{"as_of":"2026-08-09T18:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:85981c3d1fa200c838c275c32398bd4d36073e0c89f3d045c93cc73e2274b751","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T18:32:14.158944Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T12:45:29.331367Z","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":"2026-07-04T00:39:16.420475Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10385","snapshot_observed_at":"2026-08-05T12:45:29.331367Z","title":"Simplifying dino via coding rate regularization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.01360","last_updated":"2025-09-01T10:59:39Z","snapshot_observed_at":"2026-08-08T07:54:44.423333Z","submitted_at":"2025-09-01T10:59:39Z","title":"M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T12:45:29.331367Z"},"links":{"cited_paper":"/paper/2502.10385","citing_paper":"/paper/2509.01360"},"observation_digest":"sha256:25b0372814dcc95eafad6932a8701578017becdf1ac8d389885f70c06f37a66e","observation_id":"552fa559-5a28-4521-9ebe-06403ca08992","resolution":{"observed_at":"2026-08-05T12:45:29.331367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10385","snapshot_observed_at":"2026-08-04T18:12:27.419062Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10151","last_updated":"2025-09-12T11:27:17Z","snapshot_observed_at":"2026-08-09T08:24:48.428164Z","submitted_at":"2025-09-12T11:27:17Z","title":"BenchECG and xECG: a benchmark and baseline for ECG foundation models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T18:12:27.419062Z"},"links":{"cited_paper":"/paper/2502.10385","citing_paper":"/paper/2509.10151"},"observation_digest":"sha256:8fa5a2a0a4ecc3a8500ba2008893da2497689dc429e429716a875b0bad1020c2","observation_id":"3fc82161-4b5e-42c5-a847-020cdb5414c7","resolution":{"observed_at":"2026-08-04T18:12:27.419062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"cited_work":{"arxiv_id":"2502.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.10385","snapshot_observed_at":"2026-07-04T00:39:16.420475Z","title":"Simplifying dino via coding rate regularization","venue":null,"work_id":"20ac85fe-edf6-4b11-95cb-9a1022b833fc","year":2025},"citing_paper":{"arxiv_id":"2604.18390","last_updated":"2026-04-20T15:13:39Z","snapshot_observed_at":"2026-07-06T23:05:17.639285Z","submitted_at":"2026-04-20T15:13:39Z","title":"Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T05:05:37.126053Z"},"links":{"cited_paper":"/paper/2502.10385","citing_paper":"/paper/2604.18390"},"observation_digest":"sha256:45765a959b486a80151d0ffcc764b3bc74cf6499f4c5ee3cfcc01b64c5de808e","observation_id":"ed42b9b6-bcd3-4254-94d2-375d45bad332","resolution":{"observed_at":"2026-05-10T10:09:08.429481Z","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":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"cited_work":{"arxiv_id":"2502.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.10385","snapshot_observed_at":"2026-07-04T00:39:16.420475Z","title":"Simplifying dino via coding rate regularization","venue":null,"work_id":"20ac85fe-edf6-4b11-95cb-9a1022b833fc","year":2025},"citing_paper":{"arxiv_id":"2605.20107","last_updated":"2026-05-19T16:57:47Z","snapshot_observed_at":"2026-07-06T23:30:44.092395Z","submitted_at":"2026-05-19T16:57:47Z","title":"Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-20T06:47:47.122794Z"},"links":{"cited_paper":"/paper/2502.10385","citing_paper":"/paper/2605.20107"},"observation_digest":"sha256:bb9eb08f276e85e180ca70e250170555c819ed31a69ff272db6c759579338619","observation_id":"6f065ec6-111f-48b2-bde1-cbe81605b4bc","resolution":{"observed_at":"2026-05-20T06:48:05.666487Z","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":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"cited_work":{"arxiv_id":"2502.