{"as_of":"2026-08-09T22:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5492145fe42f34e4a7ddfde30d1ca03f4b1a896adb2a564b2be62c690b1aa99a","coverage":[{"denominator":16,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T15:17:59.919440Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T20:21:13.104589Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.02572","snapshot_observed_at":"2026-08-01T20:21:13.104589Z","title":"VISReg: Variance-invariance- sketching regularization for JEPA training,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16681","last_updated":"2026-07-18T07:27:04Z","snapshot_observed_at":"2026-08-07T14:42:29.549919Z","submitted_at":"2026-07-18T07:27:04Z","title":"A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T20:21:13.104589Z"},"links":{"cited_paper":"/paper/2606.02572","citing_paper":"/paper/2607.16681"},"observation_digest":"sha256:5c9c4857550d79b54e7e759df8593c7a499e601257fac40a5080b6de2cd01d8b","observation_id":"1d1ae10a-0d8b-4312-849b-8fec1e5099e2","resolution":{"observed_at":"2026-08-01T20:21:13.104589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.02572","snapshot_observed_at":"2026-07-31T08:06:19.879794Z","title":"VISReg: Variance-invariance-sketching regularization for JEPA training.arXiv:2606.02572,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28415","last_updated":"2026-07-30T16:00:39Z","snapshot_observed_at":"2026-08-07T04:01:03.188629Z","submitted_at":"2026-07-30T16:00:39Z","title":"QQWorld: Quantile-Quantile Matching for World Model Regularization","version":1},"reference_index":1968,"source":"pdf_text","source_observed_at":"2026-07-31T08:06:19.879794Z"},"links":{"cited_paper":"/paper/2606.02572","citing_paper":"/paper/2607.28415"},"observation_digest":"sha256:851238e5efac7c536cee4493aa3cffb69f219c7c541e3deb242e30825246e108","observation_id":"a344c8ac-eb3e-49c9-b92f-3c408a8332dd","resolution":{"observed_at":"2026-07-31T08:06:19.879794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2606.02572/citation-record","integrity":"/paper/2606.02572/integrity","json":"/paper/2606.02572/citation-record.json","paper":"/paper/2606.02572"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2511.08544","last_updated":"2025-11-14T08:38:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-11T18:21:55Z","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","version":3},"cited_work":{"arxiv_id":"2511.08544","doi":"10.48550/arxiv.2511.08544","metadata_source":"pith","pith_arxiv_id":"2511.08544","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","venue":"cs.LG","work_id":"b2114616-92b2-4b9a-80db-89bda6422f4e","year":2025},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"cited_paper":"/paper/2511.08544","citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:d13f50dcdd9ac48ad71bae0799c09aa82e2d750865011fe051f3a35feaf57687","observation_id":"ae447b37-d6b2-4217-b2bc-826ab092ee54","resolution":{"observed_at":"2026-07-01T22:36:17.059211Z","resolver_source":"local_arxiv","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":"2026-08-03T19:08:37.72859+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-03T19:08:37.72859+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04297","last_updated":"2020-03-09T17:56:49Z","snapshot_observed_at":"2026-07-06T09:03:25.467987Z","submitted_at":"2020-03-09T17:56:49Z","title":"Improved Baselines with Momentum Contrastive Learning","version":1},"cited_work":{"arxiv_id":"2003.04297","doi":"10.48550/arxiv.2003.04297","metadata_source":"pith","pith_arxiv_id":"2003.04297","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Improved Baselines with Momentum Contrastive Learning","venue":"cs.CV","work_id":"f275e715-bcdc-487c-bc31-6f98d8a01f5c","year":2020},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"cited_paper":"/paper/2003.04297","citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:c6a64b4c3a9d235ea1d0f6844fde81e8ee059b654b7e32839b9ef0967474cfc4","observation_id":"f7f753b0-bbfa-46a1-bcac-6625c7e560ab","resolution":{"observed_at":"2026-07-01T22:36:17.065915Z","resolver_source":"local_arxiv","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T15:17:59.919440Z","title":"Bert: Pre-training of deep bidirectional transformers for lan- guage understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:55b40a5e9d29eaa88542e1018c836d5b7cd18265f2d77b43e1b6911326d3a6e1","observation_id":"796a45f2-7717-4748-b294-961a88f42bfe","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.01456","last_updated":"2026-05-28T16:40:33Z","snapshot_observed_at":"2026-08-08T05:45:43.696468Z","submitted_at":"2026-02-01T21:49:30Z","title":"Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations","version":2},"cited_work":{"arxiv_id":"2602.01456","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.01456","snapshot_observed_at":"2026-07-01T22:36:17.073636Z","title":"Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations","venue":"cs.LG","work_id":"60ca7d57-4979-49e4-838a-2198dd4144f1","year":2026},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"cited_paper":"/paper/2602.01456","citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:d8645863f4599d5d5fb9fc3edb4471aec524eeea8f8e225cab8172c713bfb5c8","observation_id":"cd5b7182-0dc6-4bdf-b859-a396f0c094bf","resolution":{"observed_at":"2026-07-01T22:36:17.075072Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T15:17:59.919440Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:b025ab93b9a5a21912b862888083387754b2c89c818f016be3ffbb90d982a2a2","observation_id":"a5782d23-903f-45e9-b3b1-7a22dd239107","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","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":"2026-06-28T15:17:59.919440Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:d6bb24cf46c14eb2688d1f9d734fd17b178f50d3667351159edede0c27be2e9b","observation_id":"d47bd86f-b591-4504-81ef-83178fa942db","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1306.5151","last_updated":"2013-06-21T14:31:57Z","snapshot_observed_at":"2026-07-06T03:16:28.287173Z","submitted_at":"2013-06-21T14:31:57Z","title":"Fine-Grained Visual Classification of