{"as_of":"2026-08-12T04:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:543fdd4eeed701c713f6db946b6368be3864f31a137736f557dc87a1ffa0c930","coverage":[{"denominator":88,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":88,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T18:44:39.691863Z","state":"measured"},{"denominator":88,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":88,"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/2501.11063/citation-record","integrity":"/paper/2501.11063/integrity","json":"/paper/2501.11063/citation-record.json","paper":"/paper/2501.11063"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T18:44:39.149276Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.149276Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:fc48e22194c17f83dbbc3fa3d8456f56dd366829725abab6eed2005b7395eda1","observation_id":"0a847a03-a10f-440e-8479-19c3dfc27653","resolution":{"observed_at":"2026-08-10T18:44:39.149276Z","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":"2026-08-10T18:44:39.155849Z","title":"Multi- similarity loss with general pair weighting for deep metric learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.155849Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:5ad81265a4ccd792035b51f4f432f3ce64aefe6037cce9546885138d197f6eee","observation_id":"2011da0f-3700-4b63-bfff-ae3f82bcc23a","resolution":{"observed_at":"2026-08-10T18:44:39.155849Z","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":"2026-08-10T18:44:39.160995Z","title":"Arcface: Additive angular margin loss for deep face recognition,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.160995Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:c2a747c2ed53f0cd2a264e0f739354f05ec43bc82855e2a353271ec29002f058","observation_id":"da1c5c53-fc78-41c5-9303-df30a114d42d","resolution":{"observed_at":"2026-08-10T18:44:39.160995Z","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":"2026-08-10T18:44:39.166453Z","title":"Noise-resistant deep metric learning with ranking-based instance selection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.166453Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:bdc33b22b7993bc0234831649bdb8ad6d494e44f9610fbaaca4352ea7c678197","observation_id":"495a50a9-a0f4-49e1-8f0a-434ab9b034e7","resolution":{"observed_at":"2026-08-10T18:44:39.166453Z","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":"2026-08-10T18:44:39.171533Z","title":"K-means++ the advantages of careful seeding,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.171533Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:dc101248ea4e7c8e4363dc165b49eb02ac28f26bba957b88f585f1cc6a65fe8e","observation_id":"678e7a0b-b7aa-4cdc-b312-8b3252a13915","resolution":{"observed_at":"2026-08-10T18:44:39.171533Z","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":"2026-08-10T18:44:39.176405Z","title":"Hierarchical clustering,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.176405Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:7c8a7f93bda9690d5935b17ba6ef6fafe96f3ead8eef66bb053ad76e34b19bb6","observation_id":"715ad0f5-4a6d-4278-b299-b4a554c4cfbc","resolution":{"observed_at":"2026-08-10T18:44:39.176405Z","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":"2026-08-10T18:44:39.182104Z","title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.182104Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:5c26761a8643a528e0e4653358dad4e670c6ef6dc8a7394f702aefc7dfd23675","observation_id":"55a1cec0-9579-4f34-83fb-6f2ac7f06cdc","resolution":{"observed_at":"2026-08-10T18:44:39.182104Z","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":"2026-08-10T18:44:39.187100Z","title":"Sample selection with uncertainty of losses for learning with noisy labels,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.187100Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:7cf08291a5afbeb8bdee99c4ec5908723117ddbe5cb9d01f5878982ddddcb886","observation_id":"6c206718-8555-4958-bc34-d1dc2b5463ad","resolution":{"observed_at":"2026-08-10T18:44:39.187100Z","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":"2026-08-10T18:44:40.985636Z","title":"Selective-supervised contrastive learning with noisy labels,","venue":null,"work_id":"03df8392-2734-453a-9a2e-6022a95e750a","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.192900Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:5f6fb706e1612917f0ab2cfd8147946e3e3b0c11a0dd2c22b66cc698fe4b55cc","observation_id":"c4aac351-b576-452c-9d00-241ec54735a6","resolution":{"observed_at":"2026-08-10T18:44:40.990878Z","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":"2026-08-10T18:44:40.969106Z","title":"Dist-pu: Positive- unlabeled learning from a label distribution perspective,","venue":null,"work_id":"4934d0aa-b9ac-4587-9a0f-74dce24932a9","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.198313Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:48d1a4f1e4e77e094fcb1d429595b54f5cb18a4c7ea07c1955c2986e21766507","observation_id":"d7c329c5-2337-48ab-adf3-d74c5b7b4864","resolution":{"observed_at":"2026-08-10T18:44:40.974097Z","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":"2026-08-10T18:44:40.953404Z","title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels,","venue":null,"work_id":"7c5a1187-b44c-4e32-a876-a506e6970cbf","year":2018},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.203340Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:73a02ddcd9875e7dfb2f173f382e398548b486cae76c5060f70dee8fbde02a49","observation_id":"5dc48bea-ae81-4bee-9dcc-62b592e20ae3","resolution":{"observed_at":"2026-08-10T18:44:40.958622Z","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":"2026-08-10T18:44:40.937731Z","title":"Meta label correction for noisy label