{"as_of":"2026-08-12T03:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c69c41330a69438fad443db214b6ee23c61794152345b16198e00bbf79990e6d","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:40:29.663537Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.01025/citation-record","integrity":"/paper/2501.01025/integrity","json":"/paper/2501.01025/citation-record.json","paper":"/paper/2501.01025"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:40:29.133559Z","title":", \" * write output.state after.block = add.period write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.133559Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:f6bf228e2b44291aa1ed1b449425f4226bd712e86e6fced46d913649e2d76924","observation_id":"1541da85-4963-441b-b284-76a4aa251080","resolution":{"observed_at":"2026-08-10T22:40:29.133559Z","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":"2026-08-10T22:40:29.139692Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.139692Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:3fc2497997c857ec75af9b9ba8a348e26a3c4f9aa5d9011f5c5229e62392e7d4","observation_id":"28e7f455-2deb-42a3-8a61-dcd80c2315b3","resolution":{"observed_at":"2026-08-10T22:40:29.139692Z","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":"2026-08-10T22:40:31.137790Z","title":null,"venue":null,"work_id":"5e87f80b-5ce1-48ba-b989-035dc896c356","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.147326Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:8f96084bf13451e0f96ecd64ffcc1f39bacd1227ceeea0867e48c2a95e63ca57","observation_id":"2fd72dea-1919-437a-bd62-35b180727ab9","resolution":{"observed_at":"2026-08-10T22:40:31.143687Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:31.117263Z","title":null,"venue":null,"work_id":"22a88a42-5384-4a9c-8ca5-e23f3b54b27d","year":2020},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.157387Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:a61da5e1fab5919e3ca2e401f0506e022ca0e6995cd2ff44ff1de5cfe524be39","observation_id":"5e9fc3c0-0b51-4861-aa8b-857fff075d76","resolution":{"observed_at":"2026-08-10T22:40:31.122329Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:29.165554Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.165554Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:82258f8ec3104315f3becf344f185cb483398e97f27849aabee498087919652e","observation_id":"0f6e4866-d39b-48c6-9ed0-8e28069b29a2","resolution":{"observed_at":"2026-08-10T22:40:29.165554Z","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":"2026-08-10T22:40:31.087448Z","title":"a ckinger, E.; and Shah, R. 1994. Signature verification using a","venue":null,"work_id":"896706e2-8538-414f-aa56-257941a4d5a8","year":1994},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.171419Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:2f57d430a338070953a6411edc22a273d7e4dfc8748e807c8e160267281161ca","observation_id":"d71c7438-3117-4108-b130-dc2d80c05dc4","resolution":{"observed_at":"2026-08-10T22:40:31.092434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.04644","last_updated":"2017-03-22T17:46:16Z","snapshot_observed_at":"2026-07-06T05:07:10.046451Z","submitted_at":"2016-08-16T15:59:35Z","title":"Towards Evaluating the Robustness of Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.04644","snapshot_observed_at":"2026-08-10T22:40:29.176636Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.176636Z"},"links":{"cited_paper":"/paper/1608.04644","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:7db541588309f8c5ab6604b84e15b649b8d82faa9e2a8de85443eb985c836dd8","observation_id":"023c7f7d-0349-4015-9a32-650bbe16b050","resolution":{"observed_at":"2026-08-10T22:40:29.176636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00974","last_updated":"2018-06-05T10:47:05Z","snapshot_observed_at":"2026-07-06T06:42:45.078166Z","submitted_at":"2018-06-04T06:38:28Z","title":"ALMN: Deep Embedding Learning with Geometrical Virtual Point