Aircraft","version":1},"cited_work":{"arxiv_id":"1306.5151","doi":null,"metadata_source":"pith","pith_arxiv_id":"1306.5151","snapshot_observed_at":"2026-07-11T03:07:53.092922Z","title":"Fine-Grained Visual Classification of Aircraft","venue":"cs.CV","work_id":"ed360110-3ce4-4959-8c74-1785cd9e537d","year":2013},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"cited_paper":"/paper/1306.5151","citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:3047e39d80a24f4b36458e6a7b37360d1d5b8c263f73289a275039717d959311","observation_id":"e9cc8f31-b86d-475a-8443-69e2cfa3c3f5","resolution":{"observed_at":"2026-07-01T22:36:17.069287Z","resolver_source":"local_arxiv","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":"2104.10972","last_updated":"2021-08-05T15:04:28Z","snapshot_observed_at":"2026-08-06T21:17:51.553405Z","submitted_at":"2021-04-22T10:10:14Z","title":"ImageNet-21K Pretraining for the Masses","version":4},"cited_work":{"arxiv_id":"2104.10972","doi":"10.48550/arxiv.2104.10972","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.10972","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Imagenet-21k pretraining for the masses","venue":"arXiv (Cornell University)","work_id":"31e88324-e013-43f0-8c70-24aba0fa92fb","year":2021},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"cited_paper":"/paper/2104.10972","citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:620b95cc5da0cc05fbc884f987014a4fda5f0bbf899cf9789bc2f59f51e94642","observation_id":"aa4c9160-869c-476a-aa14-8fce30c641aa","resolution":{"observed_at":"2026-07-01T22:36:17.080856Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10104","last_updated":"2025-08-13T18:00:55Z","snapshot_observed_at":"2026-07-06T22:12:35.584339Z","submitted_at":"2025-08-13T18:00:55Z","title":"DINOv3","version":1},"cited_work":{"arxiv_id":"2508.10104","doi":"10.1055/a-2487-1252","metadata_source":"pith","pith_arxiv_id":"2508.10104","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DINOv3","venue":"cs.CV","work_id":"c8b07deb-8fe7-4e18-9620-f3569d3529ce","year":2025},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"cited_paper":"/paper/2508.10104","citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:193cc82bd99777d98bb3c23d4c383dbaa8653763e27a8d9174d6359a2e186a10","observation_id":"a2d47978-9784-418d-8976-a36e7d9842f0","resolution":{"observed_at":"2026-07-01T22:36:17.071973Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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":"2512.10794","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T16:59:58.043629Z","title":"What matters for representation alignment: Global information or spatial structure?","venue":null,"work_id":"f1f54511-fa19-44c2-9a85-6b1016b6d627","year":2025},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:e9c0cc8baa45fa346f5e2f93bbc7d9a17dbba9eef55d53c5384daf14088998c0","observation_id":"767a2e5d-fca9-4148-b2ab-14e335ec4046","resolution":{"observed_at":"2026-07-01T22:36:17.078001Z","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2512.19605","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T19:08:50.510527Z","title":"Kerjepa: Kernel discrepancies for euclidean self-supervised learning","venue":null,"work_id":"97806e09-defa-4706-83bf-ef32f14a3bde","year":2025},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:115a98c2c181748e9b9dfc9b02ba0cc4396efd85a8fcb5d3322d9f6a5f3cac46","observation_id":"77b8e864-1d92-406a-9a34-7840181b9b00","resolution":{"observed_at":"2026-07-01T22:36:17.062920Z","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T15:17:59.919440Z","title":"Both models are trained from scratch using the VISReg regularization objective and timm for backbones","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:658f4edd7bc4100e474555522fba97ebc908da48d895df95f8dc6b1f283fe4bc","observation_id":"78f208db-d1d2-497b-ae05-fc85b6c19e80","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","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":"2026-06-28T15:17:59.919440Z","title":"The multi-crop strategy uses Ng=2 global crops and Nl=8 local crops (98×98), still yielding 10 views per image","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:ccf68f8793a9ee05ef7177569c14ef963682ed09673d82cfcfc061c1468cf097","observation_id":"e31f21ed-e825-4a48-98a6-dfce8af427da","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","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":"2026-06-28T15:17:59.919440Z","title":null,"venue":null,"work_id":null,"year":1950},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:b9b7843e4d9a687f7e396a038b00e36a5af2c1087feca8de94dc5092d54784ca","observation_id":"15d6bdd2-7b6b-4be8-b386-555d7165f649","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","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":"2026-06-28T15:17:59.919440Z","title":"The shape component is the most impactful of the three DSSO objectives","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:ed99a2444580c360111e63f0f28fe6efc9d2d3e6a640f53356f064bf807cd1aa","observation_id":"3217c195-b4cc-43f6-b2d8-ee427023649b","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","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":"2026-06-28T15:17:59.919440Z","title":"15 VISReg : a scaling friendly method with a better generalizability","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T15:17:59.919440Z"},"links":{"citing_paper":"/paper/2606.02572"},"observation_digest":"sha256:8616d6878ca5e3683cfd0d4dd3ab6ce0117ad611b32ceec2c8ffd8a93ebd1159","observation_id":"6da3705c-2b7e-4cb8-9e30-4b6d332b044d","resolution":{"observed_at":"2026-06-28T15:17:59.919440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.02572","last_updated":"2026-06-01T17:58:01Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T23:42:58.036516Z","submitted_at":"2026-06-01T17:58:01Z","title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training"},"reference_resolution":{"displayed":16,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":8,"verified_exact":6,"verified_fuzzy":0},"total_outbound_references":16},"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 16 of 16 outbound references and 2 inbound Pith citation observations for arXiv:2606.02572."}