{"as_of":"2026-08-13T11:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:79fbc9b1e8ff4378aa9e7eb5939469850aadaa979bb9ae69d3915fbd868ab2b6","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T12:47:08.114886Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.16975/citation-record","integrity":"/paper/2411.16975/integrity","json":"/paper/2411.16975/citation-record.json","paper":"/paper/2411.16975"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1126/science.360.6388.478","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T12:47:08.151642Z","title":"Has artificial intelligence become alchemy?","venue":null,"work_id":"08358d73-2bed-4405-aedc-4380432af242","year":2018},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.959531Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:ec584c26ae2218ea061eb5afd2a0c95879d35ee371172a3abeae450f7fb0a636","observation_id":"0f28f743-6ec7-4b4c-bbef-5ee777e7a335","resolution":{"observed_at":"2026-08-12T12:47:08.157425Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.05689","last_updated":"2020-03-12T10:12:22Z","snapshot_observed_at":"2026-08-11T04:06:19.914166Z","submitted_at":"2020-03-12T10:12:22Z","title":"Hyper-Parameter Optimization: A Review of Algorithms and Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.05689","snapshot_observed_at":"2026-08-12T12:47:07.964331Z","title":"Hyper-parameter optimization: A review of algorithms and applications,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.964331Z"},"links":{"cited_paper":"/paper/2003.05689","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:24fb8d6776cf98f13d8053fa9527ab9d30479b8a5b8fd5b4109f5cdbf688f864","observation_id":"407bf9a1-9a69-41ab-be57-188ed5d30ef5","resolution":{"observed_at":"2026-08-12T12:47:07.964331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1206.5533","last_updated":"2012-09-16T17:49:12Z","snapshot_observed_at":"2026-08-03T14:15:44.080315Z","submitted_at":"2012-06-24T19:17:35Z","title":"Practical recommendations for gradient-based training of deep architectures","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.5533","snapshot_observed_at":"2026-08-12T12:47:07.968794Z","title":"Practical recommendations for gradient-based training of deep architectures,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.968794Z"},"links":{"cited_paper":"/paper/1206.5533","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:317008e597f9b8ab2a0645428ae64fc7b0ec5049a77a1a1622eedd24e4956e22","observation_id":"4c08a42a-9656-4d2d-b1d2-144de66ce079","resolution":{"observed_at":"2026-08-12T12:47:07.968794Z","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":"2026-08-12T12:47:07.973223Z","title":"Some methods of speeding up the convergence of iteration methods,","venue":null,"work_id":null,"year":1964},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.973223Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:6473df4bc76e6c29ffb619e5c2becfb8b9e710a2c66ce7c49d372d508b00add8","observation_id":"8bd6898d-0fe4-4465-ad92-4069beb436c8","resolution":{"observed_at":"2026-08-12T12:47:07.973223Z","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":"2026-08-12T12:47:08.724024Z","title":"Increased rates of convergence through learning rate adaptation,","venue":null,"work_id":"8c0dd72b-becf-4b94-93ec-6e9d939b0efe","year":1988},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.977703Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:86026bfaae1b80c1b39d6e36d784b5d125d290ea0d0d0253a7591356e15d1d4f","observation_id":"febac629-e920-4cfe-8dad-15c69339c91d","resolution":{"observed_at":"2026-08-12T12:47:08.728992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.711622Z","title":"Cyclical learning rates for training neural networks,","venue":null,"work_id":"074068b8-b038-4afe-9b0c-a32fc4af7ff0","year":null},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.981839Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:2a1f7b94b275babbc06fbc6853c9902103888a7080f66d25a3bcc7f8301b547e","observation_id":"81f67b16-8aed-4ad9-8368-af830a9ef030","resolution":{"observed_at":"2026-08-12T12:47:08.715690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:07.990019Z","title":"Adam: A method for stochastic