Generating","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00974","snapshot_observed_at":"2026-08-10T22:40:29.181981Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.181981Z"},"links":{"cited_paper":"/paper/1806.00974","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:26eca01b595b37551e1a2c4ce4b9a5965bde34249e3129376083823c176b4b17","observation_id":"0a03b1b1-9e2f-4cf5-bdc4-49a704d79181","resolution":{"observed_at":"2026-08-10T22:40:29.181981Z","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":"2026-08-10T22:40:31.071275Z","title":null,"venue":null,"work_id":"ec2a38ea-2964-489f-8356-3709886f85ff","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.190113Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:a17df35c6da538007178a3ed869df40a41d77add6689121b961788bb07b0719f","observation_id":"377422fc-3b7a-4db3-9496-427b8fbe0506","resolution":{"observed_at":"2026-08-10T22:40:31.077167Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:31.051578Z","title":null,"venue":null,"work_id":"dd5945f1-1f51-4f4c-8045-8005b57ce1f4","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.197067Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:92eea73d6d32ca9853f6d055e46be132b4ef19e76572b1a10b1e81e4416ffcf7","observation_id":"0a1b5368-d14e-4a0f-a385-6b61c7216ed5","resolution":{"observed_at":"2026-08-10T22:40:31.056486Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:31.033394Z","title":null,"venue":null,"work_id":"1fc4fa22-fe92-49f4-a500-79dcd8056d3c","year":2005},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.205165Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:845bda80b865b9864b56cf233a95ad7b8f43b48779fcd129b4a31d416a53d4e5","observation_id":"f9397f5c-053f-496b-bd80-094bd9819365","resolution":{"observed_at":"2026-08-10T22:40:31.038965Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:31.010917Z","title":null,"venue":null,"work_id":"9ee6fe8f-92c0-4fde-87b2-b268cf627c41","year":2009},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.211543Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:8a8546bf0f8e402dafd4e9f35bbc56731991c576d9f7efd7d51f2af760278581","observation_id":"68e318b9-15fe-487e-a595-bb652d97eaf4","resolution":{"observed_at":"2026-08-10T22:40:31.015946Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.990577Z","title":null,"venue":null,"work_id":"10028480-b529-4ff0-a4b0-80ffd6d75035","year":2018},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.217699Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:34e4ac185d5b569d023613a431ed3ed5bc2b1ab9ab146083ae6b3164f99fb565","observation_id":"26e6ec54-c8ab-44db-9d7d-71fef4607efa","resolution":{"observed_at":"2026-08-10T22:40:30.995734Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.967787Z","title":"K.; Harandi, M.; and Sekhar, C","venue":null,"work_id":"165dda89-ba84-4477-a41d-a3bdc48dd7b9","year":2020},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.224170Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:11b744ec8f788f6f53cfaa7b8a042538212f9efcbd494f87501eb6dae95f42d9","observation_id":"6d54eeeb-2ab3-43d0-9576-c75c071de139","resolution":{"observed_at":"2026-08-10T22:40:30.975065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:29.231609Z","title":"J.; Shlens, J.; and Szegedy, C","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.231609Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:af138e626c3d72f84b50348d506b2c3870df79728c166ab47bfded9b6cadac86","observation_id":"14f25629-6e18-402f-9dc2-4de87b436089","resolution":{"observed_at":"2026-08-10T22:40:29.231609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00117","last_updated":"2018-01-25T19:04:48Z","snapshot_observed_at":"2026-07-06T06:07:07.703002Z","submitted_at":"2017-10-31T21:22:16Z","title":"Countering Adversarial Images using Input