{"as_of":"2026-08-09T19:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:594271ad1c96bc13f889310125e8a578c436358115180c2579101a8a5bb6b7e2","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T20:43:25.887211Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T18:13:49.645874Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-21T18:14:17.397612Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"cited_work":{"arxiv_id":"2502.10478","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.10478","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"01269481-002f-4762-b119-4bb87d958d75","year":2025},"citing_paper":{"arxiv_id":"2511.17426","last_updated":"2026-05-14T21:30:52Z","snapshot_observed_at":"2026-08-02T07:34:27.041077Z","submitted_at":"2025-11-21T17:22:31Z","title":"Self-Supervised Learning by Curvature Alignment","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-05-21T18:13:49.645874Z"},"links":{"cited_paper":"/paper/2502.10478","citing_paper":"/paper/2511.17426"},"observation_digest":"sha256:11b3a7c4faf85cf176d93f64d69cf2f8b7ec4ae9ba0ecb5fad084eb31a284b6b","observation_id":"e7baccf7-3933-458c-8e1b-575f6ebc0b55","resolution":{"observed_at":"2026-05-21T18:14:17.400975Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.10478/citation-record","integrity":"/paper/2502.10478/integrity","json":"/paper/2502.10478/citation-record.json","paper":"/paper/2502.10478"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T20:43:27.366990Z","title":"A Simple Framework for Contrastive Learning of Visual Representations,","venue":null,"work_id":"884afab7-169d-44eb-9d3f-1e3bca2a5d99","year":2020},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.439722Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:64c39c614eb2f901494d472914c1da8a48531356a5e29955b3e229c52052b16e","observation_id":"82d4dc63-a977-49c7-aaaa-37c0a3c76442","resolution":{"observed_at":"2026-08-07T20:43:27.443315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:27.146084Z","title":"Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning,","venue":null,"work_id":"582f08a7-b349-4fa4-979d-edb9820c39d0","year":2020},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.443428Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:03ec5e586f10161bb4827409f4d45f95f39157341e6c765d4374713c7ca924dc","observation_id":"c9379c16-350a-4272-9f11-564042dfd578","resolution":{"observed_at":"2026-08-07T20:43:27.220962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.990759Z","title":"VICReg: Variance-Invariance- Covariance Regularization for Self-Supervised Learning,","venue":null,"work_id":"8ca9ffe2-7a9d-4204-a256-a2c4734f9118","year":2021},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.446171Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:f2c7c9abc0c82a56f9c1391d1843c961a6742e2a5508332b25021477484330c0","observation_id":"471b7cc1-8b82-4cc9-bac1-c92e2116204e","resolution":{"observed_at":"2026-08-07T20:43:27.065595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.926463Z","title":"Barlow Twins: Self-Supervised Learning via Redun- dancy Reduction,","venue":null,"work_id":"0f179347-f86a-41d9-92ca-87ca8ad4632a","year":2021},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.449241Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:0c832a42f8016103e5115d87a20ab7be2943195140fdbac216ef1aa4c6604d4c","observation_id":"5c11b81d-7174-4acf-b3cc-e97f06fa708d","resolution":{"observed_at":"2026-08-07T20:43:26.953593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.917856Z","title":"Momentum Contrast for Unsupervised Visual Representation Learning,","venue":null,"work_id":"6b393e30-27a4-42fc-8d72-4fce168f7d2c","year":2020},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.452992Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:89ebca644ff9072df4d8d196c8f631685ffd195d5737a6d5c7563b4805d2c6c4","observation_id":"c295f907-0cc5-40dc-892e-fe2668685440","resolution":{"observed_at":"2026-08-07T20:43:26.921512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.910035Z","title":"Loss Landscape of Self-Supervised Learning,","venue":null,"work_id":"c45631e2-6b2c-4373-8eb0-1ee549eee325","year":2022},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.455963Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:e3f4ddf74751c30303a1246054a2a17bc1aed468027098c618d5aafbf284d66c","observation_id":"e70b256e-50a2-413c-9dfe-ba5153aae023","resolution":{"observed_at":"2026-08-07T20:43:26.913124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.902431Z","title":"On the Transfer of