optimization,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.990019Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:581bc5a4afd55ff91328e020dd129cac8cd528f89e281862d003a7c25132e434","observation_id":"c4c1ae0b-4cee-4bb5-83ac-2e2e806a8951","resolution":{"observed_at":"2026-08-12T12:47:07.990019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.09820","last_updated":"2018-04-24T17:43:51Z","snapshot_observed_at":"2026-07-06T06:30:19.251357Z","submitted_at":"2018-03-26T20:05:59Z","title":"A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.09820","snapshot_observed_at":"2026-08-12T12:47:07.998128Z","title":"A disciplined approach to neural network hyper- parameters: Part 1 – learning rate, batch size, momentum, and weight decay,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.998128Z"},"links":{"cited_paper":"/paper/1803.09820","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:a52dc0951a55b6be824ca8473548dd2f16be109ff24fff94bf40f3ac8f039c8c","observation_id":"b8da6d46-4e2f-415c-81e5-f43511feadd1","resolution":{"observed_at":"2026-08-12T12:47:07.998128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-12T12:47:07.994016Z","title":"Available: https://arxiv.org/abs/1412.6980","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.994016Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:989f445a7471e96d121df5883c861676310f9f9b91183b25bbccfaf5c0ee69c8","observation_id":"1e9a7477-a92d-48bc-b0fc-9533cff1b65e","resolution":{"observed_at":"2026-08-12T12:47:07.994016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.13431","last_updated":"2023-08-25T15:23:06Z","snapshot_observed_at":"2026-08-13T10:27:37.044750Z","submitted_at":"2023-08-25T15:23:06Z","title":"Six Lectures on Linearized Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.13431","snapshot_observed_at":"2026-08-12T12:47:08.012659Z","title":"Six lectures on linearized neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.012659Z"},"links":{"cited_paper":"/paper/2308.13431","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:d0c6155b7914b684b46324c103f8c7d51a9d8957c6cf9e5923f1cd49fcdaa0f3","observation_id":"031e90a6-9aa5-4f22-b5b1-627a090e29a4","resolution":{"observed_at":"2026-08-12T12:47:08.012659Z","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":"2026-08-12T12:47:08.692706Z","title":"The shape of learning curves: A review,","venue":null,"work_id":"e3e890ec-d302-4b74-a44e-8ccdbe1c5dd6","year":2023},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.008585Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:b8ec31dd82efcc1688e13eefd60fdd05a2f67cbd6def02fe503402b2596d0465","observation_id":"60846d31-4815-47c8-a723-a004a825840e","resolution":{"observed_at":"2026-08-12T12:47:08.696390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.668937Z","title":"What can linearized neural networks actually say about generalization?","venue":null,"work_id":"23efddee-c744-4a6a-92d4-501abd6fe849","year":2021},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.020352Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:d906b630328066bbccc7cc70b20acfd6288d8af4b9c9f55c22da8dff16eb9bf2","observation_id":"75d8c0d0-9821-4cf7-ae0d-15e112f6aa96","resolution":{"observed_at":"2026-08-12T12:47:08.673339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.681110Z","title":"Neural tangent kernel: Convergence and generalization in neural networks,","venue":null,"work_id":"bff51235-dae1-4805-b3fd-1d283c0a7fe5","year":2018},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.016707Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:4f7adfd4bbbd311388502ded4376694f96f91dc7d10910f30e26188958069ced","observation_id":"9a1b29c6-e905-43b4-aa21-46da0646aafd","resolution":{"observed_at":"2026-08-12T12:47:08.685130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.644552Z","title":"Incremental pid controller-based learning rate scheduler for stochastic gradient descent,","venue":null,"work_id":"d3f76732-b925-4a03-95c7-97a4a268d668","year":2024},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.028243Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:8f345d19ad7456565ac7ee3e84b1ad1b4660ba170af98a459ee5c899ea338fad","observation_id":"c7c10acd-bc06-4084-86d6-19a137eeb7ca","resolution":{"observed_at":"2026-08-12T12:47:08.649140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.657141Z","title":"Wide neural networks of any depth evolve as linear models under gradient