Transformations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00117","snapshot_observed_at":"2026-08-10T22:40:29.236517Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.236517Z"},"links":{"cited_paper":"/paper/1711.00117","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:37e812ee015fcf21949640f71060bdccde56fb3b08a589095a43c287959dc2cb","observation_id":"61372ba8-fa09-4816-ade7-78ada349a10d","resolution":{"observed_at":"2026-08-10T22:40:29.236517Z","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":"2026-08-10T22:40:30.941983Z","title":null,"venue":null,"work_id":"d05c0ec1-9670-4bcd-a6cd-7419d5edf041","year":2006},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.242128Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:8c309d9e7b0223374ec4862fc9032ca2df9e737eae2626bde55fefe044591d30","observation_id":"b23272c3-554d-493e-a0e4-1fc2613579c6","resolution":{"observed_at":"2026-08-10T22:40:30.948640Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:29.256013Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.256013Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:24d6f5ec6d2fc257fb8182411c1791a5bc191bea1df937750d3c9e348ef0572d","observation_id":"e59a8126-f8ad-4e34-b771-5316e13dc24c","resolution":{"observed_at":"2026-08-10T22:40:29.256013Z","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":"2026-08-10T22:40:30.874221Z","title":null,"venue":null,"work_id":"4c4019d2-4776-4f3e-be09-b6de08f5c1d1","year":2014},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.264194Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:6d984351f591ac147865185ad3bc10400d3e0d5e83187fe5b43387a95c3aa6a5","observation_id":"f105a21e-9c77-4c09-9ca6-1d4ee81201a2","resolution":{"observed_at":"2026-08-10T22:40:30.889160Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.856323Z","title":null,"venue":null,"work_id":"cc4d9ec2-65b2-489a-80e7-088a9a8fac1d","year":2021},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.271517Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:943bf0bb42d1add92e048dc78f3cb16f8bf09ad49dd53a158ceee8a891f91e2d","observation_id":"589a981f-5dfc-450a-ba85-f85714c50d4e","resolution":{"observed_at":"2026-08-10T22:40:30.863418Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.835507Z","title":null,"venue":null,"work_id":"b2db7bca-d68c-4524-b2dc-3a3ca575f621","year":2021},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.279841Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:e3088c8ce7b242015c2b0dec62105f164577a878e07c784021b4fb91dc254467","observation_id":"384e16fd-7902-4789-9036-e5bf24918f7b","resolution":{"observed_at":"2026-08-10T22:40:30.840973Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.810778Z","title":null,"venue":null,"work_id":"f5c42086-57e0-432e-8ae7-83c860fd8c2f","year":2020},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.285524Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:15919f540ecd151d6f7b948bd32e806d2a752a489cd5ed1a4111c27a308b5d24","observation_id":"f626aad7-e19d-45a1-a7c9-cf58cdb94c84","resolution":{"observed_at":"2026-08-10T22:40:30.817608Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-07-06T04:08:54.419941Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-10T22:40:29.294666Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.294666Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:da82c49a14b696db8c35140e10eeea2bec7e3b9fa15e78e5d0fff0f5798032c6","observation_id":"d105c405-8264-4461-8ae5-406e27f5e617","resolution":{"observed_at":"2026-08-10T22:40:29.294666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.13911","last_updated":"2020-03-31T02:05:27Z","snapshot_observed_at":"2026-08-10T06:34:23.466183Z","submitted_at":"2020-03-31T02:05:27Z","title":"Proxy Anchor Loss for Deep Metric Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.13911","snapshot_observed_at":"2026-08-10T22:40:29.307539Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.307539Z"},"links":{"cited_paper":"/paper/2003.13911","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:6e6da33759c66c1f95b3c18d7b6574185af0f1c02d04529888d307884bb4e852","observation_id":"2a6f25bf-84c6-4b61-96e8-be29ee71e280","resolution":{"observed_at":"2026-08-10T22:40:29.307539Z","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":"2026-08-10T22:40:30.784143Z","title":null,"venue":null,"work_id":"755a2d70-9c78-42a9-b8a1-c45b5a5b086d","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.315414Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:4c63c5bf9505ef326cf2f87bc0b6a57af203af10fd250e60a7190a7ce081c132","observation_id":"4ff53de3-2338-4479-afc5-fe8d05b30026","resolution":{"observed_at":"2026-08-10T22:40:30.790459Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-10T22:40:29.323908Z","title":"P.; and