{"as_of":"2026-08-09T10:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7ece927a3e154d12f6fe4b082b2d2013492cb1efa6e0732e89133de51be70781","coverage":[{"denominator":72,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":72,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T16:15:07.414107Z","state":"measured"},{"denominator":72,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":72,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2502.06268/citation-record","integrity":"/paper/2502.06268/integrity","json":"/paper/2502.06268/citation-record.json","paper":"/paper/2502.06268"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:15:07.093925Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.093925Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:0d8ed88842e11b5dc23b20c1a783a10bdc5f61b31b94609d8e5a846b66525654","observation_id":"d516fe53-433f-42f1-9386-2e893b3b7b03","resolution":{"observed_at":"2026-08-08T16:15:07.093925Z","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":"2026-08-08T16:15:23.413519Z","title":"Optimization algorithms on matrix manifolds","venue":null,"work_id":"0f31d910-0e6c-4b9a-ab38-994834cab97c","year":2009},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.099845Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:6cdc1b5edd8674c54a6a7dbed08b6a55bc7d6d5b6211cb71debc6500fc74873d","observation_id":"37413ba1-3c82-4b0d-a097-391378fb0cd4","resolution":{"observed_at":"2026-08-08T16:15:23.417655Z","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":"2026-08-08T16:15:23.400478Z","title":"Efficient full-matrix adaptive regularization","venue":null,"work_id":"a9cbf87a-0adc-4a59-8c2e-a7513fb658be","year":2019},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.104684Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:a6de0d4cc4a189eab00c55a784ea3931fbf6733ccdb5de746d448342ccb988f1","observation_id":"c4db66ff-bcb0-46a3-936f-d056de873a1b","resolution":{"observed_at":"2026-08-08T16:15:23.404868Z","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":"2026-08-08T16:15:23.387317Z","title":"Learning rate grafting: Transferability of optimizer tuning","venue":null,"work_id":"e1c49c7f-debc-46ca-8a17-b8d144507c3b","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.109232Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:fe56a9ace3b17eb254aca24eb77f78f9663c7daa40770f6a6cc339fe748c94e6","observation_id":"ca5bc144-a454-47bc-97b4-0d2edeba16e8","resolution":{"observed_at":"2026-08-08T16:15:23.391647Z","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":"2026-08-08T16:15:07.113641Z","title":"Natural gradient works efficiently in learning","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.113641Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:120db613bb8c8d2dcf09dbb2d8460c64b3b09f39b5042f6586e41ccfc78d3b3d","observation_id":"d84ea81d-27e2-4982-9214-dcaf111bb66d","resolution":{"observed_at":"2026-08-08T16:15:07.113641Z","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":"2026-08-08T16:15:23.363685Z","title":"Information geometry and its applications, volume 194","venue":null,"work_id":"f80f9c5b-8565-494b-87ff-0cb7ea7292c4","year":2016},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.118267Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:1c3dcf6732714fb1c9246dd70927c9dc0a6904191b00de109b8eaf3ee1a1f154","observation_id":"ea743440-49b2-421d-9cce-490e99bad129","resolution":{"observed_at":"2026-08-08T16:15:23.368155Z","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":"2002.09018","last_updated":"2021-03-05T06:29:48Z","snapshot_observed_at":"2026-08-03T21:55:15.856477Z","submitted_at":"2020-02-20T20:51:33Z","title":"Scalable Second Order Optimization for Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.09018","snapshot_observed_at":"2026-08-08T16:15:07.123382Z","title":"Scalable second order optimization for deep learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.123382Z"},"links":{"cited_paper":"/paper/2002.09018","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:e350f557367eb04c38651eeb6d41280ae74963dedb48e531832dd35ece82d21b","observation_id":"00e2c0a0-7921-4570-9563-a03e45f402ca","resolution":{"observed_at":"2026-08-08T16:15:07.123382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.20325","last_updated":"2024-12-06T14:09:22Z","snapshot_observed_at":"2026-08-03T03:18:47.425243Z","submitted_at":"2024-09-30T14:26:12Z","title":"Old Optimizer, New Norm: An Anthology","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.20325","snapshot_observed_at":"2026-08-08T16:15:07.128452Z","title":"and Newhouse, L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.128452Z"},"links":{"cited_paper":"/paper/2409.20325","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:0248d34aebd7c9f9d488eb4aa6bdb460d950c0f687315898e76cfb68c482b83a","observation_id":"b9c04a15-7dc6-4cc4-a748-cab14c7c14b2","resolution":{"observed_at":"2026-08-08T16:15:07.128452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01580","last_updated":"2022-05-03T15:54:44Z","snapshot_observed_at":"2026-08-05T01:37:29.867606Z","submitted_at":"2022-05-03T15:54:44Z","title":"Better