{"as_of":"2026-08-10T21:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e8785dc8cf9351f2201f81b31f3232bc3583eec946c0799cdfa31371c5af6827","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T14:43:35.407031Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.24467/citation-record","integrity":"/paper/2509.24467/integrity","json":"/paper/2509.24467/citation-record.json","paper":"/paper/2509.24467"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T14:43:34.794741Z","title":"Julien Mairal","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:34.794741Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:eaa51d845fa85c0c6cb74806bdc1661ad5ba073dbc19aa6abec59fc7b36f1e25","observation_id":"b785f2c4-0d07-4326-aab1-9f924094c720","resolution":{"observed_at":"2026-08-04T14:43:34.794741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.02237","last_updated":"2020-03-05T18:46:30Z","snapshot_observed_at":"2026-08-05T13:28:56.222559Z","submitted_at":"2020-03-04T18:25:41Z","title":"Neural Kernels Without Tangents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.02237","snapshot_observed_at":"2026-08-04T14:43:35.112926Z","title":"14 Under review as a conference paper at ICLR 2026 Ravid Shwartz-Ziv and Amitai Armon","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:35.112926Z"},"links":{"cited_paper":"/paper/2003.02237","citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:3f17f976fc40b553df4c310a1261dd3e1dfdcdce1f82c7cb9989be4f7a254e02","observation_id":"134ed84e-81f1-497b-b8db-a4b31a221ed0","resolution":{"observed_at":"2026-08-04T14:43:35.112926Z","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":"2026-08-04T14:43:35.283400Z","title":"Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, and St´ephane Deny","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:35.283400Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:d635661567c83c6ea446b1d1492aa5dbbeff454a60bd6bf57ebae18bf3689155","observation_id":"7ee8cab8-3660-445c-84fb-c62ec37e2ed6","resolution":{"observed_at":"2026-08-04T14:43:35.283400Z","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":"2026-08-04T14:43:35.407031Z","title":"Loss Function Hyper-parametersFor the simple contrastive loss, spectral contrastive loss, BT, and KPCA, the regularization coefficientλis sampled from the range[10 −5,100]","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:35.407031Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:739984cd8a3ec9fb7aa4b0fead47b8da7eaddd0949de28245b3c2935cddc1e8c","observation_id":"134e9112-34c0-47ea-8b85-8224a4ac525e","resolution":{"observed_at":"2026-08-04T14:43:35.407031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08608","last_updated":"2017-03-02T19:32:10Z","snapshot_observed_at":"2026-08-07T08:20:39.814613Z","submitted_at":"2017-02-28T02:19:20Z","title":"Towards A Rigorous Science of Interpretable Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.08608","snapshot_observed_at":"2026-08-04T14:43:33.646768Z","title":"Mathilde Caron, Hugo Touvron, Ishan Misra, Herv ´e J ´egou, Julien Mairal, Piotr Bojanowski, and Armand Joulin","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":1411,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:33.646768Z"},"links":{"cited_paper":"/paper/1702.08608","citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:13783e20a447986efbee74064489bfd0668a6c65f5d5a16023aa7a7b907be936","observation_id":"65e92e69-8293-40eb-a0f2-e26e2fa70d15","resolution":{"observed_at":"2026-08-04T14:43:33.646768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-04T14:43:34.491636Z","title":"Arthur Jacot, Franck Gabriel, and Clement Hongler","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":1989,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:34.491636Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:c18a1a4ffd555e5727833593c7ca2f6c17445dfeafd3c8501fc9b28cea0fb3ef","observation_id":"343d20f6-0a31-495b-bf4f-08c9df48c859","resolution":{"observed_at":"2026-08-04T14:43:34.491636Z","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":"2026-08-04T14:43:34.044749Z","title":"Elias Frantar, Eldar Kurtic, and Dan