Ba, J","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.323908Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:dd083c71ae0bf7688f318c0c19905443af827f1b5bcf01b6e6c0005ee5588955","observation_id":"6ebcb7a4-5dbf-4c13-b74c-da7ed3f50644","resolution":{"observed_at":"2026-08-10T22:40:29.323908Z","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":"2026-08-10T22:40:30.756793Z","title":null,"venue":null,"work_id":"904d8e7a-0b54-4287-a4e2-174471e6c64e","year":2013},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.331244Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:b190b767ef1ceb92f5b869aaeefff538ae9809f72ee8bf3020581b6f2476cd41","observation_id":"f8ac88cd-5b00-4c5a-938d-fb779fc5144b","resolution":{"observed_at":"2026-08-10T22:40:30.767442Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.06784","last_updated":"2022-10-19T07:26:28Z","snapshot_observed_at":"2026-07-06T08:00:44.050111Z","submitted_at":"2019-06-16T22:01:51Z","title":"Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy","version":7},"cited_work":{"arxiv_id":"1906.06784","doi":null,"metadata_source":"pith","pith_arxiv_id":"1906.06784","snapshot_observed_at":"2026-08-10T22:40:30.174526Z","title":"Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy","venue":"stat.ML","work_id":"dfe0bed9-018c-4aaf-9db3-538fd0f75b06","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.337033Z"},"links":{"cited_paper":"/paper/1906.06784","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:fd48f99f9c079bf2b6429db8930417e24a0f7248c3cbeb0a869b35fbe0b3b957","observation_id":"9c5d525d-ae53-40ef-aa56-721a531f494a","resolution":{"observed_at":"2026-08-10T22:40:30.180975Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.739485Z","title":null,"venue":null,"work_id":"d53b0808-c0d0-4bce-b40b-33f581d6714a","year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.347484Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:40e20963e84e05085b3319d3012d0d6b10ef5038c2b512cc948e055dfd1b299a","observation_id":"0acc8454-5fc5-4eea-81bf-d90335a8518b","resolution":{"observed_at":"2026-08-10T22:40:30.746082Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.714195Z","title":null,"venue":null,"work_id":"3fc485de-d6e3-420c-876f-70d54c82266f","year":2016},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.359948Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:eddb9cca4f683c0595171f9abbe21e423b8d50280ca22fc3c869eb3a21cf01ef","observation_id":"7577219d-9d78-4051-9d3c-2b3e59b8a372","resolution":{"observed_at":"2026-08-10T22:40:30.727616Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","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":"2026-08-10T22:40:29.366582Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.366582Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:92183773c3ef5071b2234cb9854415d3af13d61280dc7547e3258c4eb3e8d029","observation_id":"e56bbeed-a80a-4cea-91d3-6caa1baea664","resolution":{"observed_at":"2026-08-10T22:40:29.366582Z","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":"2026-08-10T22:40:30.689572Z","title":null,"venue":null,"work_id":"e10e607a-cf46-4c81-983c-febc8c893579","year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.372359Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:46577c5394c92d53cbb9f28de42da90039149cae6fca0690e1ab8e3b7e2bc28f","observation_id":"c420cfdb-d08f-4b71-8283-45b2f06627b5","resolution":{"observed_at":"2026-08-10T22:40:30.696139Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-10T22:40:29.378229Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.378229Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:a39ee8e61c36b503cf1b851eae084397b161801d9a4d6897d32348fa9811742d","observation_id":"15ae086d-f269-40d8-ab63-75f4ae80cc26","resolution":{"observed_at":"2026-08-10T22:40:29.378229Z","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":"2026-08-10T22:40:30.663404Z","title":"K.; Ioffe, S.; and