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.10385","snapshot_observed_at":"2026-07-04T00:39:16.420475Z","title":"Simplifying dino via coding rate regularization","venue":null,"work_id":"20ac85fe-edf6-4b11-95cb-9a1022b833fc","year":2025},"citing_paper":{"arxiv_id":"2605.29691","last_updated":"2026-07-02T11:32:18Z","snapshot_observed_at":"2026-07-06T23:39:05.858969Z","submitted_at":"2026-05-28T09:52:52Z","title":"Unsupervised Semantic Segmentation Facilitates Model Understanding","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T08:37:02.350175Z"},"links":{"cited_paper":"/paper/2502.10385","citing_paper":"/paper/2605.29691"},"observation_digest":"sha256:c4a9c4ea7a573caceb9b21a8125618017481ba5f8bd75195394de09109278ea3","observation_id":"bb45f735-f4f7-48b9-8440-dcdc16b7ed51","resolution":{"observed_at":"2026-06-29T08:43:15.470918Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"cited_work":{"arxiv_id":"2502.10385","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.10385","snapshot_observed_at":"2026-07-04T00:39:16.420475Z","title":"Simplifying dino via coding rate regularization","venue":null,"work_id":"20ac85fe-edf6-4b11-95cb-9a1022b833fc","year":2025},"citing_paper":{"arxiv_id":"2605.29691","last_updated":"2026-07-02T11:32:18Z","snapshot_observed_at":"2026-07-06T23:39:05.858969Z","submitted_at":"2026-05-28T09:52:52Z","title":"Unsupervised Semantic Segmentation Facilitates Model Understanding","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-04T00:34:21.224797Z"},"links":{"cited_paper":"/paper/2502.10385","citing_paper":"/paper/2605.29691"},"observation_digest":"sha256:1155f4e9008be75c2af5a64c4868fce4694f0177ea993566211187cf457f2d8d","observation_id":"6e6b39c2-9e04-418a-a8bf-967dd515ce35","resolution":{"observed_at":"2026-07-04T00:39:16.422042Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2502.10385/citation-record","integrity":"/paper/2502.10385/integrity","json":"/paper/2502.10385/citation-record.json","paper":"/paper/2502.10385"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:13.218256Z","title":"Self-supervised learning from images with a joint-embedding predictive architecture","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.218256Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:120f78a9a2174e55125b8fe66f93c39bb654ebaf76a325cb87f0bb7b19a13638","observation_id":"09dfed78-ca78-4f02-86ea-46764dfad435","resolution":{"observed_at":"2026-08-07T18:32:13.218256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.02366","last_updated":"2024-09-14T03:35:04Z","snapshot_observed_at":"2026-08-09T07:41:33.120488Z","submitted_at":"2023-12-04T21:47:10Z","title":"Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.02366","snapshot_observed_at":"2026-08-07T18:32:13.242796Z","title":"Towards general purpose vision foundation models for medical image analysis: An experimental study of dinov2 on radiology benchmarks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.242796Z"},"links":{"cited_paper":"/paper/2312.02366","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:6ac5de47a8fa5ac38f603d75034552995926be11afb5e097c648cd7470bc08fa","observation_id":"86a6f0d2-234e-43e1-944a-890ebfa24ed0","resolution":{"observed_at":"2026-08-07T18:32:13.242796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.04906","last_updated":"2022-01-28T12:23:37Z","snapshot_observed_at":"2026-07-06T11:08:17.373935Z","submitted_at":"2021-05-11T09:53:21Z","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.04906","snapshot_observed_at":"2026-08-07T18:32:13.247339Z","title":"Vicreg: Variance-invariance-covariance regularization for self-supervised learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.247339Z"},"links":{"cited_paper":"/paper/2105.04906","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:86e261fe37a9ed6741f95ceac8b090ed36cb4f6ab85475913611a763f2d18557","observation_id":"f80e8cf8-a0cb-4de8-81e4-0d33f7f2a1ab","resolution":{"observed_at":"2026-08-07T18:32:13.247339Z","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":"2026-08-07T18:32:14.727294Z","title":"J., Gy \\\"o rfi, L., Van der Meulen, E","venue":null,"work_id":"72004c55-5db5-4273-a13d-95036ea229d3","year":1997},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.251245Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:9c20a4142686632c86d683afeb4ebeeab5842e21bfa0566ad43371d852a62f78","observation_id":"a02c895c-4b09-4675-b0e1-7d108b4e706f","resolution":{"observed_at":"2026-08-07T18:32:14.730105Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:13.254225Z","title":"D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.254225Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:e6b3654f01667c5588a440e07b9abeb2b86da7135e151b0afe2aaed41ca6d65d","observation_id":"7080e787-4cf6-42b5-87e4-876c24779ba5","resolution":{"observed_at":"2026-08-07T18:32:13.254225Z","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":"2026-08-07T18:32:13.257735Z","title":"Unsupervised