Masses,","venue":null,"work_id":"f71e14e2-a45f-4ce9-a3b6-616f762f2dc7","year":1942},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.459149Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:4c6877b9db0ef87b67da4a0b0f4a8066872b6edf655a38101e346114a2de6dbf","observation_id":"293b1ea4-0603-4ca6-8303-1e53c2d98072","resolution":{"observed_at":"2026-08-07T20:43:26.905283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.894338Z","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transport,","venue":null,"work_id":"a0cac76c-7123-4e63-a6eb-3a3c55736f73","year":2013},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.461486Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:41621c54b5a42f8afb74f6c0e7f61aebace0d436b7737a65d2002be97de4464c","observation_id":"72bddbae-d35b-4cde-ba06-fca09912ce2b","resolution":{"observed_at":"2026-08-07T20:43:26.897638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.885939Z","title":"Optimal Transport for Domain Adaptation,","venue":null,"work_id":"be713b8c-37bf-4af2-869c-13e0a33536f3","year":2017},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.464302Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:c56dd03d49af466e3ee1080d029165e3a63ebd415a89c5f3388e2a52ddd65ac9","observation_id":"19a0807c-4eaf-4d8b-8e57-49f2c50da272","resolution":{"observed_at":"2026-08-07T20:43:26.889159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.876895Z","title":"Learning with a Wasserstein Loss,","venue":null,"work_id":"a1d902e7-f763-42e6-9050-8bd4c998c163","year":2015},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.467092Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:d423725dfd4a262215ddc2afa6a151f704d4a59dd13e1fe077e6117e8c7a5b6e","observation_id":"32bbdc71-ab39-4f63-aa73-55b6a11e55b4","resolution":{"observed_at":"2026-08-07T20:43:26.880363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.868591Z","title":"Visualizing Data using t-SNE,","venue":null,"work_id":"2bc2141a-a624-45fc-ba73-b4a181e1e00a","year":2008},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.469846Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:58cb6481ecb9cf70d88a72e12614d02f3d4b2166a0cdd7e64207c0db780e84de","observation_id":"f475ba8a-f815-438b-8476-91fda47e30c9","resolution":{"observed_at":"2026-08-07T20:43:26.871104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.860581Z","title":"Context-Aware Augmentation for Contrastive Self-Supervised Representation Learning,","venue":null,"work_id":"592fef87-02ad-495c-b830-ed8935f577c8","year":2023},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.492423Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:077b0de9aa0cce7e4cab68f023d4a41bb8c7f89f32e1f07122cfdae77481858e","observation_id":"a3410559-d856-4de7-afe3-a847f2282742","resolution":{"observed_at":"2026-08-07T20:43:26.863264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.852708Z","title":"Aligning Feature Distributions in VICReg Using Maximum Mean Discrepancy for Enhanced Manifold Awareness in Self-Supervised Representation Learning,","venue":null,"work_id":"1acdfcb6-c81e-4f90-a629-18f77adbccbe","year":2024},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.539179Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:b09c18c5f2a5835d2d941241ce80a26b5a8c5549096eccb2153150fe34caa61a","observation_id":"fa568526-d418-4726-9fcd-ad0275d8828d","resolution":{"observed_at":"2026-08-07T20:43:26.855799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.844823Z","title":"Geometric Dataset Distances via Op- timal Transport,","venue":null,"work_id":"eeff0830-7c66-477d-ac09-d778fbbd1ae9","year":2020},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.602365Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:0d311876665ca0b1a8496c744a65c6bb064cf23f4bbb86348f87a7f12fd32f4b","observation_id":"a16c138a-d5d5-43be-8f9a-6c721ae95cf7","resolution":{"observed_at":"2026-08-07T20:43:26.848122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2501.18875","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T20:43:26.015782Z","title":"Self-Supervised Learning Using Nonlinear Dependence,","venue":null,"work_id":"c4405bbe-c991-4c2d-b55f-62a02555c76e","year":2025},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.677646Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:0b3c6967baf543f33cb06e67fdbafc6883716933e95bd53c1bbfff6087b537c9","observation_id":"37e58df1-0c67-49d9-a1ab-d3fc0b296c0e","resolution":{"observed_at":"2026-08-07T20:43:26.023798Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.11926","last_updated":"2025-03-26T16:30:42Z","snapshot_observed_at":"2026-08-02T11:14:43.562416Z","submitted_at":"2021-09-24T12:40:48Z","title":"Sinkhorn Distributionally Robust Optimization","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.11926","snapshot_observed_at":"2026-08-07T20:43:25.715757Z","title":"Sinkhorn