Singh, S","venue":null,"work_id":"537c030f-c3a7-46cf-92f0-2771233e92bc","year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.384512Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:17bf7de628f420fe01d09d512ea1c5604cefdca1098a5a18c9493331be810dd3","observation_id":"0e2b311a-7e0a-44d1-9bb2-169141ca8b67","resolution":{"observed_at":"2026-08-10T22:40:30.674432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.632345Z","title":null,"venue":null,"work_id":"b0f3bbc7-a76a-435d-978a-1a65d6bc1875","year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.392880Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:26f341f38f1abd5b406871dd4ff972483996ab011d5a53a91f1d738db8dac879","observation_id":"e88f565f-be4c-45f1-8f5c-aaf04858c119","resolution":{"observed_at":"2026-08-10T22:40:30.638388Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08846","last_updated":"2019-05-29T05:49:57Z","snapshot_observed_at":"2026-07-06T07:29:00.536663Z","submitted_at":"2019-01-25T11:57:39Z","title":"Improving Adversarial Robustness via Promoting Ensemble Diversity","version":3},"cited_work":{"arxiv_id":"1901.08846","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.08846","snapshot_observed_at":"2026-08-10T22:40:30.088496Z","title":"Improving Adversarial Robustness via Promoting Ensemble Diversity","venue":"cs.LG","work_id":"de3ffd90-aa24-425b-bd1e-8a60d71ff89e","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.398219Z"},"links":{"cited_paper":"/paper/1901.08846","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:31763ca4afd6d1f472c610c0ce6ea7f05c23a1135be66856a36c3ae4277f04d2","observation_id":"1c265ab4-ce27-4222-90fe-e20edb7b0eac","resolution":{"observed_at":"2026-08-10T22:40:30.094761Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11515","last_updated":"2020-02-20T08:54:57Z","snapshot_observed_at":"2026-08-09T11:23:03.281470Z","submitted_at":"2019-09-25T14:21:55Z","title":"Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks","version":2},"cited_work":{"arxiv_id":"1909.11515","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.11515","snapshot_observed_at":"2026-08-10T22:40:30.057827Z","title":"Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks","venue":"cs.LG","work_id":"36f29449-1088-4df9-a210-bc6a45092ab4","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.404386Z"},"links":{"cited_paper":"/paper/1909.11515","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:583971942c50d4e662f43ecf47f6e1fb59bcf9c98e16ed42a9f1473233fb072c","observation_id":"a6f4bca5-9319-4a94-976d-cbc564fdd265","resolution":{"observed_at":"2026-08-10T22:40:30.064047Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.07265","last_updated":"2021-02-14T23:18:12Z","snapshot_observed_at":"2026-08-11T19:04:38.674215Z","submitted_at":"2021-02-14T23:18:12Z","title":"Exploring Adversarial Robustness of Deep Metric Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.07265","snapshot_observed_at":"2026-08-10T22:40:29.416088Z","title":"K.; Wang, Z.; Kan, P.; Fernandes, E.; and Jha, S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.416088Z"},"links":{"cited_paper":"/paper/2102.07265","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:eb00ec33cffebc77f3a5ad6fb0076f15442592c1cf17b46abc9b4380a8cf2a58","observation_id":"6f541f0e-9002-4916-be9a-02551f7ff008","resolution":{"observed_at":"2026-08-10T22:40:29.416088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.07528","last_updated":"2015-11-24T01:07:08Z","snapshot_observed_at":"2026-08-04T23:22:01.681405Z","submitted_at":"2015-11-24T01:07:08Z","title":"The Limitations of Deep Learning in Adversarial Settings","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.07528","snapshot_observed_at":"2026-08-10T22:40:29.424926Z","title":"B.; and Swami, A","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.424926Z"},"links":{"cited_paper":"/paper/1511.07528","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:d46d58bee9be35fe2bfb2309eaaa5a3336e740861bc642201568dd8cac36df48","observation_id":"9f837c5e-840c-45c7-909e-e24220f39f1b","resolution":{"observed_at":"2026-08-10T22:40:29.424926Z","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":"2026-08-10T22:40:30.614685Z","title":"M.; Vedaldi, A.; and