{"as_of":"2026-08-19T09:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:10e38d57b10a4cef48c9afd52d6e15b00418427750cd2b2251f132f5c9589d54","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:08:33.467330Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2608.12597/citation-record","integrity":"/paper/2608.12597/integrity","json":"/paper/2608.12597/citation-record.json","paper":"/paper/2608.12597"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:08:34.759559Z","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","venue":null,"work_id":"dfe66625-d58a-46e3-821f-73206e38f797","year":2021},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:30.637520Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:2a3d9344253485318dd803373c25c89d4992ed0537b36e1cecf609fad6b07b61","observation_id":"813f79ef-836b-400c-9768-9229ff52ee96","resolution":{"observed_at":"2026-08-16T00:08:34.763847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.748518Z","title":"The fast Johnson–Lindenstrauss transform and approximate nearest neighbors","venue":null,"work_id":"fdba17a8-746e-4b5e-811a-f0f02b2b5dd0","year":2009},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:30.863173Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:d760769e13cc5fdff1d74a87143a3d62c3b53f579a11f8a3362d3f6f512c006e","observation_id":"ea84966b-9de2-4ac3-84aa-c58110e5b0cc","resolution":{"observed_at":"2026-08-16T00:08:34.752462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:31.837274Z","title":"Living on the Edge: Phase Transitions in Convex Programs with Random Data","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:31.837274Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:5a646c072760d59c58ff25bbe593a12e87b99b5ab1c23e690e1a298bcc40a640","observation_id":"d3d15786-d731-4ed9-8c35-8cf12f88a787","resolution":{"observed_at":"2026-08-16T00:08:31.837274Z","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":"2026-08-16T00:08:34.736658Z","title":"Exact expressions for double descent and implicit regularization via surrogate random design","venue":null,"work_id":"e99a9fe9-d515-4559-aecc-598d65e641ad","year":2020},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.186017Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:7db90706d478e237ebf5d92c48450d2c8e012586a9bdcdc44d483dea819c78e2","observation_id":"f13ba29d-4351-446a-8763-125c751c49ba","resolution":{"observed_at":"2026-08-16T00:08:34.740759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.624207Z","title":"An investigation into neural net optimization via hessian eigenvalue density","venue":null,"work_id":"b30d0ef4-59f9-4153-9da8-1fdf298ce2be","year":2019},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.215684Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:04b04446c558a3f3a3cfae09bfe0c93dff72bfe412ce635904197c08b6f16508","observation_id":"5b5ae243-86e7-4c2d-ae3b-6152ddaa230c","resolution":{"observed_at":"2026-08-16T00:08:34.727703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.612551Z","title":"On Milman’s Inequality and Random Subspaces which Escape through a Mesh in Rn","venue":null,"work_id":"9c1c9b34-4eec-4ec2-818b-605483fa5745","year":1988},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.221132Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:4c5b9c4a328b386c041aebae0da279d74ed8f1cdf717758fe7652ab2a1d46bb5","observation_id":"b3e135b1-e5bc-4d9b-b28f-25d5cf40e728","resolution":{"observed_at":"2026-08-16T00:08:34.616816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.599711Z","title":"Improving Neural Network Training in Low Dimensional Random