plain ViT baselines for ImageNet-1k","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01580","snapshot_observed_at":"2026-08-08T16:15:07.133167Z","title":"Better plain vit baselines for imagenet-1k","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.133167Z"},"links":{"cited_paper":"/paper/2205.01580","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:9767806285df97d8fbbd131af77c022529dbab54b871c981c5f65ef9fb645664","observation_id":"9c6fa4ac-c613-48d0-b3c6-cad7b79de2a0","resolution":{"observed_at":"2026-08-08T16:15:07.133167Z","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":"2026-08-08T16:15:23.349829Z","title":"Manopt, a matlab toolbox for optimization on manifolds","venue":null,"work_id":"44e215d5-2b24-435d-831c-16d152443507","year":2014},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.138580Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:11149dd72eecca19511d5a5d4220845c35d098599c9e96f589ef2651a1da2c60","observation_id":"c41f817e-9a1c-4a8a-a5dd-24d5a9608ed2","resolution":{"observed_at":"2026-08-08T16:15:23.354545Z","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":"2026-08-08T16:15:23.337153Z","title":"S., Sra, S., and Tropp, J","venue":null,"work_id":"54408dae-acd8-4589-a45d-1286a89360a5","year":2008},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.142508Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:a5f7036ec70851e97c49af5a175542a674c43ae297d6b2bf22d74c9ce794a63a","observation_id":"49abba08-f9fe-463c-8d02-ae60413aecd2","resolution":{"observed_at":"2026-08-08T16:15:23.341312Z","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":"2026-08-08T16:15:23.323320Z","title":"Closing the generalization gap of adaptive gradient methods in training deep neural networks","venue":null,"work_id":"31972a4e-c9d5-4c54-bcc1-c17aef4cbf47","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.146568Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:08fa2eb92d915d2baf4ecbcb5ba5279463982dc2ed45c6881f3b15776cbeceea","observation_id":"bfb5ef71-6a46-4399-9b00-2dec1431e214","resolution":{"observed_at":"2026-08-08T16:15:23.328043Z","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":"2302.06675","last_updated":"2023-05-08T21:49:57Z","snapshot_observed_at":"2026-08-02T01:29:22.350700Z","submitted_at":"2023-02-13T20:27:30Z","title":"Symbolic Discovery of Optimization Algorithms","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.06675","snapshot_observed_at":"2026-08-08T16:15:07.150424Z","title":"Symbolic discovery of optimization algorithms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.150424Z"},"links":{"cited_paper":"/paper/2302.06675","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:558968e66b8d1eeff1e1c721ca76db37bfbcf96ada64d7d098a574a29436dc1b","observation_id":"7615c643-16ed-474f-ad7f-04698c8c0a9e","resolution":{"observed_at":"2026-08-08T16:15:07.150424Z","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":"2026-08-08T16:15:23.309241Z","title":"Z., Huang, J., Reich, S., and Stuart, A","venue":null,"work_id":"4a70c9d5-1902-4990-974c-acfd785ee8cb","year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.154897Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:672aaf6288b7e02e2edc3523d038b1532340af242157c0b5477e06e40e53b684","observation_id":"c0e3e54d-d70d-4a47-999c-20c17f630a06","resolution":{"observed_at":"2026-08-08T16:15:23.313727Z","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":"1910.05446","last_updated":"2020-06-16T00:58:12Z","snapshot_observed_at":"2026-08-06T08:58:02.295940Z","submitted_at":"2019-10-11T23:51:09Z","title":"On Empirical Comparisons of Optimizers for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.05446","snapshot_observed_at":"2026-08-08T16:15:07.158626Z","title":"J., Nado, Z., Lee, J., Maddison, C","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.158626Z"},"links":{"cited_paper":"/paper/1910.05446","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:916c30270e8ec22ed494a78ae69c0890637a3ff8b9a1b7f602fc1313c3eb823e","observation_id":"262b1a58-0d27-4111-bb45-9f3713acef7d","resolution":{"observed_at":"2026-08-08T16:15:07.158626Z","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":"2026-08-08T16:15:07.164008Z","title":"and Mehta, H","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.164008Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:78906664872f50d6d582989e5b0e8d9f8daef2db41568a756c67c09cd63db792","observation_id":"a44f0adb-6656-4b28-a66d-59000abda482","resolution":{"observed_at":"2026-08-08T16:15:07.164008Z","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":"2026-08-08T16:15:23.286347Z","title":"Adaptive subgradient methods for online learning and stochastic