Zisserman, A","venue":null,"work_id":"8e7e9d85-3bc4-4c33-9d45-19a736cd7ad9","year":2015},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.432088Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:ed1b8606f9f6639cd470337101d227b1611fb923993054c2a0dcb911c251d097","observation_id":"38a09bc9-eb9e-4160-a544-f64f2b86e0f1","resolution":{"observed_at":"2026-08-10T22:40:30.621040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.598155Z","title":"G.; Stra z ar, M.; and Zupan, B","venue":null,"work_id":"1a12a6c5-a6fd-4161-b202-227f0f8162a3","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.445160Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:420c202b887b82368abaa52c1b96b7ca77e93e46441bf805ae07dd324dcb977a","observation_id":"557a0970-fac5-4072-97a7-0e8bffe54bc8","resolution":{"observed_at":"2026-08-10T22:40:30.603722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.05235","last_updated":"2020-04-15T02:17:42Z","snapshot_observed_at":"2026-08-02T03:54:48.599564Z","submitted_at":"2019-09-11T17:47:25Z","title":"SoftTriple Loss: Deep Metric Learning Without Triplet Sampling","version":2},"cited_work":{"arxiv_id":"1909.05235","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.05235","snapshot_observed_at":"2026-08-10T22:40:29.960451Z","title":"SoftTriple Loss: Deep Metric Learning Without Triplet Sampling","venue":"cs.CV","work_id":"9324e715-8a6e-437b-a62a-3f2cf84740ea","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.458088Z"},"links":{"cited_paper":"/paper/1909.05235","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:2842ecb80252bddec6b295446560f58c0be455175f64577c30287689a3e84fd5","observation_id":"11525a49-fdcf-4b1a-ab75-7cd756ea0208","resolution":{"observed_at":"2026-08-10T22:40:29.974365Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.574759Z","title":null,"venue":null,"work_id":"0609944e-a23e-48df-9659-a95a27ca9c1d","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.467072Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:b07254eec3df99c43c4567692d45fec907d357a50eeeea1fb27ff627c8dd6f6c","observation_id":"55dad838-f1b7-4d05-9944-0cf9cff683ea","resolution":{"observed_at":"2026-08-10T22:40:30.579010Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.556307Z","title":null,"venue":null,"work_id":"2777dc56-b402-4a88-9649-a529e1094992","year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.474589Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:0bb10991df6c3d669d1bb1afa5f50ea72f5643e64f22e68de5442e4b7d55a0d2","observation_id":"f90c8d2a-c288-43ac-aef0-8081595ec21f","resolution":{"observed_at":"2026-08-10T22:40:30.563113Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.528754Z","title":null,"venue":null,"work_id":"4f0d76be-2f59-4223-a3b4-f732542d6105","year":2016},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.480107Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:b5d0f0562fb8ccea64c2de970fe047abf0e9c8e787df66db9f7dd77c2575cf12","observation_id":"458b40ec-3ab3-427e-947b-a7c4a053ddf5","resolution":{"observed_at":"2026-08-10T22:40:30.534407Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.08473","last_updated":"2020-08-01T16:14:33Z","snapshot_observed_at":"2026-08-09T20:26:21.986343Z","submitted_at":"2020-02-19T22:16:12Z","title":"Revisiting Training Strategies and Generalization Performance in Deep Metric Learning","version":9},"cited_work":{"arxiv_id":"2002.08473","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.08473","snapshot_observed_at":"2026-08-10T22:40:29.917357Z","title":"Revisiting Training Strategies and Generalization Performance in Deep Metric Learning","venue":"cs.CV","work_id":"e28f9c77-06f5-4ea3-93bc-16c5270d4f92","year":2020},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.485326Z"},"links":{"cited_paper":"/paper/2002.08473","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:5ef6ed233f1437e264824f5782ba359ec43016bd425ce2bdc54d8f1f6b65633d","observation_id":"a2dcd0d3-1449-43f1-ae22-459e938ff642","resolution":{"observed_at":"2026-08-10T22:40:29.929726Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.04381","last_updated":"2019-03-21T19:44:34Z","snapshot_observed_at":"2026-08-10T07:51:53.985038Z","submitted_at":"2018-01-13T04:46:26Z","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.04381","snapshot_observed_at":"2026-08-10T22:40:29.491828Z","title":"G.; Zhu, M.; Zhmoginov, A.; and