learning,","venue":null,"work_id":"d6843a3f-257c-4441-96f4-e2a79a442a36","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.208226Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:32b75448e75e4d924429fb6f563d032f8164e01d7c61923c3f20c23a90b285bb","observation_id":"ebc18e4d-4d53-4598-a492-37361fdf87fa","resolution":{"observed_at":"2026-08-10T18:44:40.942732Z","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":"2026-08-10T18:44:40.921964Z","title":"Making deep neural networks robust to label noise: A loss correction approach,","venue":null,"work_id":"09649aaa-ae16-4141-8fc4-5ac3564164c6","year":2017},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.212991Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:0f2e2281f998043871826ad007ab3808a99682d2b65206d4e316e7661f221777","observation_id":"77307729-1a0e-4d97-b466-3b1c70efe3ea","resolution":{"observed_at":"2026-08-10T18:44:40.927001Z","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":"2026-08-10T18:44:40.906889Z","title":"Estimating noise transition matrix with label correlations for noisy multi-label learning,","venue":null,"work_id":"04421722-8e2c-4416-8821-8cc3303b4786","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.218859Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:6ef9dd290eccd599c6fbb3194b23cb1052e715c5d49a601183d12b80225fd3f8","observation_id":"ec27d609-fa4a-4cd2-a4f6-f615cabc8ec7","resolution":{"observed_at":"2026-08-10T18:44:40.911838Z","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":"2026-08-10T18:44:40.890846Z","title":"A parametrical model for instance-dependent label noise,","venue":null,"work_id":"402f95a4-8e46-461c-b43c-32d3443bb41a","year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.224370Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:19f37936ee8b9626b4257e30048251c32030417a446843282451bd70ee2313be","observation_id":"690d18c9-fad9-47bb-969c-703b23a38692","resolution":{"observed_at":"2026-08-10T18:44:40.896460Z","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":"2002.07394","last_updated":"2020-02-18T06:20:06Z","snapshot_observed_at":"2026-08-06T03:18:08.960708Z","submitted_at":"2020-02-18T06:20:06Z","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07394","snapshot_observed_at":"2026-08-10T18:44:39.228965Z","title":"Dividemix: Learning with noisy labels as semi-supervised learning,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.228965Z"},"links":{"cited_paper":"/paper/2002.07394","citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:7b58baaca573806b57756389c95d58133523945152e178d70728cf8e8c892af8","observation_id":"64a1094a-db99-4bca-8e25-4d7dabbf2897","resolution":{"observed_at":"2026-08-10T18:44:39.228965Z","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":"2026-08-10T18:44:40.875636Z","title":"Me-momentum: Extracting hard confident examples from noisily labeled data,","venue":null,"work_id":"6af846c8-688a-4d60-b4db-730a0db35345","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.233914Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:2e9ec9f30021841967ee8716ca4d99313e01430d2ba6c9badea819319da19939","observation_id":"92f72323-4f72-4767-b8b6-610963c760d6","resolution":{"observed_at":"2026-08-10T18:44:40.880669Z","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":"2026-08-10T18:44:40.859811Z","title":"Maxmatch: Semi-supervised learning with worst-case consistency,","venue":null,"work_id":"0943468a-c07b-4b42-ad4d-dd48c55f0443","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.238985Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:00dced1b791f8b19e7257eeb97a50a88d6cebacc7b29b40b56d5557bf4dc70aa","observation_id":"afa435c5-e692-41a1-85ed-6bd5017911c4","resolution":{"observed_at":"2026-08-10T18:44:40.865091Z","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":"2026-08-10T18:44:40.843840Z","title":"Learning a similarity metric discriminatively, with application to face verification,","venue":null,"work_id":"ab55df56-840d-4b2f-8bb5-15bccd1976df","year":2005},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.243846Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:f299b4a9dbdc9e48cea3060e89faef1b474a88998a1b011b851e1c3781c8e6d8","observation_id":"dd920d03-2a76-4192-88d6-85924c6cb706","resolution":{"observed_at":"2026-08-10T18:44:40.849027Z","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":"2026-08-10T18:44:40.827858Z","title":"Cross-batch memory for embedding learning,","venue":null,"work_id":"a0fd9a65-923c-4baa-bb47-6873a39e8886","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.248715Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:918fb30d4d51d5b2339ff64e73b38ce0c77d35a44283ab549975a2456a578b60","observation_id":"18ade2d3-9b3f-4b4b-a5d5-256556633f53","resolution":{"observed_at":"2026-08-10T18:44:40.833131Z","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":"2026-08-10T18:44:40.811882Z","title":"Deep image retrieval is not robust to label noise,","venue":null,"work_id":"f1d20bc1-3f31-4200-8655-b2477e891622","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.253486Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:20a3b62172f1e6a7ce7ac2222de1da47b7a48bd393047a36172fb9d20cbfebbd","observation_id":"d55a2e1b-2ebe-4361-8724-8f648ea85056","resolution":{"observed_at":"2026-08-10T18:44:40.816990Z","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":"2026-08-10T18:44:40.795805Z","title":"Facenet: A unified embed- ding for face recognition and clustering,","venue":null,"work_id":"8270ce5f-d359-453f-9b96-a71863c62844","year":2015},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.259262Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:7647c2b12cd3443002b5766bd449a17d041babb7958ba4979cbd14f81fd49632","observation_id":"17fdc3ae-545a-4538-ab0c-f7ce3399fe8a","resolution":{"observed_at":"2026-08-10T18:44:40.800775Z","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":"2026-08-10T18:44:40.779844Z","title":"Circle loss: A unified perspective of pair similarity