learning of visual features by contrasting cluster assignments","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.257735Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:c312c58ea8b8e26977dd568269076e21f8cf607e1e21a7a6125887e3d11fa899","observation_id":"62aa4929-5496-4643-8573-166f628f59b6","resolution":{"observed_at":"2026-08-07T18:32:13.257735Z","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":"2026-08-07T18:32:13.301329Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.301329Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:7bd0d10f4fe0728471df1f290309811b8779ca66080480ff10a3a0a0bc12e0be","observation_id":"f00608ee-8fbf-428f-97b9-9e781c576b92","resolution":{"observed_at":"2026-08-07T18:32:13.301329Z","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":"2026-08-07T18:32:13.362341Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.362341Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:9bc63bc4af323cf6fb310ffe217a28858fc84404245a12f25e9e37877b9947a1","observation_id":"f1721a16-e09d-4f36-ad9e-fdf1d5cc539e","resolution":{"observed_at":"2026-08-07T18:32:13.362341Z","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":"2026-08-07T18:32:13.393878Z","title":"and He, K","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.393878Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:0ed34ac748ebdb194238595e3fae84574a8b379a5b3e76897b5815da0fb1fea0","observation_id":"06c888b2-4f7a-4fe0-af28-fc48cba395fb","resolution":{"observed_at":"2026-08-07T18:32:13.393878Z","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":"2026-08-07T18:32:13.396187Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.396187Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:6eab0b50ae0735b8ff0f8635fed190b6bdb11052fc6240b924049937c206de62","observation_id":"5840d80f-afc9-4c63-aada-f2f6df24fa88","resolution":{"observed_at":"2026-08-07T18:32:13.396187Z","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":"2026-08-07T18:32:14.692573Z","title":null,"venue":null,"work_id":"f87a8df2-86ee-451a-bd54-2f5c9667d9a6","year":2022},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.419659Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:972b82ed0eb1ef39535f2465f7cf1dc00d465408b83bc8d81df94b3dded08d59","observation_id":"24502955-cd8b-4f64-8e87-407afd56d4a1","resolution":{"observed_at":"2026-08-07T18:32:14.695947Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-07T18:32:14.681334Z","title":"and Fournier, N","venue":null,"work_id":"70edc4b2-a617-40d4-88c1-3f53a8ca2be9","year":2017},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.449930Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:0cdb99fd90b9f2167b3f46e59e3846e5695c3533e5f768ee355c2d0c5c077920","observation_id":"86ea3955-305f-4e1d-a44b-13afcb2d1016","resolution":{"observed_at":"2026-08-07T18:32:14.685673Z","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":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-07T18:32:13.452817Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.452817Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:3b2c6287d2e93b7a4c8b45c83eca11d90c0db07959a5e266bfb5a656cbd8a56e","observation_id":"c8db3808-b65a-4105-9b00-84744998649f","resolution":{"observed_at":"2026-08-07T18:32:13.452817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-07T18:32:13.456641Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.456641Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:72778ef0648c17d807f43f44cfd57e0879666da6c4a8a7438c04df66c5176714","observation_id":"5ab352de-48fa-4137-8ebb-096f01014fc9","resolution":{"observed_at":"2026-08-07T18:32:13.456641Z","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":"2026-08-07T18:32:14.669958Z","title":"Masked autoencoders as spatiotemporal learners","venue":null,"work_id":"1c0364fd-cc1c-47dc-8dc1-b9624673b0b1","year":2022},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.460724Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:d22740a2e457dfdee29d9bd2221955c3c99e8a39e803f0dab50bcc9fd8ae402e","observation_id":"df7d181e-23ae-4eb2-9a4f-f134d301c114","resolution":{"observed_at":"2026-08-07T18:32:14.674643Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:13.463971Z","title":"Bootstrap your own latent-a new approach to