optimization","venue":null,"work_id":"ca421242-1b07-4d21-aee9-476a37071bfc","year":2011},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.168477Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:b95cf228c989a6402af27213afea2ee84f90afff2d66a7fcc0f8836d3489428b","observation_id":"94d03f1e-902c-4587-b65c-e32c24bc1a72","resolution":{"observed_at":"2026-08-08T16:15:23.291223Z","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":"2026-08-08T16:15:23.272135Z","title":"Proposal of distance-weighted exponential natural evolution strategies","venue":null,"work_id":"692e35d0-7f6c-44a9-9f88-9c3b8dea112a","year":2011},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.173157Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:60ffed83116d8aa16828c244eab39e95af2479e3defe080ef641ae30e9fd4361","observation_id":"0c9def5e-bff6-46b8-95d2-e17d763db378","resolution":{"observed_at":"2026-08-08T16:15:23.276055Z","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":"2026-08-08T16:15:23.258979Z","title":"Exponential natural evolution strategies","venue":null,"work_id":"6ff786a7-0208-41fd-be3b-c9664d067c4b","year":2010},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.177955Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:304ab2fbc841933f7c047a1221595d3c0297df6dba39cb88de70a64a7b411c58","observation_id":"0032d898-44e8-4844-ac23-fd404ffc5334","resolution":{"observed_at":"2026-08-08T16:15:23.263452Z","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":"2026-08-08T16:15:23.245873Z","title":"Natural gradient variational bayes without fisher matrix analytic calculation and its inversion","venue":null,"work_id":"be9811d2-773b-4100-8eca-67f68cd88e39","year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.182079Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:141d35e0b6cfb52cff109ca97a7cbf301da72c0fc1cc1d280907cdce3e230fbf","observation_id":"9f1f57e1-317d-4c0c-bf4b-460f4d558ec2","resolution":{"observed_at":"2026-08-08T16:15:23.250263Z","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":"2026-08-08T16:15:23.230660Z","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","venue":null,"work_id":"1bd35479-1d16-4972-9616-9474070ea31e","year":2018},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.186598Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:fc788762dbc3f2be1edfd4e7569b922b6d1c4748afc45ed339a65aa1ca2788de","observation_id":"e790a1eb-1253-405d-997c-947d814fdca2","resolution":{"observed_at":"2026-08-08T16:15:23.235652Z","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":"2026-08-08T16:15:23.216474Z","title":"K., and Gao, J","venue":null,"work_id":"0aaa182c-4dea-4627-8f4b-2034e67f6be4","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.191078Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:597a5228f4f4631f60693469d4cb18362a5c3ecec3e5b5fe77432051cdb8dc65","observation_id":"88f86604-c7b3-4cdf-8260-90fe4f59457c","resolution":{"observed_at":"2026-08-08T16:15:23.220656Z","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":"2026-08-08T16:15:23.203203Z","title":null,"venue":null,"work_id":"0718c4db-cef9-4e90-8cb2-7c209d2d4cf0","year":2003},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.195632Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:25ef54485921f4ff56ad25c6b9be0c5db0bb37c5b457b3b7c160a8ee99fe75ce","observation_id":"0325d712-d2ca-416d-9fd0-a2cca310a9f0","resolution":{"observed_at":"2026-08-08T16:15:23.207351Z","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":"2026-08-08T16:15:23.190011Z","title":"NanoGPT (124M) quality in 8.2 minutes","venue":null,"work_id":"3f436e4f-1b95-45ed-a5ba-02aef48948ea","year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.199643Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:67126dd545922d7c53f0dd26149dcd00c80c8cc72d9bc50b791a2ce68fe26dcb","observation_id":"51c93680-6c3b-423e-b9c2-a43edafc0d98","resolution":{"observed_at":"2026-08-08T16:15:23.194031Z","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":"2026-08-08T16:15:23.177742Z","title":null,"venue":null,"work_id":"7b59c6f2-f13a-4915-ac8c-af7fe0dee580","year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.203995Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:15ecff8b2354cf60196be3c06c5a8d55f6711bd61ec228b01e17238c4700a4a0","observation_id":"0420da59-06ca-480c-a840-2934fa01f6e0","resolution":{"observed_at":"2026-08-08T16:15:23.181442Z","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":"2026-08-08T16:15:23.164637Z","title":"E., Nielsen, D., Tangkaratt, V., Lin, W., Gal, Y., and