Bases","venue":null,"work_id":"844446b6-78d5-4af1-a7b7-56db74a76cb6","year":2020},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.226582Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:e73c4528956b085cfb1be9e868b2f2d1fee4eaf08ed9b9e00e093fc08bd3ec83","observation_id":"8e733eb3-e193-4a23-9eaa-668ad3861839","resolution":{"observed_at":"2026-08-16T00:08:34.604263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.538950Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","venue":null,"work_id":"306d71b2-3532-4412-a390-dd142ba1b446","year":2022},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.232054Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:f2d54031e6688f1d6645c02fa602b1fc8b81ba41853753c2b17f1b5d2d2816a3","observation_id":"4132ba17-2358-4846-b6dc-4259abcd6121","resolution":{"observed_at":"2026-08-16T00:08:34.561987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02556","last_updated":"2024-04-30T01:58:16Z","snapshot_observed_at":"2026-08-16T14:55:16.035060Z","submitted_at":"2023-10-04T03:30:24Z","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02556","snapshot_observed_at":"2026-08-16T00:08:32.237668Z","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.237668Z"},"links":{"cited_paper":"/paper/2310.02556","citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:d222c0853e61c45729ae7c46b2ba6e7e367b499c5e03af5c48e3296fb9b4bc6e","observation_id":"aeb3677e-58ca-490a-914d-4cb38efaaf50","resolution":{"observed_at":"2026-08-16T00:08:32.237668Z","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":"2026-08-16T00:08:34.525630Z","title":"VeRA: Vector-based Random Matrix Adaptation","venue":null,"work_id":"7a374d93-1832-4aad-8af7-2ae1bc0cabf9","year":2024},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.243268Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:9c20e841d3d49ea7e5048719c834c5b095511dd986706b234f1a40e3e020ea07","observation_id":"af22e4c3-7fc9-419c-bb6e-586a0f15a97c","resolution":{"observed_at":"2026-08-16T00:08:34.530199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.454183Z","title":"How Many Degrees of Freedom Do We Need to Train Deep Networks: A Loss Landscape Perspective","venue":null,"work_id":"af0c4565-46d3-46c8-866b-641134763b16","year":2022},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.247792Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:9cf002c01aeed03a73b8f6ba7aed75d78158cda73b282bdca0f1de9a31726917","observation_id":"d4effd97-f469-43fe-b41a-9cf78c91fdd1","resolution":{"observed_at":"2026-08-16T00:08:34.516594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.371868Z","title":"Fastfood - Computing Hilbert Space Ex- pansions in Loglinear Time","venue":null,"work_id":"5698d6c6-eede-4778-9966-054ea1b61e81","year":2013},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.254256Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:b349f3f811927fda4206ea7b387fb4c3f9916d8539a01b93299032bd488b1252","observation_id":"0401c524-29e6-4aec-b2db-a90e0293fda2","resolution":{"observed_at":"2026-08-16T00:08:34.375344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.359874Z","title":"Eigenvectors of some large sample covariance matrix ensembles","venue":null,"work_id":"a0363b39-c4ac-46d0-b107-316e034ed807","year":2011},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.319112Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:2e4e0a4550e126637324a283072a701f3d27f651f188946dcfa3be768891efd7","observation_id":"33e07686-36e8-4138-bcc7-134087ee7ba7","resolution":{"observed_at":"2026-08-16T00:08:34.363564Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.301488Z","title":"Measuring the intrinsic dimension of objective landscapes","venue":null,"work_id":"b062757e-2a4e-4165-8ac8-0d2dff53c82a","year":2018},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.392344Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:f8c297a9fa5b3e4bc1546b6b30cb2de71f827de805b9247c2324b025b1d8357c","observation_id":"2d2a0872-92f5-476d-ba68-776aae0fbb0a","resolution":{"observed_at":"2026-08-16T00:08:34.352908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.160078Z","title":"D´ ecomposition orthogonale d’un espace hilbertien selon deux cˆ ones mutuellement polaires","venue":null,"work_id":"7e13d8a4-dde9-474b-ae22-fb352c229bc4","year":1962},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.519660Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:96e415f4fd7916702b7a1f248398fdbac4e611a6d2d12fc53e8b7d33f7092abf","observation_id":"12674da8-e811-481f-a2eb-c5f9c38f0478","resolution":{"observed_at":"2026-08-16T00:08:34.232131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.08464","last_updated":"2023-08-28T22:09:07Z","snapshot_observed_at":"2026-08-16T16:52:23.962852Z","submitted_at":"2022-06-16T22:03:35Z","title":"PRANC: Pseudo RAndom Networks for Compacting deep