self-supervised learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.463971Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:b4ef267fca923c13cdbe31e3f3a7970d2b8c008b3fa4d384e2e2c66a8bc889e4","observation_id":"02327a77-254f-4bdc-bf17-7ec412978422","resolution":{"observed_at":"2026-08-07T18:32:13.463971Z","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":"2026-08-07T18:32:14.656821Z","title":"Dimensionality reduction by learning an invariant mapping","venue":null,"work_id":"036492e5-81ae-4a34-9d08-2db01a00f800","year":2006},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.479507Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:409e19641f44db3739c761033264d3dfe6afe5cb5aefc128a02359b36b8cf22e","observation_id":"ca774501-a91b-4a05-9974-f86d64335ed7","resolution":{"observed_at":"2026-08-07T18:32:14.660517Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:13.541735Z","title":"Momentum contrast for unsupervised visual representation learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.541735Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:8c42fe172cef44826510330f2ec0326a466572d48e8a61b97710a8876b7cc5f4","observation_id":"157b005d-fa09-4669-ab15-3117819d21d2","resolution":{"observed_at":"2026-08-07T18:32:13.541735Z","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":"2026-08-07T18:32:13.573769Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.573769Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:ff2060d0884d4cbbc9e13db37c730efad7f0e0c9729dc6930ced1cee3872cc99","observation_id":"81a54f45-785c-43d3-84fc-adeffc6c7c2e","resolution":{"observed_at":"2026-08-07T18:32:13.573769Z","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":"2026-08-07T18:32:14.605099Z","title":"and Marshall, A","venue":null,"work_id":"4079104b-37bf-4484-81b0-ad67c8cae5da","year":1953},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.577863Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:ae4157a8c0385b54ecf9c830ed3c081d6e1c54e4b087ce92dea3352369655d57","observation_id":"8d46b3ca-eeeb-409a-9657-2f056d330e98","resolution":{"observed_at":"2026-08-07T18:32:14.643214Z","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":{"arxiv_id":"2201.10000","last_updated":"2022-01-24T23:13:37Z","snapshot_observed_at":"2026-08-08T18:21:07.282968Z","submitted_at":"2022-01-24T23:13:37Z","title":"Neural Manifold Clustering and Embedding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.10000","snapshot_observed_at":"2026-08-07T18:32:13.581465Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.581465Z"},"links":{"cited_paper":"/paper/2201.10000","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:2427d2bf6fb9562b9e3756f76596fedaf39f38678c2bdde5e72573e2a9c2c0bd","observation_id":"d1df81c7-1f7a-4d29-af4f-bdb371246ed6","resolution":{"observed_at":"2026-08-07T18:32:13.581465Z","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":"2026-08-07T18:32:13.633210Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.633210Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:7d4b137c6b29f05894b6a76edb1214cfa232722b7cdd64032b2a330805de27d2","observation_id":"470c664d-ab88-4345-a8d0-04edc173b91f","resolution":{"observed_at":"2026-08-07T18:32:13.633210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-07T18:32:13.636448Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.636448Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:6aa761a04251fcb503283a283c341a5a9325cb64d36c85d82f0ca10b6d769b9a","observation_id":"7ca0bbcf-b337-4633-93b6-596cb01fb6bf","resolution":{"observed_at":"2026-08-07T18:32:13.636448Z","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":"2026-08-07T18:32:14.591784Z","title":"Segmentation of multivariate mixed data via lossy data coding and