Srivastava, A","venue":null,"work_id":"ca887265-7850-4f6c-b892-28c1a4291126","year":2018},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.208587Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:4804d9b80de94779d7dc4c8e86c90c70a75d2ab053b26c9ce8474be723dfe561","observation_id":"f9198895-69b4-44fa-8451-9c31d68ea10a","resolution":{"observed_at":"2026-08-08T16:15:23.168820Z","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":"2026-08-08T16:15:07.212989Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.212989Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:a88fc4d77d86bd58bdd8d7003a986efd4b81797af6b49846129ce18c409035fb","observation_id":"7d6f67c1-0f70-42e0-8834-5a282c5d637d","resolution":{"observed_at":"2026-08-08T16:15:07.212989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14173","last_updated":"2023-03-02T22:26:46Z","snapshot_observed_at":"2026-07-06T13:14:48.753329Z","submitted_at":"2022-05-27T18:01:45Z","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","version":3},"cited_work":{"arxiv_id":"2205.14173","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.14173","snapshot_observed_at":"2026-08-08T16:15:22.669280Z","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","venue":"cs.LG","work_id":"a06b5c16-77c2-4618-a350-c99e630c930f","year":2022},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.217128Z"},"links":{"cited_paper":"/paper/2205.14173","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:641a755636adc2f2ffe001bec7d96d6624e23f6e8886ee0c2ef5833132f83a4f","observation_id":"4384aed9-b1f8-4916-ad05-f0096188c627","resolution":{"observed_at":"2026-08-08T16:15:22.674597Z","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":"1712.03298","last_updated":"2017-12-08T22:26:58Z","snapshot_observed_at":"2026-07-06T06:13:32.542717Z","submitted_at":"2017-12-08T22:26:58Z","title":"Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.03298","snapshot_observed_at":"2026-08-08T16:15:07.222585Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.222585Z"},"links":{"cited_paper":"/paper/1712.03298","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:4cdd4bdb96f306ed6e6235c7d2c40ec66012b229a76fd82446a969f078766ba9","observation_id":"cbfbca9e-dfc5-4ef3-a529-b9b8bbd460f7","resolution":{"observed_at":"2026-08-08T16:15:07.222585Z","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":"2026-08-08T16:15:07.228099Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.228099Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:4654e94d0056c8e67edb3a2ea9595f83935f155d4d39b8cda5e28efec3ad1655","observation_id":"0fe15b20-d4c3-491c-b669-5e12e9c1e2c5","resolution":{"observed_at":"2026-08-08T16:15:07.228099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.01113","last_updated":"2020-02-04T04:01:51Z","snapshot_observed_at":"2026-07-06T08:54:43.689129Z","submitted_at":"2020-02-04T04:01:51Z","title":"Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.01113","snapshot_observed_at":"2026-08-08T16:15:07.232002Z","title":"Efficient riemannian optimization on the stiefel manifold via the cayley transform","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.232002Z"},"links":{"cited_paper":"/paper/2002.01113","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:828bd857cd99719b63d86c6a5ffed654f6d900ebbf37c0bbd818eeca9b7e8a46","observation_id":"9701ce43-72f9-4f7c-8846-a2c03c91fe3c","resolution":{"observed_at":"2026-08-08T16:15:07.232002Z","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":"2026-08-08T16:15:07.236153Z","title":"Preconditioned stochastic gradient descent","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.236153Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:bcc9b24bf5702f11b067ebf4c3d82703dd950200b70b8625029cb914df7a5d0d","observation_id":"d6f07db2-312e-47bd-a7d3-01dee2f00a43","resolution":{"observed_at":"2026-08-08T16:15:07.236153Z","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":"2026-08-08T16:15:23.125221Z","title":"E., and Schmidt, M","venue":null,"work_id":"ffb66bc8-1aaf-49a3-9a20-acb1357201dc","year":2019},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.241043Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:924b7a0ae81c4a0167f5c731dc153ea3cdb2f2b5cb9903fc38c1e18c99770855","observation_id":"d85c4705-1f8e-47c2-96a6-e4211c2f6226","resolution":{"observed_at":"2026-08-08T16:15:23.129381Z","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":"2026-08-08T16:15:23.112788Z","title":null,"venue":null,"work_id":"31f7cdec-b2c3-471e-be2d-f7d29de676af","year":2020},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.246447Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:a8135e437898b52c9328486cc53a898cb7fdc784e3bf801566bf1051ff8452d0","observation_id":"221cef9f-1fe2-4649-8cfb-ad280f9f81bd","resolution":{"observed_at":"2026-08-08T16:15:23.116766Z","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":"2026-08-08T16:15:23.100338Z","title":"M., and Schmidt, M","venue":null,"work_id":"1198ddb5-a785-44e3-b43e-0d2a134ba1b5","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.251231Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:76b9846f77e24961f147bdbe3e9136faf07e93451a39b51b700dceb97a9f4333","observation_id":"df6dda30-82db-4525-8555-8b6a24361d51","resolution":{"observed_at":"2026-08-08T16:15:23.104451Z","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":"2026-08-08T16:15:23.088493Z","title":"E., and