optimization,","venue":null,"work_id":"301eec6e-27f6-40cc-98f4-c6977bfcb6f7","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.264023Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:1696949f65d1900fe52af5e95577291cf0310a67f5717d84f5542226f21aee6e","observation_id":"06f59d0d-ef0f-4703-8236-c8a4cb506376","resolution":{"observed_at":"2026-08-10T18:44:40.785032Z","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":"2026-08-10T18:44:40.764336Z","title":"Attributable visual similarity learning,","venue":null,"work_id":"63e2df19-d213-427a-a664-fa4eee0fac9d","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.268754Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:ef2e306a73a5e245a86722493f3ed8c4c994d315c1c0d2ca30fc61e7a9ae4a46","observation_id":"73124348-31ae-4560-898a-3c4bd8152fc5","resolution":{"observed_at":"2026-08-10T18:44:40.769307Z","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":"2026-08-10T18:44:40.747850Z","title":"Neighbourhood components analysis,","venue":null,"work_id":"75ceb09c-41ba-43f0-b04b-7e75db9f045a","year":2004},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.273636Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:8dd287df855685173650e63fa7ae709db0fafa0b896334536999ae80c48e39d1","observation_id":"b54a0db9-0813-439b-af2d-64439805a2fd","resolution":{"observed_at":"2026-08-10T18:44:40.752935Z","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":"2026-08-10T18:44:40.731938Z","title":"Sampling matters in deep embedding learning,","venue":null,"work_id":"83712da0-179d-4a70-b26d-ee8fff84149f","year":2017},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.280001Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:c87978bc128fc3fc2c60d1f68b7fed3e8620351e831848b5b3524a6deaebddf6","observation_id":"550e9327-3311-4c29-8a29-70d1217480fd","resolution":{"observed_at":"2026-08-10T18:44:40.736976Z","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":"2026-08-10T18:44:40.716062Z","title":"Deep metric learning to rank,","venue":null,"work_id":"6e7b10b4-17b1-405f-8764-505c6a9c8ae2","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.284580Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:2bc2d9a2b7ff990842845ccec87444811d9d65e9d2287473e6a75cd946550539","observation_id":"168c8608-4ae6-4041-b223-eb0992e3db77","resolution":{"observed_at":"2026-08-10T18:44:40.720944Z","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":"2026-08-10T18:44:40.699719Z","title":"Robust and decomposable average precision for image retrieval,","venue":null,"work_id":"5e61c793-f587-45a2-9a34-80224e76b6cc","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.289349Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:08172eae6dbbc3b66eb37290d9c17389b6ec6e6b524faee6aee06aa910d24a41","observation_id":"b33f1ca5-a5f6-4fd5-b04b-98d28696f67f","resolution":{"observed_at":"2026-08-10T18:44:40.704893Z","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":"2026-08-10T18:44:40.683033Z","title":"Exploring the algorithm- dependent generalization of auprc optimization with list stability,","venue":null,"work_id":"454813b7-0d61-43cf-9b03-c08776298449","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.294094Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:1010dc28266261067c6bd2281b753cd5de061b63905fbbb36e8f05416b4ef849","observation_id":"3cee76a9-c830-422d-8b52-1bd481e64a01","resolution":{"observed_at":"2026-08-10T18:44:40.688186Z","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":"2026-08-10T18:44:40.667597Z","title":"Classification is a strong baseline for deep metric learning,","venue":null,"work_id":"84dc6343-4cc5-4c32-9cee-ac52bb91f004","year":2018},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.298829Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:99dd564a6c3f6f9322331832a6637cb0893dc2c52e9a2438a12f7a116bd9ce2b","observation_id":"a7927d2b-bc61-4929-bbc7-0eacb99dce39","resolution":{"observed_at":"2026-08-10T18:44:40.672677Z","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":"2026-08-10T18:44:40.652324Z","title":"No fuss distance metric learning using proxies,","venue":null,"work_id":"b9a770e2-1174-464b-97a0-d68ddbf5a0de","year":2017},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.303537Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:69f8517344b46072f49f33aec448d66c513cc247209d1f0436058af61038b0ef","observation_id":"3b5ef8e4-0ac4-495c-80f3-b8fa85e8c084","resolution":{"observed_at":"2026-08-10T18:44:40.657237Z","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":"2026-08-10T18:44:40.636821Z","title":"Softtriple loss: Deep metric learning without triplet sampling,","venue":null,"work_id":"8aff0c4f-afe6-40a2-8603-5a208a42f4e0","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.308341Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:be3e924f6484531888eed403fed643c37c2d27253aa04261d02b89a7745afb06","observation_id":"b7cceb0c-e22e-46e4-b9cf-974125a388ea","resolution":{"observed_at":"2026-08-10T18:44:40.642148Z","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":"2026-08-10T18:44:40.620899Z","title":"Proxynca++: Revisiting and revitalizing proxy neighborhood component analysis,","venue":null,"work_id":"5358fbef-e68c-4b4f-80c6-04d64ff02c04","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.312986Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:97de05787a1be7049e68b0f4d797a0146b5fbd129db32af61aaacc88391e2d44","observation_id":"62649483-235b-4695-8a81-b9b9c8d0354b","resolution":{"observed_at":"2026-08-10T18:44:40.626088Z","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":"2304.05884","last_updated":"2023-04-12T14:25:52Z","snapshot_observed_at":"2026-08-12T01:58:27.491720Z","submitted_at":"2023-04-12T14:25:52Z","title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.05884","snapshot_observed_at":"2026-08-10T18:44:39.431591Z","title":"Unicom: Universal and compact