compression","venue":null,"work_id":"d5f5bf0b-5d24-4bd3-a633-c51020461ab3","year":2007},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.640214Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:b0db75696c9f0f9d06b596cd6371519124c13d5b6dc10f63998f36bdcafade11","observation_id":"aac8d634-c002-4ab3-8150-0fadbd12e040","resolution":{"observed_at":"2026-08-07T18:32:14.595510Z","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":{"arxiv_id":"2410.19560","last_updated":"2024-10-25T13:48:12Z","snapshot_observed_at":"2026-07-06T19:39:42.675941Z","submitted_at":"2024-10-25T13:48:12Z","title":"Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning","version":1},"cited_work":{"arxiv_id":"2410.19560","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.19560","snapshot_observed_at":"2026-08-07T18:32:14.238221Z","title":"Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning","venue":"cs.CV","work_id":"d7ded315-26f3-4dfa-897a-ea79bf4e06f6","year":2024},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.643767Z"},"links":{"cited_paper":"/paper/2410.19560","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:bbb64fcde1ef0a75c13f9931c6774748aa85744e215a46e1b9e2e08652ee480a","observation_id":"10f57125-7775-42c5-8741-a63c6d2281bc","resolution":{"observed_at":"2026-08-07T18:32:14.276492Z","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":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-07T18:32:13.647184Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.647184Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:08a7ef589f02ff5a9bd9ec37c73d5257ecd0a2084e1dd71fa9215a52e199b2f2","observation_id":"83f2fdca-f5a9-420b-8490-80d0d1e4944e","resolution":{"observed_at":"2026-08-07T18:32:13.647184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-09T18:02:17.307812Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-07T18:32:13.691301Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.691301Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:f36ab9a3ac3fa3b9cf6f6be88c22ab0ba93f4832085d1ce8817c0e5745c77588","observation_id":"d7168fac-b78d-4379-80ee-2d8ae897f7dd","resolution":{"observed_at":"2026-08-07T18:32:13.691301Z","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":"2026-08-07T18:32:14.532818Z","title":"W., Buchanan, S., Yu, Y., and Ma, Y","venue":null,"work_id":"dd6c33de-3af7-4d52-9ef9-9aa072c5def6","year":2023},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.768045Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:c84aed68c7b6247e77f8a94c67ce9f06776de69909dae5ea1f811fdb1b0af1a3","observation_id":"4973898e-01b5-4b4a-8a3d-7f782711a776","resolution":{"observed_at":"2026-08-07T18:32:14.586357Z","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":{"arxiv_id":"1704.00675","last_updated":"2018-03-01T17:50:08Z","snapshot_observed_at":"2026-08-02T10:51:13.194643Z","submitted_at":"2017-04-03T16:44:46Z","title":"The 2017 DAVIS Challenge on Video Object Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.00675","snapshot_observed_at":"2026-08-07T18:32:13.831893Z","title":"The 2017 davis challenge on video object segmentation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.831893Z"},"links":{"cited_paper":"/paper/1704.00675","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:775c865cbe3e12b39a92ea6f764121b9273a410454316e239de4a7d18b876d25","observation_id":"0fdd4316-e04b-435c-b320-73f56bb5afc5","resolution":{"observed_at":"2026-08-07T18:32:13.831893Z","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":"2026-08-07T18:32:13.835123Z","title":"Improving language understanding by generative pre-training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.835123Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:6b5d086359055490204a5990a11dc8011448d4369c2990536d3684676bc5379c","observation_id":"caef8c6d-1a64-4071-a364-b2342413eef2","resolution":{"observed_at":"2026-08-07T18:32:13.835123Z","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":"2026-08-07T18:32:13.885418Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.885418Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:67ca19521e97d9b6f137d241b4d400a19093fad63918e0208247aec009d92eaa","observation_id":"7d41f663-6982-48b1-98c2-ef1347c553e1","resolution":{"observed_at":"2026-08-07T18:32:13.885418Z","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":"2026-08-07T18:32:13.918091Z","title":"W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.918091Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:640e1187b80287f0353a5b06a3c316272334f0dfdbac93dd05ba4aeb507af625","observation_id":"145fbe42-336a-4e8b-ae3c-4f627abf53da","resolution":{"observed_at":"2026-08-07T18:32:13.918091Z","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":"2026-08-07T18:32:14.487477Z","title":"and