descent,","venue":null,"work_id":"16ec6124-b4db-4920-85d6-678d27a9edae","year":2019},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.024237Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:fb8ddc1074ac546f4bb2b493628d42214ccdbc82548c3350b78f9c87e2e3c038","observation_id":"e913d2f6-beaf-423b-81d7-ab83ffc06f44","resolution":{"observed_at":"2026-08-12T12:47:08.661245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.620568Z","title":"Distribution of the largest eigenvalue for real wishart and gaussian random matrices and a simple approximation for the tracy–widom distribution,","venue":null,"work_id":"3751d79e-4af0-4146-ac8e-0ab5fe0ec677","year":2014},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.035332Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:e9076e6c9910709ad249507cc9774f755b3596d4e22182e0a470a810b926dedb","observation_id":"bf94e6e0-ea51-4a14-8ff8-7f13d4986963","resolution":{"observed_at":"2026-08-12T12:47:08.624732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.632345Z","title":null,"venue":null,"work_id":"d2ada28d-590d-4812-99bb-f2eba3d017a1","year":1997},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.031810Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:e79f112c9d01a163535eb9ff89327a1f7d2426d636a9910cb669512f5e3131be","observation_id":"43cf6485-8b44-46ff-a0f8-3f36e8a01568","resolution":{"observed_at":"2026-08-12T12:47:08.636402Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02281","last_updated":"2019-10-26T06:58:22Z","snapshot_observed_at":"2026-08-06T22:39:11.101764Z","submitted_at":"2018-10-04T15:53:32Z","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02281","snapshot_observed_at":"2026-08-12T12:47:08.042205Z","title":"A convergence analysis of gradient descent for deep linear neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.042205Z"},"links":{"cited_paper":"/paper/1810.02281","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:8de013f0b61bcdbfda50e4d569d8f8cfdd635d0399e8624134c2004256e08cab","observation_id":"bc779744-8424-470b-b98e-afe19be35b99","resolution":{"observed_at":"2026-08-12T12:47:08.042205Z","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":"2026-08-12T12:47:08.609438Z","title":"Maximal initial learning rates in deep relu networks,","venue":null,"work_id":"105f1c95-97cf-4062-9060-8d165aec9cbb","year":2023},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.038661Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:faf9543c9ee152bb3c28699738daa910bed5b9c1d5ea8b8a80b6bc725c89dcef","observation_id":"b93c998f-a977-487c-b7a3-7b68f94bdff1","resolution":{"observed_at":"2026-08-12T12:47:08.613185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.5701","last_updated":"2012-12-22T15:46:49Z","snapshot_observed_at":"2026-07-06T03:02:42.105044Z","submitted_at":"2012-12-22T15:46:49Z","title":"ADADELTA: An Adaptive Learning Rate Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.5701","snapshot_observed_at":"2026-08-12T12:47:08.049579Z","title":"Adadelta: An adaptive learning rate method,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.049579Z"},"links":{"cited_paper":"/paper/1212.5701","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:f26bca56a01cede0106acdd3703f1473dd49e47f1ff074331438e613bb3a2f4e","observation_id":"7721a42c-8f4b-46dd-b755-247b0bb848a7","resolution":{"observed_at":"2026-08-12T12:47:08.049579Z","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":"2026-08-12T12:47:08.597871Z","title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude,","venue":null,"work_id":"9f65c814-5c47-43dd-8bd0-7fb5e96dd52a","year":2012},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.046087Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:43c9c1324f43038e90051ececc7d78e6b97b5fa0cf03057442516c2f51d09a2b","observation_id":"692432f8-f454-42e6-9b67-7d6bdd9339e5","resolution":{"observed_at":"2026-08-12T12:47:08.601946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.056777Z","title":"Array programming with NumPy,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.056777Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:268076ce9cb28d67e810595e68019f53ee4037c31eac15e1a7047a0d6c5e7884","observation_id":"e8c2b2d1-510e-410a-8d2d-f66b1b181e71","resolution":{"observed_at":"2026-08-12T12:47:08.056777Z","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":"2026-08-12T12:47:08.586171Z","title":"Van Rossum and