representation learning for image retrieval,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.431591Z"},"links":{"cited_paper":"/paper/2304.05884","citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:f1ef1291f322feff3e40c4981d283a13999fb93a5e82a6afc7eabd4ae31b0c7d","observation_id":"7fb6c16e-794c-410f-8032-6ec10d993da4","resolution":{"observed_at":"2026-08-10T18:44:39.431591Z","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":"2026-08-10T18:44:40.604932Z","title":"Supervised metric learning to rank for retrieval via contextual similarity optimization,","venue":null,"work_id":"c0093744-308a-43ae-a5ff-40ee14b8f7fc","year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.437224Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:d6eb15cb485e560f408f447d4ba3d0496f826abd36287acbf697aa5d8bf26012","observation_id":"e9ae21a8-deee-470e-94c9-184aa0520fad","resolution":{"observed_at":"2026-08-10T18:44:40.610462Z","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":"2026-08-10T18:44:40.588067Z","title":"Metricformer: A unified perspective of correlation exploring in similarity learning,","venue":null,"work_id":"a543dd13-e64e-4a0d-ad59-742bd45e5f17","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.442093Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:1d8336508f204bdebe9c53e5d839ccb3410f28547752eeeccd432f6a6863d16d","observation_id":"44800497-b2a4-47b7-82e3-7bd0a2f7bf2e","resolution":{"observed_at":"2026-08-10T18:44:40.593282Z","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":"2026-08-10T18:44:40.572621Z","title":"Causality-invariant interactive mining for cross-modal similarity learning,","venue":null,"work_id":"66edfddc-7972-45dc-8815-d98876ebf238","year":2024},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.446929Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:e0d7403bc01b4a15f5b1ed8d9f3ef911cc531ebedcab6dcb2f469e41b0b6d2df","observation_id":"f876fc59-ca04-4f22-a23f-f240018d0a75","resolution":{"observed_at":"2026-08-10T18:44:40.577823Z","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":"2026-08-10T18:44:40.557251Z","title":"Learning from noisy examples,","venue":null,"work_id":"2c3f0bf4-659b-4d09-a3f3-a9502bce9e39","year":1988},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.451838Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:9d1cf99eb2c0ca6ec142d741ad2bbb5181d581435505e470f7a1c93bd4b0e8d3","observation_id":"c3c23ca0-7c54-4fde-ba5d-fc4e816a2df7","resolution":{"observed_at":"2026-08-10T18:44:40.562021Z","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":"2026-08-10T18:44:40.541367Z","title":"Iterative learning with open-set noisy labels,","venue":null,"work_id":"302247d7-eba2-4b17-a507-a79e198862dc","year":2018},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.456407Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:e8a03182cb22db4515973cd26d02247a67fff1ba6f3fa69c4cadb9a0c4f47fa3","observation_id":"f3b1a7ba-1094-4de7-8f47-52b67962fc75","resolution":{"observed_at":"2026-08-10T18:44:40.546422Z","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":"2026-08-10T18:44:40.525886Z","title":"Which is better for learning with noisy labels: the semi-supervised method or modeling label noise?","venue":null,"work_id":"6fd11d0f-ff20-4f24-a5d6-1d68a8d7ca07","year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.461124Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:9964104283fe13ee2a3c946decd9a70ed063d168698fd128b2d1ebe271512f58","observation_id":"81f6d60d-1cf6-410e-bfb9-bc9d96dac634","resolution":{"observed_at":"2026-08-10T18:44:40.531002Z","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":"2026-08-10T18:44:40.509962Z","title":"Psnea: Pseudo- siamese network for entity alignment between multi-modal knowledge graphs,","venue":null,"work_id":"04761545-76cb-46a7-9fd1-a1c42aae3ce3","year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.465798Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:df66e99f2d49021d21d967da2755ce3bdc1ad91d61257031794322a4a44e4b6f","observation_id":"6db21d5f-f926-4417-b44a-f9f6f4509a6c","resolution":{"observed_at":"2026-08-10T18:44:40.515407Z","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":"2026-08-10T18:44:40.494077Z","title":"Positive-unlabeled learning with label distribution alignment,","venue":null,"work_id":"405ff35b-a22d-471f-a089-b944d901a2be","year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.470562Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:66a557400e0f991ca782f86baf7507095423f74e56fb60826fece9efc352c527","observation_id":"f2c5aabb-292a-4ea2-8f3e-ae3240b99c9f","resolution":{"observed_at":"2026-08-10T18:44:40.499389Z","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":"2026-08-10T18:44:40.478305Z","title":"How does disagreement help generalization against label corruption?","venue":null,"work_id":"cbf2622f-c5ee-460a-a057-1c0da26a8a7d","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.475229Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:c06efe12b8ff2fbcd8c40123008ec44feacfeb9bb5b029a83b87a44541f52f11","observation_id":"3fff90da-e7d9-433c-bc99-3a98d95569a1","resolution":{"observed_at":"2026-08-10T18:44:40.483429Z","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":"2026-08-10T18:44:40.462282Z","title":"Improving label noise robustness with data augmentation and semi-supervised learning (student abstract),","venue":null,"work_id":"fad9392a-17dc-4714-a4da-5d7894eadeb0","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.479772Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:7151aa30960421d9c7c9502e73bfab8fca02f21d8288c126bb5a6ad3ac61b7ed","observation_id":"577cb23e-1540-4d5f-a342-d75d5f20ba2e","resolution":{"observed_at":"2026-08-10T18:44:40.467599Z","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":"2026-08-10T18:44:40.446768Z","title":"Regularized contrastive partial