Kingma, D","venue":null,"work_id":"bc8f84e4-d1f2-4388-9f26-6c3c06787f26","year":2016},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.922062Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:c891c02de87fe5e77af0a3fc8f044ce2e151fb7e4a61324fa655f16ccd5b20d7","observation_id":"48303c01-df05-4bc4-b4d6-34df08d2d969","resolution":{"observed_at":"2026-08-07T18:32:14.515902Z","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":{"arxiv_id":"2406.09366","last_updated":"2024-06-13T17:49:56Z","snapshot_observed_at":"2026-08-09T01:08:44.441447Z","submitted_at":"2024-06-13T17:49:56Z","title":"Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09366","snapshot_observed_at":"2026-08-07T18:32:13.925908Z","title":"B., Carranza, A., Isik, B., Unell, A., Khona, M., Yerxa, T., LeCun, Y., Chung, S., et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.925908Z"},"links":{"cited_paper":"/paper/2406.09366","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:6e5393da10dded450807d2a16bf655327f4a9f60408636a4fba9a1970f8c41fb","observation_id":"9f1e7eaf-f58e-4296-b92e-115813994c40","resolution":{"observed_at":"2026-08-07T18:32:13.925908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.16782","last_updated":"2022-10-30T09:09:05Z","snapshot_observed_at":"2026-07-06T14:12:09.938885Z","submitted_at":"2022-10-30T09:09:05Z","title":"Unsupervised Learning of Structured Representations via Closed-Loop Transcription","version":1},"cited_work":{"arxiv_id":"2210.16782","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.16782","snapshot_observed_at":"2026-08-07T18:32:14.199157Z","title":"Unsupervised Learning of Structured Representations via Closed-Loop Transcription","venue":"cs.CV","work_id":"6ccbeb06-fa6a-4a53-ba2f-39338a87dede","year":2022},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.945079Z"},"links":{"cited_paper":"/paper/2210.16782","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:3b3535bf264bb61a207a4238e7caa996220219d92219b908f1b805dbf691921a","observation_id":"5732e5c8-45a7-4ddd-8102-971b91fbc679","resolution":{"observed_at":"2026-08-07T18:32:14.204278Z","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":"2026-08-07T18:32:13.991565Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.991565Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:d32b3553b750e411f1c008b0a98509c8ed3d56f6d82c488f9192c3593f22ae4c","observation_id":"a572794e-d121-4437-a2d0-f551e3515969","resolution":{"observed_at":"2026-08-07T18:32:13.991565Z","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":"2026-08-07T18:32:14.473461Z","title":"X., and Misra, I","venue":null,"work_id":"b3bee4d0-f655-4935-b041-544a8e9daab1","year":2023},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.995876Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:c5586e365da15baec59e001628446176198db9a580e230105b2725589719c322","observation_id":"16483a51-5916-4b69-a724-6ff79dadc007","resolution":{"observed_at":"2026-08-07T18:32:14.477483Z","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":"2026-08-07T18:32:14.408807Z","title":"Stronger fewer & superior: Harnessing vision foundation models for domain generalized semantic segmentation","venue":null,"work_id":"bb98d2e4-d51e-4d82-94e4-a3b735099c0c","year":2024},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:13.999271Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:b72c3c9bffa121cb7da234445d99fc318a1e82cb09fec87653583cc1d918d122","observation_id":"6617336d-73b9-4fe4-bfe5-d3b4fb642f98","resolution":{"observed_at":"2026-08-07T18:32:14.430066Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.002122Z","title":"X., and Lin, D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.002122Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:01c6a3b79d0bf380131856a7fde1d20f5fa1ccddac8cb4277a150a0e1802c71a","observation_id":"d3bb7217-a60f-4d20-a0f7-ab658cd1733e","resolution":{"observed_at":"2026-08-07T18:32:14.002122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.17810","last_updated":"2024-12-23T18:59:21Z","snapshot_observed_at":"2026-07-06T20:12:18.144353Z","submitted_at":"2024-12-23T18:59:21Z","title":"Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.17810","snapshot_observed_at":"2026-08-07T18:32:14.005816Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.005816Z"},"links":{"cited_paper":"/paper/2412.17810","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:cc903bf9331401e6653547808edda6bbd00f6b0f6b65ba2de4e1e2adb10d2269","observation_id":"a5fb8b49-1b7f-46d8-a961-46104d6d4f20","resolution":{"observed_at":"2026-08-07T18:32:14.005816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20299","last_updated":"2025-01-14T16:38:36Z","snapshot_observed_at":"2026-08-08T14:38:53.836623Z","submitted_at":"2024-05-30T17:46:23Z","title":"Scaling