Schmidt, M","venue":null,"work_id":"e5dc3d33-21c1-4b2f-af93-64296169d1a5","year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.255860Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:5b173b67444194980616047bbb04b38ea5ee0ace9d2e143b8bd2677f1a4d1495","observation_id":"3fcaa1b1-fb2c-484d-bf17-2aaaa7df3e02","resolution":{"observed_at":"2026-08-08T16:15:23.092126Z","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":"2026-08-08T16:15:23.076543Z","title":"E., and Makhzani, A","venue":null,"work_id":"7e854fef-a4b1-42f3-bca1-828f65a0f361","year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.259785Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:5c302bcdd24a088b7a819c0ec9b517c5379c4c8845fb6a6746ac000c89848b3e","observation_id":"dcb09d83-3130-494d-8a13-281bf898245e","resolution":{"observed_at":"2026-08-08T16:15:23.080428Z","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":"2305.14342","last_updated":"2024-03-05T17:07:16Z","snapshot_observed_at":"2026-08-08T09:25:28.224090Z","submitted_at":"2023-05-23T17:59:21Z","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14342","snapshot_observed_at":"2026-08-08T16:15:07.263627Z","title":"Sophia: A scalable stochastic second-order optimizer for language model pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.263627Z"},"links":{"cited_paper":"/paper/2305.14342","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:8bfb6e9eb4b34d4016c2f705afd3b2f2b8425e78e96574a74964ce28d5533907","observation_id":"d1ff73d5-fed1-4f72-bc32-107140871d21","resolution":{"observed_at":"2026-08-08T16:15:07.263627Z","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":"2026-08-08T16:15:23.063458Z","title":"M., Paull, L., Xiong, L., Song, L., and Weller, A","venue":null,"work_id":"8510b206-66f2-4b61-af98-14dbb6a8984c","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.267941Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:cdb3e34c21be49a80030ae2e81c18e35941c07672e73fda747567acbe51bf94a","observation_id":"aa3e3da1-5d1d-49f0-a52a-472240fdd597","resolution":{"observed_at":"2026-08-08T16:15:23.067863Z","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":"2026-08-08T16:15:23.050648Z","title":"Optimizing millions of hyperparameters by implicit differentiation","venue":null,"work_id":"97a813c1-76a0-48be-aaf2-cfa9ea5d819b","year":2020},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.271522Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:aa338ae0a6b9c4ce6c66815dd002fe4a36ed5c801ef61f4b7316a0417155bcce","observation_id":"71b17889-1f39-4b49-91d1-1374354c56a8","resolution":{"observed_at":"2026-08-08T16:15:23.054950Z","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":"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":"2026-08-08T16:15:07.275513Z","title":"and Hutter, F","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.275513Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:2ae90b9ecf404354688afa8b45b0b0cd839e41f160c931e07d3ec611e446798c","observation_id":"40b8ec48-0b30-4e23-92ae-559af5f0822d","resolution":{"observed_at":"2026-08-08T16:15:07.275513Z","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":"2026-08-08T16:15:23.037408Z","title":"Lecture Notes: Mathematical Modelling of DNA","venue":null,"work_id":"d1c1808a-e2f1-4f4e-bec2-f6a18a1671b0","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.279885Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:1cf1c82ff88072d967ca9b0d3b4ddcb28b61f83c2d58fa0749a4e2f320e9f58b","observation_id":"b3a7781b-536f-4795-bcc0-f136e6b7a69f","resolution":{"observed_at":"2026-08-08T16:15:23.041692Z","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":"2026-08-08T16:15:23.020809Z","title":null,"venue":null,"work_id":"79b4491c-3888-43ed-9ef2-47d61d761a02","year":1963},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.284116Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:b1e23061ab922e1fb35ee3e11045bf18952a5f307b2a6eaea900b9852797803b","observation_id":"48c1f793-94a8-4f7b-bbab-9770694628fb","resolution":{"observed_at":"2026-08-08T16:15:23.028316Z","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":"2026-08-08T16:15:23.009127Z","title":"and Grosse, R","venue":null,"work_id":"cda7bbe4-17fa-4511-94cf-a71a501d0374","year":2015},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.288236Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:0a8f24cd4ccdfe5453b572790983d74b4df2e75a7975fdba4d6a45fd8785bbd9","observation_id":"ae16ffee-619a-49b2-9cd7-e227a5a31cc6","resolution":{"observed_at":"2026-08-08T16:15:23.012780Z","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":"2026-08-08T16:15:22.996807Z","title":"Mixed precision training","venue":null,"work_id":"46a508b2-0f75-4b0b-9423-60c35aa5c21a","year":2018},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.292353Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:66425be132c5077d589a055ec55d7c8e8fe18b7153e8154c0027c265e6ea2038","observation_id":"f17a77a8-3322-4558-8a8c-fddbf8951010","resolution":{"observed_at":"2026-08-08T16:15:23.001186Z","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":"2026-08-08T16:15:22.983790Z","title":"and