multi-view outlier detection,","venue":null,"work_id":"cd286c6e-a6bf-4f50-a886-7920575368e4","year":2024},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.484144Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:ad18ecf2ace4db41a7af5b7d9bdc2b2caf5ca4b304712e62b1b0b9ad1f69e2f0","observation_id":"6783480a-bfea-492f-a330-e7e820be6a22","resolution":{"observed_at":"2026-08-10T18:44:40.452104Z","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":"2026-08-10T18:44:40.430263Z","title":"Uni- con: Combating label noise through uniform selection and contrastive learning,","venue":null,"work_id":"d2adf55c-f141-4377-880b-2eedd1dc7081","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.489040Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:27d55d5be6c9b79e7acb849201201a9f4099ee33fff5dd0acd4c9745bada2111","observation_id":"447a337e-2cfc-463b-acb4-87c9bd44a3d0","resolution":{"observed_at":"2026-08-10T18:44:40.435441Z","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":"2026-08-10T18:44:40.414449Z","title":"Label-retrieval-augmented diffusion models for learning from noisy labels,","venue":null,"work_id":"827fa7eb-1e20-4dcd-8f4a-6fbebdf8f745","year":2024},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.493634Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:6477f3936e7adb75e68a7945b4097f9b1f01908e18624610f3b674a5ea30d8b8","observation_id":"d493aed8-cbf6-40b4-97c1-2a49f6801bcf","resolution":{"observed_at":"2026-08-10T18:44:40.419588Z","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":"2026-08-10T18:44:40.397215Z","title":"Understanding and improving early stopping for learning with noisy labels,","venue":null,"work_id":"fad563c6-92e8-418d-a826-a58ecec68ad4","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.498157Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:50e3d291839d13d4267f0e18a984c5edea144c89c44af29bf592107a1efad283","observation_id":"e1c50774-5026-4f17-8548-9a569c344822","resolution":{"observed_at":"2026-08-10T18:44:40.402288Z","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":"2026-08-10T18:44:40.381640Z","title":"Early stopping against label noise without validation data,","venue":null,"work_id":"4ec46daa-ab83-4516-bf94-cc2f67ac7a96","year":2024},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.502814Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:12a388f1ed618f2fc49ee31993b34a7d02579186b703782bea0d2f41138f8082","observation_id":"7cd1473f-62ef-4f4f-a7a1-a3e14e5223aa","resolution":{"observed_at":"2026-08-10T18:44:40.387090Z","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":"2026-08-10T18:44:40.366021Z","title":"Dm2c: Deep mixed- modal clustering,","venue":null,"work_id":"306e1f64-f9b1-4ba9-b87d-1f18eaa6a3ca","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.507669Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:25a45479d88349fedbdc6bb4aec092865194716cae1028c856bb5f89ed09c9dd","observation_id":"fa1a1563-68b6-4212-8162-fcf7b2e734d0","resolution":{"observed_at":"2026-08-10T18:44:40.371381Z","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":"2026-08-10T18:44:40.350375Z","title":"When to learn what: Deep cognitive subspace clustering,","venue":null,"work_id":"fa82fe3b-dcbb-4092-9300-4e149c05c99f","year":2018},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.512503Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:a3c242e738a8eb355727759af6016fc7db07a5b1175760aa64bb14c3d797c37a","observation_id":"ca3167a7-b988-4923-92ff-bcb136c363b5","resolution":{"observed_at":"2026-08-10T18:44:40.355542Z","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":"2026-08-10T18:44:40.334900Z","title":"Duet robust deep subspace clustering,","venue":null,"work_id":"f7dfda51-462c-4bf5-8372-1b1d11e092f2","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.517297Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:85cb4d71294a439d00e592c7a38a36b0e332dd399350e5cd51b361da9bd21b8b","observation_id":"e80d9049-bd57-4d78-9b6f-717b5239b901","resolution":{"observed_at":"2026-08-10T18:44:40.339885Z","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":"2026-08-10T18:44:40.319709Z","title":"Robust distance metric learning via bayesian inference,","venue":null,"work_id":"b5ca3c62-61d2-42bb-806a-fa1f729fa70d","year":2017},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.522108Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:e44b291a697109cbcb6d8d4816fa3a492c01a5bdf7d1f8b19166fbf3ba734e8b","observation_id":"2655a934-8237-401f-a1b2-e9d5dc32af13","resolution":{"observed_at":"2026-08-10T18:44:40.324720Z","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":"2026-08-10T18:44:40.304243Z","title":"Deep metric learning by online soft mining and class-aware attention,","venue":null,"work_id":"3ec14df5-bab9-435f-a7af-52e53d07d8ce","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.526735Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:7c54f309b6cf7ee1c744811e5049103106688b9abe761620bd5ac1bc679d2dde","observation_id":"bbd266ea-5a3b-414d-bcba-328a309aac38","resolution":{"observed_at":"2026-08-10T18:44:40.309336Z","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":"1906.04087","last_updated":"2019-06-11T08:32:16Z","snapshot_observed_at":"2026-08-11T21:42:06.172366Z","submitted_at":"2019-06-10T16:00:06Z","title":"Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset","version":2},"cited_work":{"arxiv_id":"1906.04087","doi":null,"metadata_source":"pith","pith_arxiv_id":"1906.04087","snapshot_observed_at":"2026-08-10T18:44:39.730864Z","title":"Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset","venue":"cs.CV","work_id":"3d510183-7c24-43c8-8a2a-1fbcc98f47b3","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.531255Z"},"links":{"cited_paper":"/paper/1906.04087","citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:2283470baf10509d3898c520557ea715e6b3c11ff9342a749da9ed1e1e87c3fd","observation_id":"58e15dbf-cad4-49b4-ab39-009f59fc10a5","resolution":{"observed_at":"2026-08-10T18:44:39.738029Z","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":"2026-08-10T18:44:40.288166Z","title":"Hyperbolic