Alistarh","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:34.044749Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:d0fe24b0cbb4a2e1d2173158ae0c7a5a35f10143d8060965e1c7ce8b2e374f29","observation_id":"6068096f-5dd1-406d-98f2-2af3b42d94cb","resolution":{"observed_at":"2026-08-04T14:43:34.044749Z","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":"2026-08-04T14:43:34.372399Z","title":"URLhttps://doi.org/10.1137/090771806","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:34.372399Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:e2f257c2690a2701fa48c1839290b09cf33b761a69e6cbb00371413f926f7b03","observation_id":"eb1d89f7-63c5-47d0-ad0b-3961a1eb7582","resolution":{"observed_at":"2026-08-04T14:43:34.372399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02803","last_updated":"2019-12-05T18:51:57Z","snapshot_observed_at":"2026-08-08T12:08:12.089821Z","submitted_at":"2019-12-05T18:51:57Z","title":"Neural Tangents: Fast and Easy Infinite Neural Networks in Python","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02803","snapshot_observed_at":"2026-08-04T14:43:35.015653Z","title":"Neil Mallinar, James B","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:35.015653Z"},"links":{"cited_paper":"/paper/1912.02803","citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:36b317d8629f49bdf0edccf5f115963a9f61e4f22e8fe5c74d30ffbb85746484","observation_id":"317ac1fa-66e5-461c-80eb-5899dda8a0e5","resolution":{"observed_at":"2026-08-04T14:43:35.015653Z","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":"2026-08-04T14:43:34.904739Z","title":"Julien Mairal, Piotr Koniusz, Zaid Harchaoui, and Cordelia Schmid","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:34.904739Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:7308b80c00b194c0dd440296e295e7da79426420b36fe3dcd843cbfb98f183d7","observation_id":"c595462a-1b9b-415e-8c28-b73bf79093a8","resolution":{"observed_at":"2026-08-04T14:43:34.904739Z","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":"2026-08-04T14:43:34.173799Z","title":"Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, and Andrea Montanari","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:34.173799Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:5aa19c5ddfa345c2f9a80143a1c52786e4c2c1d5d4d07ce137fb134630e27df2","observation_id":"56028b67-6b10-4b86-870f-d5697ce2bf64","resolution":{"observed_at":"2026-08-04T14:43:34.173799Z","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":"2026-08-04T14:43:33.527837Z","title":"David Arthur and Sergei Vassilvitskii","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:33.527837Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:9b478dac9bb38dd4819c4cb62b8fe5fee7640c9b79323f1594b004a6f0a476a1","observation_id":"1991a402-0b6b-4b45-9474-b445cd7f02ac","resolution":{"observed_at":"2026-08-04T14:43:33.527837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12359","last_updated":"2019-06-18T08:58:18Z","snapshot_observed_at":"2026-07-06T07:18:01.039966Z","submitted_at":"2018-11-29T18:10:40Z","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.12359","snapshot_observed_at":"2026-08-04T14:43:34.687216Z","title":"Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar R ¨atsch, Sylvain Gelly, Bernhard Sch¨olkopf, and Olivier Bachem","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:34.687216Z"},"links":{"cited_paper":"/paper/1811.12359","citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:a33020323d5b165d1b79642d8e37cb84ec2d7f33c89ae487149af4441b056766","observation_id":"fd28fe45-4b02-4ee8-9d4d-ff6d0410d78d","resolution":{"observed_at":"2026-08-04T14:43:34.687216Z","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":"2026-08-04T14:43:33.814744Z","title":"Pascal Mattia Esser, Maximilian Fleissner, and Debarghya Ghoshdastidar","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:33.814744Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:7ae21a4f821cf279dd49cce990b0eef5f3e75991309dede4a2ae55c351383e22","observation_id":"8bc046b0-63f7-4b93-be77-c0ea5ee41db4","resolution":{"observed_at":"2026-08-04T14:43:33.814744Z","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":"2026-08-04T14:43:35.206630Z","title":"Alexander Wei, Wei Hu, and Jacob Steinhardt","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","version":4},"reference_index":2195,"source":"pdf_text","source_observed_at":"2026-08-04T14:43:35.206630Z"},"links":{"citing_paper":"/paper/2509.24467"},"observation_digest":"sha256:afacaf764f92b34d2753c50914630c57bb3ba55f1ea2cb54a6c4fda58586cb4e","observation_id":"616a8a4b-2e3f-441d-a678-102e6e2980a6","resolution":{"observed_at":"2026-08-04T14:43:35.206630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.24467","last_updated":"2026-06-08T09:26:17Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T22:57:00.532523Z","submitted_at":"2025-09-29T08:45:40Z","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":15},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2509.24467."}