Archambeau, C","venue":null,"work_id":"3071dd80-d738-4ffb-882c-4d47c372955f","year":2009},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.296972Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:b8cbc1bde0286f0beb935a66420527eb6c51260cb9c02a3ddcdbe7b8343dd99b","observation_id":"58f6880a-ca02-4bd0-bce6-3ff394159dfa","resolution":{"observed_at":"2026-08-08T16:15:22.987915Z","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":"2026-08-08T16:15:22.971127Z","title":null,"venue":null,"work_id":"04673633-652f-4187-b5a3-e1245074adfa","year":2019},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.302124Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:e96e936959339d6a161c326bc2d1a39ec04c9f673b801ba7a15165b0de4ac6fd","observation_id":"f8ae8b2c-a2cb-4e82-867c-0c4d73fb565c","resolution":{"observed_at":"2026-08-08T16:15:22.975280Z","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":"2026-08-08T16:15:22.958593Z","title":"B., Pedersen, M","venue":null,"work_id":"cacfa0bd-8828-49a1-9fe7-b8bff949e583","year":2008},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.306084Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:3e192587d4d0ea45fc82180b12295a48cfcf81701f098fd1e48c7b441a976bff","observation_id":"57ca8511-4dd2-41aa-a0ea-253a2fb68655","resolution":{"observed_at":"2026-08-08T16:15:22.962144Z","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":"2026-08-08T16:15:22.946595Z","title":"Controlling text-to-image diffusion by orthogonal finetuning","venue":null,"work_id":"88cd681d-4a26-4a63-a38e-032e8754c7c9","year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.309853Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:3bd6c4e003b92c974ae921978f7f281f1fa69e09f0f42134071cd61f84d63cb3","observation_id":"c1a29769-998a-4b1b-98f4-5188fa456bef","resolution":{"observed_at":"2026-08-08T16:15:22.950305Z","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":"2026-08-08T16:15:22.934518Z","title":"and Goldfarb, D","venue":null,"work_id":"121b7b58-1a55-41fd-8fe7-86d0477fac14","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.314993Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:1041e86664b9527205cafda43fbc6bfaac1ab9ab0dfb2ac75e88969e1541920b","observation_id":"4910e34a-e02b-4c1e-9156-c94d82b65170","resolution":{"observed_at":"2026-08-08T16:15:22.938132Z","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":"2026-08-08T16:15:22.920078Z","title":"Topmoumoute online natural gradient algorithm","venue":null,"work_id":"bb7e6464-ec2d-41f9-8717-12ef0f9571a9","year":2007},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.319971Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:5a7353061f7e7ce6acb70dec89e8b5c8d153c08a660c571bcd1416fbc8d1580d","observation_id":"d4d9bc23-e920-4c46-a91a-4351ef49f056","resolution":{"observed_at":"2026-08-08T16:15:22.924444Z","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":"2026-08-08T16:15:22.906631Z","title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","venue":null,"work_id":"3605d1ba-00b5-4abb-bff4-1c47aaa02b99","year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.324628Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:a7c9644682a12807d6ca17a4f1ff6609c1a66f3d7b5ca8a090c78b88da3e173e","observation_id":"0bed36cc-740f-4e70-a97f-9e59a8bb8767","resolution":{"observed_at":"2026-08-08T16:15:22.911091Z","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":"2026-08-08T16:15:22.891934Z","title":"Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models","venue":null,"work_id":"eaba59c6-8580-4c6a-915e-f055e006df98","year":2018},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.328481Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:bb79e0fd1ce334e061a9181484e238c0d2b418ad7532c6d509ddbd6249f8883f","observation_id":"25ae04b8-a9d5-4a3b-8dc3-e035189877dd","resolution":{"observed_at":"2026-08-08T16:15:22.896822Z","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":"2402.17641","last_updated":"2024-06-06T04:31:43Z","snapshot_observed_at":"2026-07-06T17:36:20.138864Z","submitted_at":"2024-02-27T16:11:05Z","title":"Variational Learning is Effective for Large Deep Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17641","snapshot_observed_at":"2026-08-08T16:15:07.332674Z","title":"M., Bazan, C., Yokota, R., Gurevych, I., Cremers, D., Khan, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.332674Z"},"links":{"cited_paper":"/paper/2402.17641","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:712d53e805060b8fc92d6af36c35a3e3ee825fbdba47b29322859e5ea69f2432","observation_id":"94265aaf-654f-43e5-9518-debed1819096","resolution":{"observed_at":"2026-08-08T16:15:07.332674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.06497","last_updated":"2023-09-12T18:11:10Z","snapshot_observed_at":"2026-08-05T09:31:11.684666Z","submitted_at":"2023-09-12T18:11:10Z","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.06497","snapshot_observed_at":"2026-08-08T16:15:07.336710Z","title":"M., Lee, T.