vision transformers: Combining improvements in metric learning,","venue":null,"work_id":"9d928ab4-a5c2-4b6a-b698-dd82dfda08cf","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.536275Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:1e4afd4caa3cab6a81ec957470d36ea1899e67b3dd50f2c1c675a1116b9a240e","observation_id":"8760ceb3-4df9-4273-9cac-4eaaa6fe9ae8","resolution":{"observed_at":"2026-08-10T18:44:40.293008Z","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":"2026-08-10T18:44:40.273237Z","title":"Adaptive hierarchical similarity metric learning with noisy labels,","venue":null,"work_id":"122953a1-6bcb-40ad-b13b-ea66d7c2dc66","year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.540716Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:80360ce09d4c3f4b0ad1a5cc2a73ec5a333f7967bf45e0508b14cb918b771651","observation_id":"2363922c-c2e2-4977-8773-28126ff08962","resolution":{"observed_at":"2026-08-10T18:44:40.278031Z","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":"2026-08-10T18:44:40.257332Z","title":"Unsupervised hyperbolic metric learning,","venue":null,"work_id":"5d75cd78-9223-4c86-a945-ff6305c6b9e7","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.545577Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:21f64fed3b509f85daba5acb99e19fb1773fc38e54d8914609c5cf7aa0520891","observation_id":"4488bea5-4d46-4cc2-8884-fd6e5ace62fa","resolution":{"observed_at":"2026-08-10T18:44:40.262850Z","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":"2026-08-10T18:44:40.241876Z","title":"One for more: Selecting generalizable samples for generalizable reid model,","venue":null,"work_id":"b1edf27a-a7e1-4726-a232-0db2463cbb5e","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.550360Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:c58b35cf5177628608ca0370bc6b2ea499cd0b34f884b3bc4b9e8c98f8d59224","observation_id":"35fc11c8-f48a-450f-b73f-ca1beaed84e5","resolution":{"observed_at":"2026-08-10T18:44:40.246899Z","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":"2026-08-10T18:44:40.225310Z","title":"Collaborative refining for person re-identification with label noise,","venue":null,"work_id":"8407346f-13fa-4e52-a460-e27ec41ab992","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.554942Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:ddf580200fb4bf7af676fe7bcd2030870f620ac5b39e74c021b29dc491021a15","observation_id":"ceaff385-7ea5-4a21-9317-0beb4b481aef","resolution":{"observed_at":"2026-08-10T18:44:40.230975Z","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":"2026-08-10T18:44:40.206842Z","title":"Noise is also useful: Negative correlation-steered latent contrastive learning,","venue":null,"work_id":"234080ae-4a33-4e9c-b190-d69d325261a2","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.559428Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:b8c5fe4fd908272b6912c6995ebb23eb99ac7491de9117299b6953ff9b337244","observation_id":"132a007e-eeb9-4a01-be59-b6883fb99089","resolution":{"observed_at":"2026-08-10T18:44:40.212032Z","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":"2026-08-10T18:44:40.190823Z","title":"Learning to purifi- cation for unsupervised person re-identification,","venue":null,"work_id":"510e3674-7add-4b72-a681-553fd12d4a84","year":2023},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.563905Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:e0064a4f9bab91e158840c368a8f00c8456120fa2c8087ae836f984ae4c294da","observation_id":"a30f1731-01fd-464d-99ef-37c55dc4101d","resolution":{"observed_at":"2026-08-10T18:44:40.196038Z","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":"2026-08-10T18:44:40.174376Z","title":"Momentum contrast for unsupervised visual representation learning,","venue":null,"work_id":"5bb5110b-bbfe-4903-9ffd-d68f24da0099","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.569140Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:0f8da725c2528efec35ba6493af150887e1c41b86ff02ca6b8106ccae40aab5e","observation_id":"9522f7f9-0c2f-44ad-9639-1ef4d637ebb1","resolution":{"observed_at":"2026-08-10T18:44:40.179680Z","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":"2026-08-10T18:44:40.156885Z","title":"Online deep clustering for unsupervised representation learning,","venue":null,"work_id":"854819d5-937a-4473-8b2e-2d620e25adc4","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.573800Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:56feab4dc6780495fe4cb53ee98006a61878ad8a93bbf1a62a229258fdca8013","observation_id":"69e671de-5c19-47e7-9fb5-f660ec939750","resolution":{"observed_at":"2026-08-10T18:44:40.163212Z","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":"2026-08-10T18:44:40.140358Z","title":"Percolation and cluster distribution. i. cluster multiple labeling technique and critical concentration algorithm,","venue":null,"work_id":"8aefe382-61a4-4f8b-889c-0c0ad923a4c4","year":1976},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.578375Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:da24cebf2652dc5739828f54b1f48de341279be1e224f7d044087b47c3bf8bb3","observation_id":"cc0acfdc-cd4a-46a8-8a73-f155ab1ce83f","resolution":{"observed_at":"2026-08-10T18:44:40.145632Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T18:44:39.583242Z","title":"Hierarchical clustering schemes,","venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.583242Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:b7810aae51609c1ad78f30be48b75f124fddfe470d3409d9f24d973170b1d8fc","observation_id":"c648bac2-90d4-45f7-aac1-834f87ccf3c6","resolution":{"observed_at":"2026-08-10T18:44:39.583242Z","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":"2026-08-10T18:44:40.113342Z","title":"Mean