Distributionally Robust Opti- mization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.715757Z"},"links":{"cited_paper":"/paper/2109.11926","citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:04a0f98599f3535d69a7e1f07b3d717fd318a56dfdfd8d5e1d444511246ad059","observation_id":"7e4d1603-e183-405a-b0f1-4d4f13a05431","resolution":{"observed_at":"2026-08-07T20:43:25.715757Z","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":"2026-08-07T20:43:26.714856Z","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transport,","venue":null,"work_id":"c6b10ba0-6116-4e67-8c1e-132bad8b82e5","year":2013},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.803195Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:c31455b830a0615579cc072d6eda432985083d3cc2e7e79cf344db7b3b4fa235","observation_id":"7b39e630-d07e-4fb3-88e7-548956551f9d","resolution":{"observed_at":"2026-08-07T20:43:26.768737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.537117Z","title":"Optimal Transport: Old and New,","venue":null,"work_id":"a011a0c5-78c6-4529-a3da-672d6b5ede40","year":2009},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.845132Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:d0a9f2cdddc1bc51c95f6d4c8e734f5bd4fd1b63f9188f193a4c8f9387d88555","observation_id":"bb080f91-679d-417e-a111-00ad1098bbd6","resolution":{"observed_at":"2026-08-07T20:43:26.613084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.477997Z","title":"Joint Distribution Optimal Transportation for Domain Adaptation,","venue":null,"work_id":"69b8af8c-6b1e-408f-a37b-ac087ddab2a6","year":2017},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.847631Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:fda575fef29e64048ee91b2857a7930a3358a1ee4dc1092b9882cbe73b3ab768","observation_id":"370ceaa0-7cbe-4b45-96cb-94a5f3607542","resolution":{"observed_at":"2026-08-07T20:43:26.495752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.471038Z","title":"Optimal Transport for Domain Adaptation,","venue":null,"work_id":"5fceadef-7889-49e8-94ab-1eb7d21e4d0b","year":2016},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.850149Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:ab468d5c239a85fd72bee22084980cd010ce499a5e9ab3463e615a40cd0783c8","observation_id":"10dbf7ba-5b27-474c-b2f1-40f753b1ae57","resolution":{"observed_at":"2026-08-07T20:43:26.473543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.463085Z","title":"DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation,","venue":null,"work_id":"aa1dcadc-bb69-4b82-bb99-21a93c2bb0c7","year":2018},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.852490Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:4bf2fdce75706862efa21e93842cb28dcf1dbb720fa7e3856102a87b4ac57cd8","observation_id":"357404f2-752e-4d5a-aee1-18eba986b0b7","resolution":{"observed_at":"2026-08-07T20:43:26.466078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.454907Z","title":"Wasserstein Generative Adversarial Networks,","venue":null,"work_id":"cf384d84-452c-4203-ba29-b2247153d7e9","year":2017},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.854374Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:4d58d1a7dc798899b57e4def70e0323769770caac5752a10d9f831df5356b153","observation_id":"d8ecf6cc-babc-4a45-b624-f80f42bc9f5a","resolution":{"observed_at":"2026-08-07T20:43:26.458152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.447503Z","title":"Wasserstein Auto-Encoders,","venue":null,"work_id":"c9b48832-dd08-48e9-9ad0-9da4f611cae8","year":2018},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.857029Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:b94b6db145b2de407f805b978dc36c4bdc2b16f18c47d0eb05cf7de4e7cdaf43","observation_id":"d3e5b7c6-eb68-4bda-b4e8-8bf6ac74087c","resolution":{"observed_at":"2026-08-07T20:43:26.450608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.439278Z","title":"Improved Training of Wasserstein GANs,","venue":null,"work_id":"949c9963-71ed-4aaa-9887-6ce615d5c0ac","year":2017},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.859720Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:1c4afcfdf7ec2d3cec05e663012dd24554aee3855e867ca0c17bf4bd641a634d","observation_id":"daf66c13-884e-4c67-b620-0daf1bc1cf49","resolution":{"observed_at":"2026-08-07T20:43:26.442599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.431617Z","title":"Learning Generative Models with Sinkhorn