Chen, L","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.491828Z"},"links":{"cited_paper":"/paper/1801.04381","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:85d82b76f2881980768b8d2aeb7c1a693d5251eb1fd0a2d50cfce5bbbbfe4b46","observation_id":"865e11e2-458d-4a7f-82d0-0659da00db45","resolution":{"observed_at":"2026-08-10T22:40:29.491828Z","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":"2026-08-10T22:40:30.507722Z","title":null,"venue":null,"work_id":"bbb890ed-49b2-4b4e-92b2-26a3a733601a","year":2015},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.505115Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:0d80ad7e6f8f3331772109d3223f95b640edb05dc2059a84ec0a9929eea1fcb8","observation_id":"a560055e-b367-4c73-805d-cdf4596fbd7c","resolution":{"observed_at":"2026-08-10T22:40:30.513693Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.07545","last_updated":"2015-11-24T02:46:35Z","snapshot_observed_at":"2026-07-06T04:37:33.504552Z","submitted_at":"2015-11-24T02:46:35Z","title":"Constrained Deep Metric Learning for Person Re-identification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.07545","snapshot_observed_at":"2026-08-10T22:40:29.518363Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.518363Z"},"links":{"cited_paper":"/paper/1511.07545","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:0a8819f561590d00c82a73b453c069eb99981d7d9927c838c8eab08f7edd4873","observation_id":"50407477-d77d-431a-a58d-35c73b20daa6","resolution":{"observed_at":"2026-08-10T22:40:29.518363Z","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":"2026-08-10T22:40:29.526253Z","title":"H.; and Hospedales, T","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.526253Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:2f747ac396649d07a4fbb86fd32ffa2463992aa3fa9a1c990887c6d2f7eeac91","observation_id":"1c3e1ae9-15b8-4e58-9efe-69bbd60823c9","resolution":{"observed_at":"2026-08-10T22:40:29.526253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-10T22:40:29.531728Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.531728Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:9207acdfb5630cf5ef30298a45095bdeed72b9980d17f3b7c3f5b3802e1a670a","observation_id":"2455ac8c-393c-4e86-bc0a-737b9f97500c","resolution":{"observed_at":"2026-08-10T22:40:29.531728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.05236","last_updated":"2019-05-11T16:50:55Z","snapshot_observed_at":"2026-08-12T00:41:21.141718Z","submitted_at":"2018-06-13T19:32:59Z","title":"Manifold Mixup: Better Representations by Interpolating Hidden States","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.05236","snapshot_observed_at":"2026-08-10T22:40:29.548393Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.548393Z"},"links":{"cited_paper":"/paper/1806.05236","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:abebf9c47b1f430f3ca03fb853adef525c7adfa174944c12f08f348b44b584b9","observation_id":"a1ef10fc-c714-4141-88be-bcf05fb85485","resolution":{"observed_at":"2026-08-10T22:40:29.548393Z","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":"2026-08-10T22:40:30.479257Z","title":null,"venue":null,"work_id":"940d6a19-5fbf-4f7c-93c4-f4ccd7a1ca94","year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.570550Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:949e1c35de9676edb2b202120f8a16ed19f5a851b129eaa32bc586dad66fe819","observation_id":"642fbb2f-5754-4ad2-bf7a-092355433ad2","resolution":{"observed_at":"2026-08-10T22:40:30.485694Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.457455Z","title":null,"venue":null,"work_id":"b7ea17f1-8b6f-45a3-b531-61f4b2f58750","year":2015},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.587834Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:17a13d82748cdc10afef009439be38a98b96f8f0bda957f476ba9e2ec1552d51","observation_id":"2de4012a-49ae-4416-9753-5bee6c51eae2","resolution":{"observed_at":"2026-08-10T22:40:30.464600Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.437827Z","title":"T.; and