shift: A robust approach toward feature space analysis,","venue":null,"work_id":"40956516-d320-4f4e-a319-8d558a014fde","year":2002},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.587913Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:28c16e85c361724c588f4c906930c4bb60ef6bcf7a7907e29cc1bb70c82740f3","observation_id":"81f152a3-a455-489f-8f91-578a2bab8e05","resolution":{"observed_at":"2026-08-10T18:44:40.118737Z","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":"2026-08-10T18:44:40.096823Z","title":"3d object representations for fine-grained categorization,","venue":null,"work_id":"35456835-9d14-4110-8713-e44a0117386c","year":2013},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.593620Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:26cf1e330133a026b627aa8d2154f44e4f8a9248c76e8d1fd4dfb776107c6fe9","observation_id":"b4291a98-39da-4c6b-82e5-f19053eb2f35","resolution":{"observed_at":"2026-08-10T18:44:40.102105Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T18:44:39.598227Z","title":"The caltech-ucsd birds-200-2011 dataset,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.598227Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:12bc5b083ed7759357cae1aac9c50594bdf7e351fa5d085ad55849f6705e51d1","observation_id":"1c343c1a-a9be-4132-9a74-a9661a369a2e","resolution":{"observed_at":"2026-08-10T18:44:39.598227Z","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":"2026-08-10T18:44:40.070421Z","title":"Deep metric learning via lifted structured feature embedding,","venue":null,"work_id":"31d6bd7b-63e1-4ba8-b7c7-68fe635c2ae4","year":2016},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.603352Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:b9a096f164492d7994d9f00cd7db1875c231dd5d5d3746f882046023bec98743","observation_id":"dd423012-90aa-46ff-ae1f-2415f2f240d2","resolution":{"observed_at":"2026-08-10T18:44:40.075314Z","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":"2026-08-10T18:44:40.054633Z","title":"Cleannet: Transfer learning for scalable image classifier training with label noise,","venue":null,"work_id":"9c95606e-cf8e-4c47-9175-7ebc077d1b21","year":2018},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.608226Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:e310c2bed0c2d53adebf0fc091bbd5e578b6ffea02063a5356dbccb1a55a03e5","observation_id":"ecdcb92a-1ed4-49f2-9073-d121658abcad","resolution":{"observed_at":"2026-08-10T18:44:40.059768Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T18:44:39.612805Z","title":"Food-101–mining discriminative components with random forests,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.612805Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:3dff5f065da80e5d43b4f8347616ff017adf831a630b2aedb45b103187702921","observation_id":"e2d4179b-504c-43fc-854c-5075db00da95","resolution":{"observed_at":"2026-08-10T18:44:39.612805Z","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":"2026-08-10T18:44:40.025516Z","title":"Ms-celeb-1m: A dataset and benchmark for large-scale face recognition,","venue":null,"work_id":"8fe98cbf-7702-44dc-af39-5b7c6963ea6f","year":2016},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.617538Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:7dd9d4db76292b94e480394dcbbc413c373b53de7d47bd8c59d1fb7e45b2b098","observation_id":"ba6b4d92-c3d8-40af-987a-02be5d06911f","resolution":{"observed_at":"2026-08-10T18:44:40.031098Z","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":"2026-08-10T18:44:40.007956Z","title":"Learning from massive noisy labeled data for image classification,","venue":null,"work_id":"58a6764c-1945-4167-bcb8-3ac6ef47b937","year":2015},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.623313Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:17735226d0d93fdf5e0bc83649ecc48634fef86f63b8f91339709daf1d773821","observation_id":"32c00107-191b-47af-8e36-5b252a954c8b","resolution":{"observed_at":"2026-08-10T18:44:40.013424Z","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":"2026-08-10T18:44:39.991126Z","title":"Learning with symmetric label noise: The importance of being unhinged,","venue":null,"work_id":"d659caca-1cdf-41a3-b852-2553dbb961c9","year":2015},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.627893Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:010b9c8cbf2c17667a6f786f94d409818588408dcff01a11fc998f303f47f52a","observation_id":"cfb76d21-afc1-4ffc-8b49-6cab6449fb37","resolution":{"observed_at":"2026-08-10T18:44:39.996751Z","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":"2026-08-10T18:44:39.974359Z","title":"Supervised contrastive learn- ing,","venue":null,"work_id":"c33b8784-f7b9-48b7-91aa-731eeb273426","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.632616Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:cbdacdb3c0a16431accb8c61cd12d10ac4e90b3ea524b56387aabb95fbcf237c","observation_id":"b33272ed-1a58-49f0-ab5d-261daf0aed84","resolution":{"observed_at":"2026-08-10T18:44:39.979338Z","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":"2026-08-10T18:44:39.957889Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift,","venue":null,"work_id":"8a4544e9-d458-45df-811e-a48f643de6ff","year":2015},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.637235Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:5b23a597f7e9f88a7f1a4ac54939373498f84ab8c1dfb106247cb1c9a5c7cb01","observation_id":"97fd85b7-b600-4b4b-a3dd-2667e1c408a7","resolution":{"observed_at":"2026-08-10T18:44:39.963262Z","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":"2026-08-10T18:44:39.941635Z","title":"A metric learning reality