Divergences,","venue":null,"work_id":"2e52e48c-0317-41db-bdaa-fbc21f863d15","year":2019},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.862362Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:87c38da253410ab888241a7d646b990c76026658779482f3baa556839b6d353e","observation_id":"66ddf595-45a6-46b9-84ca-f8fda57e5184","resolution":{"observed_at":"2026-08-07T20:43:26.434334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.414868Z","title":"Fast Computation of Wasserstein Barycen- ters,","venue":null,"work_id":"ad738d10-8f6b-457e-9643-47f581e6472d","year":2014},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.867815Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:96a17976039e135adbed06b3e98b4cb0d1f3b76ff8f632748d5a37660bc158fa","observation_id":"918b23a9-545e-4812-a6cc-bd1c23cb4176","resolution":{"observed_at":"2026-08-07T20:43:26.418133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.422998Z","title":"Unbalanced Optimal Transport in High-Dimensional Machine Learning,","venue":null,"work_id":"17008d8a-2d57-4df1-a86f-3c7477fe449b","year":2021},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.869853Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:885422d9363ef54357914c7f01d1c4ed0610a1c7f590d0dc6b2ef06ffbe90166","observation_id":"a63e25fc-d2bd-4539-b810-39e8a1b16f6f","resolution":{"observed_at":"2026-08-07T20:43:26.426352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.290683Z","title":"Mapping Estimation for Discrete Optimal Transport,","venue":null,"work_id":"f8f09adc-76ad-4ec8-a3ec-a0e7a9721287","year":2016},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.872602Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:3f8d2ffe04ccb2c19321ee09a070eba73f2a8f46be4e5aa4bcc2bd58d24bd757","observation_id":"3f039f17-6e68-4090-ac9d-a2f0120812dd","resolution":{"observed_at":"2026-08-07T20:43:26.371991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.155104Z","title":"Wasserstein Dictionary Learning: Optimal Transport-based Unsupervised Nonlinear Dictionary Learning,","venue":null,"work_id":"e83bf448-a9fc-4ef7-ac1a-9bc72831d939","year":2018},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.875389Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:afcc655808fa66e3578af104ec14c30daf6e62a25a9de1d6ad839b5b8cd9a1b4","observation_id":"83574955-6cba-4482-aaa1-cb263f6eb379","resolution":{"observed_at":"2026-08-07T20:43:26.231751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.057527Z","title":"Sinkhorn Autoencoders,","venue":null,"work_id":"ad42b164-92b4-4520-9507-aa23d51bdd17","year":2020},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.877954Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:2873ae2c143f8485aae59c3551564e353fbb2c401bf2f769d3971c30537de3da","observation_id":"8c9e08d6-1a4d-4b44-9bde-ae232ac56de5","resolution":{"observed_at":"2026-08-07T20:43:26.073779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.049150Z","title":"Learning Generative Models with Sinkhorn Divergences,","venue":null,"work_id":"618627c5-18f9-44d7-8495-6b6a92a37875","year":2018},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.880826Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:623a4c7ba5e70a0ed8d110ef65feabc4d6a3290467aa7c2685168f2e96d8997e","observation_id":"6b9e69f6-9b8a-4d98-849e-838e194fbc20","resolution":{"observed_at":"2026-08-07T20:43:26.052277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.039763Z","title":"Self-labelling via Simul- taneous Clustering and Representation Learning,","venue":null,"work_id":"9ee903cd-adaf-44d2-8793-8caa56e11591","year":2019},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.883836Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:15c361bca675498c505302663a8323cfa9c52e73119e0760c52c3b540d31204a","observation_id":"ec2f606e-c2f3-4d16-8540-3d57db4aa123","resolution":{"observed_at":"2026-08-07T20:43:26.042710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T20:43:26.030778Z","title":"Contrastive Self-Supervised Learning: Review, Progress, Challenges and Future Research Direc- tions,","venue":null,"work_id":"43dc2b95-acbd-4f12-8f18-ba2631f86fd8","year":2022},"citing_paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T20:43:25.887211Z"},"links":{"citing_paper":"/paper/2502.10478"},"observation_digest":"sha256:5a7ef8b932a67d29bcfd583d2fa0a4dbaf59e8dc4bbb8c450b8472a5bfdfc882","observation_id":"b4932038-b0b7-433f-994c-7b09794edd6a","resolution":{"observed_at":"2026-08-07T20:43:26.033841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.10478","last_updated":"2025-02-13T19:49:25Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T16:06:16.296270Z","submitted_at":"2025-02-13T19:49:25Z","title":"SinSim: Sinkhorn-Regularized SimCLR"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":1,"verified_fuzzy":31},"total_outbound_references":33},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2502.10478."}