-H., Iwasaki, S., Gallego-Posada, J., Li, Z., Rangadurai, K., Mudigere, D., and Rabbat, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.336710Z"},"links":{"cited_paper":"/paper/2309.06497","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:19dfdb71e73c68a5564e469ae7a8ba29176a7217538493833fed601b10099ce1","observation_id":"a5ee00b1-8cf5-4761-bc55-477f7dd8b99e","resolution":{"observed_at":"2026-08-08T16:15:07.336710Z","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":"2026-08-08T16:15:22.878602Z","title":null,"venue":null,"work_id":"64e3772e-f7a1-4c33-9eca-63680751851d","year":2011},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.341785Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:a81a7cadff07cd92ddf647cdcec77dac64fecc7e021d36c0c4f46694932720cd","observation_id":"508c6753-bc7d-4df4-b82f-bf397a2db88c","resolution":{"observed_at":"2026-08-08T16:15:22.883048Z","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":{"arxiv_id":"2109.00375","last_updated":"2025-02-04T09:06:46Z","snapshot_observed_at":"2026-07-06T11:43:24.789080Z","submitted_at":"2021-09-01T13:27:12Z","title":"Analytic natural gradient updates for Cholesky factor in Gaussian variational approximation","version":10},"cited_work":{"arxiv_id":"2109.00375","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.00375","snapshot_observed_at":"2026-08-08T16:15:22.566946Z","title":"Analytic natural gradient updates for Cholesky factor in Gaussian variational approximation","venue":"stat.CO","work_id":"a3b922f8-52fc-428d-a03a-716f20bf5d58","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.345804Z"},"links":{"cited_paper":"/paper/2109.00375","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:b71354162037f0999cb100e6bb31cd821f57e34c230a0f865242d9fe0bc0c2fd","observation_id":"8b52138f-430a-4a20-8762-1113f292dde4","resolution":{"observed_at":"2026-08-08T16:15:22.573647Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:15:22.864844Z","title":"and Hinton, G","venue":null,"work_id":"764e6c21-6a30-42bf-a231-55d319ae10b7","year":2012},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.350467Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:370b3475ce5e7be9c7cf429e3cfc85d1fa779399ffcd19a78d8cf04fce46ea9a","observation_id":"83b96c36-73e7-493c-9ee5-199a5e93837b","resolution":{"observed_at":"2026-08-08T16:15:22.868880Z","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":"2026-08-08T16:15:22.851949Z","title":"H., and Nguyen, D","venue":null,"work_id":"370c2596-e34c-44ed-b735-6d949ca0dc56","year":2021},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.354539Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:6013476d07f1871d171e043f7ed15d04c218bd5a546997444bcd8c9c676682c4","observation_id":"bf389409-905e-4f2b-a8f6-243ac71fec16","resolution":{"observed_at":"2026-08-08T16:15:22.855781Z","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":"2026-08-08T16:15:22.837584Z","title":null,"venue":null,"work_id":"d1989704-1ad3-4c44-966b-5658251671fd","year":1993},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.358604Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:ab027dae46fae45d3f17b3e59d69d88254ba5e169a3db30ff736e3410a8d6078","observation_id":"9ce8ecdc-9a00-49d0-9a2d-df1e63d66bc5","resolution":{"observed_at":"2026-08-08T16:15:22.842598Z","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":"2026-08-08T16:15:22.823012Z","title":"Invariance properties of the natural gradient in overparametrised systems","venue":null,"work_id":"0a90e660-3435-4186-9814-9a89462ba299","year":2023},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.362478Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:5097734bc18c723e758f14e40343169a15cc6b69e0de403b53b848306754b3a6","observation_id":"fbacb41b-212c-40d6-99bf-708bc6ee40dc","resolution":{"observed_at":"2026-08-08T16:15:22.827737Z","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":"2409.11321","last_updated":"2025-01-31T18:52:42Z","snapshot_observed_at":"2026-07-06T19:16:51.512681Z","submitted_at":"2024-09-17T16:18:05Z","title":"SOAP: Improving and Stabilizing Shampoo using Adam","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11321","snapshot_observed_at":"2026-08-08T16:15:07.366670Z","title":"Soap: Improving and stabilizing shampoo using adam","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.366670Z"},"links":{"cited_paper":"/paper/2409.11321","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:b223a58933587f24ddfc439350cbe3b65c46313cce6e3974edb59aa4306399b6","observation_id":"44adf111-4888-4f8c-8bff-40c19ff7da16","resolution":{"observed_at":"2026-08-08T16:15:07.366670Z","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":"2026-08-08T16:15:22.808991Z","title":"Natural evolution