ceb6ea19515443e00fa7a552c75c7cc5ae30694dfcc4102b6ab5e09db1a","observation_id":"03338ce6-e90f-4a7e-a8f0-b9263fafd2ce","resolution":{"observed_at":"2026-08-07T15:26:11.859680Z","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":"2026-08-07T15:26:13.265051Z","title":"Deep hashing network for unsupervised domain adaptation","venue":null,"work_id":"dcdbb420-dd8a-429d-9ad2-49aad3f25f92","year":2017},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:11.976563Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:ed5bc987a96ba3b2153ea08ebeee92cbbadcc74f956da3c4092242198aff7d25","observation_id":"f99ec291-820c-4968-b735-3bf2e780ce45","resolution":{"observed_at":"2026-08-07T15:26:13.308702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.181659Z","title":"Domain-adversarial train- ing of neural networks","venue":null,"work_id":"747d3fcd-8560-49d4-97df-e1d10a048331","year":2016},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:12.051906Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:cad8eaad5dce495dfdbc19bf6aad12d128996a1f9989d63934ce814dc0f0ffa8","observation_id":"e0828175-aad9-4ca2-a7ec-58ae2a239688","resolution":{"observed_at":"2026-08-07T15:26:13.221407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.087856Z","title":"Maximum classifier discrepancy for unsu- pervised domain adaptation","venue":null,"work_id":"14ce42d4-f960-44a9-9532-5bff7209a26c","year":2018},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:12.159108Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:31ddcec4d01a32732090b87534ad8682d94813c612cd6d04afb6085f0f13ce51","observation_id":"a89e7dc5-0f34-44c6-8c7b-e8022b40b7f3","resolution":{"observed_at":"2026-08-07T15:26:13.120847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:13.006512Z","title":"Bridging theory and algorithm for domain adap- tation","venue":null,"work_id":"a4f6e248-0edb-4b02-b312-398e53deadeb","year":2019},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:12.254853Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:cb47c3c85c7604f10de82152afdcfdb380cf09bb7d3cb797bf06b3c8eddcc2a8","observation_id":"da4e9586-21d0-42b3-a4e4-b107ab64d8e9","resolution":{"observed_at":"2026-08-07T15:26:13.034909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:12.872351Z","title":"Mutual mean-teaching: Pseudo la- bel refinery for unsupervised domain adaptation on person re-identification","venue":null,"work_id":"4138ab39-3fcf-4ca8-91a6-d47e7b006b2e","year":2020},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:12.381529Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:74f5ac1f2980df7db082acaa21ce3b22d9fdf2a005b8f843c2ae8b064bc49478","observation_id":"0b99a43c-a55b-4c66-969e-8972c4a7e0df","resolution":{"observed_at":"2026-08-07T15:26:12.934831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T15:26:12.726316Z","title":"Tent: Fully test-time adaptation by entropy minimization","venue":null,"work_id":"f379dd34-d335-44ca-9043-d418f8ae5415","year":2021},"citing_paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:12.508709Z"},"links":{"citing_paper":"/paper/2505.15194"},"observation_digest":"sha256:088c86c1eab7e81cb56b5f4e01cfad9bc1a903da3ca80ce9962035aa8590e10a","observation_id":"7fd1e525-0c75-442a-b376-ba8ba68c52e4","resolution":{"observed_at":"2026-08-07T15:26:12.787017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.15194","last_updated":"2025-05-21T07:16:42Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T15:20:24.222087Z","submitted_at":"2025-05-21T07:16:42Z","title":"GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":24},"total_outbound_references":33},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2505.15194."}