check,","venue":null,"work_id":"0cff7937-2f33-4621-bc6e-d6ac4070dfcd","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.642303Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:09123f071f0c31e68b1a2633aeba594fcca8de2b251c7d7522d22e55b589ba24","observation_id":"9946747a-1ccf-435d-8717-56162decbe3d","resolution":{"observed_at":"2026-08-10T18:44:39.946766Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T18:44:39.646805Z","title":"Paddlepaddle: An open-source deep learning platform from industrial practice,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.646805Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:eff9a035fe3f7fae9f83c37afcaa2b7af4e48f3fd66a728c04db5346651eb4d1","observation_id":"c7884dce-69e5-4f2a-b848-b246fea5ffcf","resolution":{"observed_at":"2026-08-10T18:44:39.646805Z","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":"2026-08-10T18:44:39.914698Z","title":"Dynamic class queue for large scale face recognition in the wild,","venue":null,"work_id":"91962340-5d40-4948-83f9-11dade5f5310","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.651743Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:1f2a032043a2d4f1bbd5e4ac40254291902e7e48446b5aabd0f6a8c2921d42fe","observation_id":"5d449f3c-2d85-4bf9-9b28-ba4351f4af46","resolution":{"observed_at":"2026-08-10T18:44:39.919922Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T18:44:39.656516Z","title":"Cosface: Large margin cosine loss for deep face recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.656516Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:9c582666bda118d6ac71fb51b27f045b832dea4e731275671848c6a192175141","observation_id":"9d9cedf3-c97e-420c-b2b4-2136d959945c","resolution":{"observed_at":"2026-08-10T18:44:39.656516Z","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":"2026-08-10T18:44:39.887413Z","title":"Noise-tolerant paradigm for training face recognition cnns,","venue":null,"work_id":"0a0ed737-c463-48d7-910c-6daff5357256","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.661631Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:61e68131351238ed6097ac5011a72d16559569fd0b422e1d339398387f67ae63","observation_id":"5d4057f1-4652-4f00-b9a0-c39dbd4c123a","resolution":{"observed_at":"2026-08-10T18:44:39.892924Z","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":"2026-08-10T18:44:39.870081Z","title":"Unequal-training for deep face recognition with long-tailed noisy data,","venue":null,"work_id":"336ff6ec-d09b-4a21-82dc-ec31d090e0a3","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.666567Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:9cf0ab162b925b07ffc473f7a4e400d3dd42856bb20ed4309ccdc5370d0e7e4b","observation_id":"ce6588a9-beb9-439c-ae81-9f5a07cbef22","resolution":{"observed_at":"2026-08-10T18:44:39.876229Z","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":"2026-08-10T18:44:39.852722Z","title":"Co-mining: Deep face recognition with noisy labels,","venue":null,"work_id":"6d0d1d90-f3b1-4a66-a886-31562f02ab67","year":2019},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.671360Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:5a4ce79d930a183f8c53fd2f3f42a9f44fea949ff118c859ea3bcb81187136de","observation_id":"0d6875fd-8df8-45ed-9aac-c51dce9a5ac6","resolution":{"observed_at":"2026-08-10T18:44:39.858003Z","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":"2026-08-10T18:44:39.835564Z","title":"Sub-center arcface: Boosting face recognition by large-scale noisy web faces,","venue":null,"work_id":"377e2673-d0b9-40af-8fc2-4b1d3e4ab6fb","year":2020},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.676274Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:ca824e11444fb65fcd8af09878afbd81fb01d8d305a1514a67fafded9241e7f2","observation_id":"6c3006ee-d427-450f-9a97-c10935cc9442","resolution":{"observed_at":"2026-08-10T18:44:39.840709Z","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":"2026-08-10T18:44:39.819531Z","title":"Switchable k-class hyperplanes for noise-robust representation learning,","venue":null,"work_id":"9cc4f144-129d-4b27-8111-35a72ccff14f","year":2021},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.681932Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:a572339a6be3eb6a8fe3ae58525c2207249e3023b50460cf0d0a3668a6fb6ab4","observation_id":"a648600b-1b87-414d-9302-e949e7f4d9c2","resolution":{"observed_at":"2026-08-10T18:44:39.824752Z","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":"2026-08-10T18:44:39.803355Z","title":"An efficient training approach for very large scale face recognition,","venue":null,"work_id":"b1a48683-6774-41ca-bef1-0851317331db","year":2022},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.686984Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:2d82d4320fe2e077e2ac4c6c524c22a2db0621abd55e89825a5c2cb0ea4df3d7","observation_id":"b94d5b0d-b51c-4c44-98cb-73a3d72761ab","resolution":{"observed_at":"2026-08-10T18:44:39.808350Z","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":"2026-08-10T18:44:39.786447Z","title":"Her research interests include machine learning and computer vision","venue":null,"work_id":"0d59ad98-11b4-453c-94fb-91c9d29849a6","year":1999},"citing_paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T18:44:39.691863Z"},"links":{"citing_paper":"/paper/2501.11063"},"observation_digest":"sha256:4a894882abae9649e605a21b71791b6eb600e7e075621e5fc23c7a4ec659dd4f","observation_id":"cd7169dc-5d21-4259-9d38-454c094fa004","resolution":{"observed_at":"2026-08-10T18:44:39.792112Z","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"}}],"paper":{"arxiv_id":"2501.11063","last_updated":"2025-01-19T14:41:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T01:58:51.482353Z","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection"},"reference_resolution":{"displayed":88,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":1,"verified_fuzzy":72},"total_outbound_references":88},"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 88 of 88 outbound references and 0 inbound Pith citation observations for arXiv:2501.11063."}