White-Box Transformers for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20299","snapshot_observed_at":"2026-08-07T18:32:14.055513Z","title":"Scaling white-box transformers for vision","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.055513Z"},"links":{"cited_paper":"/paper/2405.20299","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:b590b3053f2b9d9da29aba2c625e118041e228cb6a6eb762a9f75c323605632a","observation_id":"50144da2-00b4-494f-b1d8-38bb92327350","resolution":{"observed_at":"2026-08-07T18:32:14.055513Z","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":"2026-08-07T18:32:14.378619Z","title":"Learning efficient coding of natural images with maximum manifold capacity representations","venue":null,"work_id":"8a499745-c763-4bcf-b569-b373ab0b24cb","year":2023},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.059165Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:8d61f34b33347e071270c85ef42349bbf1a165dcb6e59c96d92270ac6f3137c9","observation_id":"1ead335a-078a-4d4a-b37e-0902692ebf91","resolution":{"observed_at":"2026-08-07T18:32:14.399737Z","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":"2026-08-07T18:32:14.341661Z","title":null,"venue":null,"work_id":"99eeda7c-f0da-4a9f-b874-8afe4765118a","year":2020},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.062953Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:0fb6db625155ad6f717e1901afc3aeb9a855193d410d48340737ea0eddf972c2","observation_id":"19d9dd64-225f-4ef9-9713-dd2887a51b3c","resolution":{"observed_at":"2026-08-07T18:32:14.344368Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-07T18:32:14.326630Z","title":"White-box transformers via sparse rate reduction","venue":null,"work_id":"d0ec9e35-5189-42aa-9c19-3f3031b65a26","year":2023},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.065666Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:c6b5b7cff2193f8daf503df9bacce4a884708675ccaed80a83e62a9b722cc8d4","observation_id":"1bff7803-aa13-4d8c-917e-1dd04e9248eb","resolution":{"observed_at":"2026-08-07T18:32:14.336900Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.068597Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.068597Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:6462f741b3287a43a66f68a485ffb11e19ac10f364b5b70499dc09f47c3efe27","observation_id":"62a4c3e9-ccc3-45c8-955f-0da282b10271","resolution":{"observed_at":"2026-08-07T18:32:14.068597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07832","last_updated":"2022-01-27T09:20:49Z","snapshot_observed_at":"2026-07-06T12:08:39.149450Z","submitted_at":"2021-11-15T15:18:05Z","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07832","snapshot_observed_at":"2026-08-07T18:32:14.117596Z","title":"ibot: Image bert pre-training with online tokenizer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.117596Z"},"links":{"cited_paper":"/paper/2111.07832","citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:e358fb93726241f2bd5efdc399b54ba15404060e6b2dcde61da3afe218e6dddc","observation_id":"9fc0ec8b-1079-4161-99cf-29250b3dc522","resolution":{"observed_at":"2026-08-07T18:32:14.117596Z","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":"2026-08-07T18:32:14.158944Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.158944Z"},"links":{"citing_paper":"/paper/2502.10385"},"observation_digest":"sha256:7deb1384fb016803375cc9b20b52f806570508d8faf0f07c577df6130b1aa1c5","observation_id":"1723178b-0008-437a-b671-68a35df59311","resolution":{"observed_at":"2026-08-07T18:32:14.158944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.10385","last_updated":"2025-02-14T18:58:04Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T07:41:54.364716Z","submitted_at":"2025-02-14T18:58:04Z","title":"Simplifying DINO via Coding Rate Regularization"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":2,"verified_fuzzy":12},"total_outbound_references":47},"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 47 of 47 outbound references and 6 inbound Pith citation observations for arXiv:2502.10385."}