Ni, L","venue":null,"work_id":"141aa89e-e6d9-4549-ad17-3f3697412dbb","year":2020},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.602465Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:44885cdfff43f84523de853bbad309f5d798cd7511701b14bd1cd0c38b8daf10","observation_id":"baaab654-88f3-4a92-8379-c85f3e53f5a8","resolution":{"observed_at":"2026-08-10T22:40:30.445116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.417791Z","title":null,"venue":null,"work_id":"c6e66483-4b66-4f7e-a7e1-b086c596b6e8","year":2010},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.609470Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:21403f6bafdb67748217856bc04ada00affd270b421e8b5b570ac032cff7e3cb","observation_id":"b374c175-db23-47c6-a474-8858b0d40c67","resolution":{"observed_at":"2026-08-10T22:40:30.423187Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.386856Z","title":null,"venue":null,"work_id":"ca34ecb3-6789-484c-a249-2c4eee8b3f30","year":2018},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.623836Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:a350900407d8e12f0586e7ba07b885b6d5274bfd4ede58410324b804d46f59a2","observation_id":"91289af8-fd55-4df9-88a4-c0de65a5a664","resolution":{"observed_at":"2026-08-10T22:40:30.395179Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T22:40:30.353580Z","title":null,"venue":null,"work_id":"3d84ffcf-cb8b-4d84-b73b-83ecf51320f8","year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.634821Z"},"links":{"citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:e57da50b631639049ebf7360cf571da92788ade0f9252cf8814154ac5ec8c628","observation_id":"9c96d5f9-9772-4133-b5a4-38506386bc4f","resolution":{"observed_at":"2026-08-10T22:40:30.360391Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.01991","last_updated":"2018-02-28T22:39:15Z","snapshot_observed_at":"2026-08-04T13:57:53.214741Z","submitted_at":"2017-11-06T16:22:54Z","title":"Mitigating Adversarial Effects Through Randomization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.01991","snapshot_observed_at":"2026-08-10T22:40:29.642000Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.642000Z"},"links":{"cited_paper":"/paper/1711.01991","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:09dd5daf543ea5a7ec0e3cf5e35af0dac082a7639f8b10c4c60b4d6d10850e01","observation_id":"0acacf78-a73d-4946-a75b-e9c68f8b4b1c","resolution":{"observed_at":"2026-08-10T22:40:29.642000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-10T22:40:29.652228Z","title":"N.; and Lopez-Paz , D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.652228Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:f68fd83fcecfc026e7f29ed405f94b325dc2f36706203fd855833e3adf65c239","observation_id":"de0eb9e4-d3da-44ef-beb1-ee3997b758c9","resolution":{"observed_at":"2026-08-10T22:40:29.652228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08573","last_updated":"2019-06-24T07:04:11Z","snapshot_observed_at":"2026-08-10T04:04:10.505875Z","submitted_at":"2019-01-24T18:43:57Z","title":"Theoretically Principled Trade-off between Robustness and Accuracy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.08573","snapshot_observed_at":"2026-08-10T22:40:29.663537Z","title":"P.; Ghaoui, L","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-10T22:40:29.663537Z"},"links":{"cited_paper":"/paper/1901.08573","citing_paper":"/paper/2501.01025"},"observation_digest":"sha256:c23561aa1f0a93447bd71a78fd06158149b036206ec45dbc73dabb300f45f728","observation_id":"a7c12fd3-88fd-4431-9b61-dfa4d9b0a00c","resolution":{"observed_at":"2026-08-10T22:40:29.663537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.01025","last_updated":"2025-01-12T04:43:46Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T18:10:19.914103Z","submitted_at":"2025-01-02T03:15:25Z","title":"Towards Adversarially Robust Deep Metric Learning"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":50,"verified_exact":5,"verified_fuzzy":6},"total_outbound_references":61},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2501.01025."}