strategies","venue":null,"work_id":"d777b1a2-5eca-4d77-b007-0ccd7c9b2ff6","year":2008},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.370902Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:6e85aabe323c2ec7e0f1e2aa07607aae5e0d912142b14d071ed0857ccb94d7f4","observation_id":"5d049ff4-1172-42c2-9bef-ab7c8f335e17","resolution":{"observed_at":"2026-08-08T16:15:22.813559Z","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":"2026-08-08T16:15:07.374922Z","title":null,"venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.374922Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:ac1689f7aac3ca9b696c7fb9e8d32e2de43e44d4d4640125f04330725105d7e6","observation_id":"c2691899-b9fb-41bb-bee3-a8b33a115cd4","resolution":{"observed_at":"2026-08-08T16:15:07.374922Z","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":"2026-08-08T16:15:07.379246Z","title":"J., Chun, S., Choe, J., and Yoo, Y","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.379246Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:721bc756f79f3ed38858c078ea4b42ca9865f0a3fca6233e1ad025db1da5e1a2","observation_id":"bf0e4f03-f66b-4ce9-957c-5496a186889b","resolution":{"observed_at":"2026-08-08T16:15:07.379246Z","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":"2026-08-08T16:15:22.778038Z","title":"Noisy natural gradient as variational inference","venue":null,"work_id":"e349df03-ee94-4bb1-83a5-a0bb8949a3cf","year":2018},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.383551Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:1c859c95fdfb972c346f21e099f8f22e4a5586876d99f59cad557a4a6302bda0","observation_id":"aaa2e5af-25a1-43c2-acb9-f5c52582ef4d","resolution":{"observed_at":"2026-08-08T16:15:22.782559Z","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":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-08T16:15:07.387966Z","title":"mixup: Beyond empirical risk minimization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.387966Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:5900346ffcb0d34f6d8c82d878aa6c0b6a7c8eb016d741e46cd549e5ec100882","observation_id":"1a6bc752-0ecb-4ebb-8765-4616954ef9ef","resolution":{"observed_at":"2026-08-08T16:15:07.387966Z","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":"2026-08-08T16:15:07.393216Z","title":"P., Veit, A., Kim, S., Reddi, S., Kumar, S., and Sra, S","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.393216Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:79426baae51b14fcb6561d9c3bd1f0d9382539dd0ee2490c35c0047433612f91","observation_id":"1b8b188b-e946-4551-9ced-bbb0eb046cee","resolution":{"observed_at":"2026-08-08T16:15:07.393216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16788","last_updated":"2024-10-21T08:27:23Z","snapshot_observed_at":"2026-07-06T17:35:41.168780Z","submitted_at":"2024-02-26T18:01:41Z","title":"Why Transformers Need Adam: A Hessian Perspective","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16788","snapshot_observed_at":"2026-08-08T16:15:07.397282Z","title":"Why transformers need adam: A hessian perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.397282Z"},"links":{"cited_paper":"/paper/2402.16788","citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:072a42183dec128b3a151a9f35310e6af909efe17b4e99cce4d99144386e7cca","observation_id":"f01a9f2a-5a2d-4ef5-a118-3ce50a59f375","resolution":{"observed_at":"2026-08-08T16:15:07.397282Z","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":"2026-08-08T16:15:07.402681Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.402681Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:b99ae7ef3631d5a8cfd302e733b84c356844e588e776a251c902416b7e4b19b6","observation_id":"d5997082-c6bd-435a-b92c-8f8bae59f180","resolution":{"observed_at":"2026-08-08T16:15:07.402681Z","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":"2026-08-08T16:15:07.409213Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.409213Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:4145fd1ea18438251128b51dba23628feb7e013e3fd0630c99656ee1345f81bf","observation_id":"6c5288ed-3836-4da0-8208-9d84eabb415d","resolution":{"observed_at":"2026-08-08T16:15:07.409213Z","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":"2026-08-08T16:15:07.414107Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","version":3},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-08T16:15:07.414107Z"},"links":{"citing_paper":"/paper/2502.06268"},"observation_digest":"sha256:d30a562d0a1b13b93e7a8db3deec3b70147ae339af2cc383f82096221b6acb8f","observation_id":"33f15f5c-6b30-48d6-8348-f68aa9ea2d46","resolution":{"observed_at":"2026-08-08T16:15:07.414107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.06268","last_updated":"2025-03-28T15:49:41Z","latest_version":3,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-09T07:29:38.826457Z","submitted_at":"2025-02-10T09:07:04Z","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training"},"reference_resolution":{"displayed":72,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":2,"verified_fuzzy":37},"total_outbound_references":72},"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 72 of 72 outbound references and 0 inbound Pith citation observations for arXiv:2502.06268."}