F","venue":null,"work_id":"45276f95-faa9-4735-a2f5-eb5aba2c11e8","year":2009},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.053311Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:0cc1cb7d4732e2324dc6fe69f6a7d4aae8b1a086230ace88db0a2f1161da593c","observation_id":"28e4ada5-a4cb-4954-9fb5-052497bc171e","resolution":{"observed_at":"2026-08-12T12:47:08.590144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.063851Z","title":"Scikit-learn: Machine learning in Python,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.063851Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:bacaa60c70995996c4ba7f9e1ed15f1e562cd43beec124e36733c647d782c44b","observation_id":"5705dba9-3458-4f9d-8320-8a5ca4368736","resolution":{"observed_at":"2026-08-12T12:47:08.063851Z","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":"2026-08-12T12:47:08.060253Z","title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.060253Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:3c593b24666ea97ed094dec3938a24fa191ceb9b0875abec557e145cfd49a125","observation_id":"cc8b231f-6693-4831-a947-6b1d43b9590c","resolution":{"observed_at":"2026-08-12T12:47:08.060253Z","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":"2026-08-12T12:47:08.071449Z","title":"Matplotlib: A 2d graphics environment,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.071449Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:85509b62b2ac04bc4d4e9717200073a7af57fb2172b1f1fdfd94ff2b288d8ade","observation_id":"d94d3ebf-4f96-43fd-8f8d-0fad62a2110f","resolution":{"observed_at":"2026-08-12T12:47:08.071449Z","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":"2026-08-12T12:47:08.067645Z","title":"Paszke, S","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.067645Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:b0d7c24fc993103f2bfcee26385d342e5ae8eff8c1898f52879e7f863dd85ec7","observation_id":"a512b36d-7864-496f-97d4-4ed5530494c3","resolution":{"observed_at":"2026-08-12T12:47:08.067645Z","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":"2026-08-12T12:47:08.534956Z","title":"Sparse spatial autoregressions,","venue":null,"work_id":"5981e77f-2da7-4e2e-bc6c-955f3fb7a1d6","year":1997},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.079341Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:5be0255b9cc261e69e27e689a5ca82fc4c2b1215d9dcb83098cd01e1ddb80137","observation_id":"5b236560-16f9-4ff5-a4d0-c972e18077e1","resolution":{"observed_at":"2026-08-12T12:47:08.538859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.546476Z","title":"The mnist database of handwritten digit images for machine learning research [best of the web],","venue":null,"work_id":"ba6e3c06-d413-4e73-8e77-746a8dc5b479","year":2012},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.075268Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:65ba4430b63cbaaa16fbff124afee0be8b7be1da24967fa5e2a053c8d7a3f11f","observation_id":"752982ca-59b3-43b5-bf49-8bf3acc08716","resolution":{"observed_at":"2026-08-12T12:47:08.550294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.087208Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.087208Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:157efabb6038892a5c149816f8ee0315c3e700923935ef7f9315dbb57d874e8f","observation_id":"a75c6c04-31f8-412c-b783-d206a1b2a4e0","resolution":{"observed_at":"2026-08-12T12:47:08.087208Z","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":"2026-08-12T12:47:08.523018Z","title":"The marginal value of adaptive gradient methods in machine learning,","venue":null,"work_id":"3ce3c3e7-f9c2-483a-86ac-b140221d1562","year":2017},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.083245Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:c15e1b6899f59a34b82551a3193bff9658079d5c96b2c3d7381d0469eca42809","observation_id":"e1da35fa-ab7c-41f4-bbab-3058307bdc30","resolution":{"observed_at":"2026-08-12T12:47:08.527009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1709.01953","last_updated":"2017-09-08T03:27:06Z","snapshot_observed_at":"2026-07-06T05:58:24.260916Z","submitted_at":"2017-09-06T18:12:04Z","title":"Implicit Regularization in Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.01953","snapshot_observed_at":"2026-08-12T12:47:08.099559Z","title":"Implicit regularization in deep learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.099559Z"},"links":{"cited_paper":"/paper/1709.01953","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:c30220c6a5ff2d763c023af1a439512f4b77d31f52fb66098e362c53893b0713","observation_id":"bfe77262-30ba-49f0-9104-5b48760d7d29","resolution":{"observed_at":"2026-08-12T12:47:08.099559Z","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":"2026-08-12T12:47:08.504459Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":"143f19c1-b07d-485a-8c05-2f77c1ac9b2f","year":null},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.090921Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:28cf9ebf2b5f99f90d6f9808dcc1984009f58f9b991cb1a617159fa183d79a7d","observation_id":"f59dfe29-b176-4f00-8cc5-a248116b8db3","resolution":{"observed_at":"2026-08-12T12:47:08.508526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.480112Z","title":"Implicit gradient regularization,","venue":null,"work_id":"27329f00-0447-4a68-b5fa-3a2cf1b9eff7","year":2021},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.107574Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:3a61b2c201aa859ad0703a8a8e625bd3ddcfeb6e61e2133245826c6f47ed687a","observation_id":"db1d0b37-6831-4f1c-886d-0f482b5836e2","resolution":{"observed_at":"2026-08-12T12:47:08.484142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T12:47:08.111062Z","title":"Dropout: A simple way to prevent neural networks from overfitting,","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.111062Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:8d8589b903427b7d483c6df0b4460ed249fd3c9592b806a98208e80e5ffcf413","observation_id":"97e0294e-b227-487a-8e40-85a14f0b5c13","resolution":{"observed_at":"2026-08-12T12:47:08.111062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.01075","last_updated":"2018-10-02T05:27:59Z","snapshot_observed_at":"2026-07-06T07:05:33.551678Z","submitted_at":"2018-10-02T05:27:59Z","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.01075","snapshot_observed_at":"2026-08-12T12:47:08.103513Z","title":"Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.103513Z"},"links":{"cited_paper":"/paper/1810.01075","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:a0e581ee2471c908a4b8e8f55805c70fad11a2fa4606a828dd0319edd02830f1","observation_id":"0f556149-976b-4648-a820-7d76bd326af5","resolution":{"observed_at":"2026-08-12T12:47:08.103513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-08-12T21:01:12.961874Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-12T12:47:08.114886Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.114886Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:591b876faf7fb5f2e379dd5ecdda313e63e15dc2af0e4c186bd3674d05150935","observation_id":"2f07008d-ecc5-47f0-ab7a-c3b14d9ff7a1","resolution":{"observed_at":"2026-08-12T12:47:08.114886Z","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":"2026-08-12T12:47:08.492447Z","title":"Available: http://dblp.uni-trier.de/db/conf/iclr/iclr2015","venue":null,"work_id":"3bcf4453-bac4-41b2-aa3d-637212d21ed8","year":null},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:08.094872Z"},"links":{"citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:98634809614c673d29c64cf1446b50ddb04d706023f3014cacb3089452cc48cd","observation_id":"94f1e5a8-ee27-4f37-8691-531b39efe478","resolution":{"observed_at":"2026-08-12T12:47:08.496489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.01186","last_updated":"2017-04-04T11:34:46Z","snapshot_observed_at":"2026-07-06T04:19:46.347735Z","submitted_at":"2015-06-03T09:54:31Z","title":"Cyclical Learning Rates for Training Neural Networks","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.01186","snapshot_observed_at":"2026-08-12T12:47:07.985553Z","title":"Available: https://arxiv.org/abs/1506.01186","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-12T12:47:07.985553Z"},"links":{"cited_paper":"/paper/1506.01186","citing_paper":"/paper/2411.16975"},"observation_digest":"sha256:0c27e3d33ed47e57fe1c08cf609617861d42142b0eb516537d32efe62c14adda","observation_id":"c5317c77-8249-4e8d-8b02-c2a2ea61b0f2","resolution":{"observed_at":"2026-08-12T12:47:07.985553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.16975","last_updated":"2024-11-25T22:58:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T12:38:40.548742Z","submitted_at":"2024-11-25T22:58:22Z","title":"ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":1,"verified_fuzzy":17},"total_outbound_references":39},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2411.16975."}