models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.08464","snapshot_observed_at":"2026-08-16T00:08:32.655162Z","title":"PRANC: Pseudo RAndom Networks for Compacting Deep Models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.655162Z"},"links":{"cited_paper":"/paper/2206.08464","citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:550c5fb4edca925cfb2f55195cf41643bf4fdc7545c0c619e92662153bebecd2","observation_id":"4868493b-ab0d-4977-8230-e15e16d7e13a","resolution":{"observed_at":"2026-08-16T00:08:32.655162Z","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":"2026-08-16T00:08:34.054593Z","title":"Traces of class/cross-class structure pervade deep learning spectra","venue":null,"work_id":"9d4e70e3-1fbe-4ae2-a14c-00d9014704dd","year":2020},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:32.859120Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:db33ca7a6503865e95be4f7819457d4097502886d5515849bea1b3bf1e694f19","observation_id":"e6457d4f-6717-4bc8-af8f-4b43d7207107","resolution":{"observed_at":"2026-08-16T00:08:34.058613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:34.005149Z","title":"Spectral convergence for a general class of random matrices","venue":null,"work_id":"556056e2-bf94-4554-b494-e3713cf668d2","year":2011},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:33.102115Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:06debeec33a8e689e498dc53589df3369455d150f143518df19c0d05008fb300","observation_id":"18d61a6d-9ada-422d-a768-a669a7b50cdb","resolution":{"observed_at":"2026-08-16T00:08:34.046679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.04454","last_updated":"2018-05-07T15:43:39Z","snapshot_observed_at":"2026-08-17T17:22:50.487571Z","submitted_at":"2017-06-14T12:50:00Z","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.04454","snapshot_observed_at":"2026-08-16T00:08:33.244736Z","title":"Empirical analysis of the hessian of over-parametrized neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:33.244736Z"},"links":{"cited_paper":"/paper/1706.04454","citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:79fb3739b7a02bffbbebc060a1c7715ee7b412013fea80f423763a389a92e374","observation_id":"68dfad4a-8a60-4011-a539-acb70c8c9d82","resolution":{"observed_at":"2026-08-16T00:08:33.244736Z","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":"2026-08-16T00:08:33.774162Z","title":"Mapping Networks","venue":null,"work_id":"229af15e-d6a3-4509-aa72-2826e3b2a3cd","year":2026},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:33.371150Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:6b848b56f53dbea3ee7af5649b47ab1c18e97b2bc94c9df6c7ca9fbf5c61cfa2","observation_id":"dbbbff45-f2f8-493c-b994-e465408b485b","resolution":{"observed_at":"2026-08-16T00:08:33.909289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:33.726589Z","title":"Improved analysis of the subsampled randomized Hadamard transform","venue":null,"work_id":"6873f32d-0c53-4d51-925e-d5eafea651fe","year":2011},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:33.378415Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:960ab6173b750d05529e2c667e6001708f0863021716b9b44fc4859b5f9c3ca1","observation_id":"4ad33e4e-c446-47b2-9edc-91a0d0573ae5","resolution":{"observed_at":"2026-08-16T00:08:33.732141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:33.382517Z","title":"Cambridge Series in Statistical and Probabilistic Mathematics","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:33.382517Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:87ba1b0b47b0c677f09b74cf93904e8985b81f65c4a437ee9b4b93bfdd2c6e18","observation_id":"04efdb92-04aa-4c13-84f5-148056c982e8","resolution":{"observed_at":"2026-08-16T00:08:33.382517Z","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":"2026-08-16T00:08:33.710513Z","title":"Theorem2 (Random affine-slice intersection: conic phase transition).Let S⊂R P be nonempty, compact, and convex, let θ0 /∈S, and let C be the closed convex cone of Lemma 1","venue":null,"work_id":"145ac5ab-17eb-4e16-96b4-c68869fb56e4","year":null},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:33.427248Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:bec36ff1d8facdda5a1a5a66d6183bc7a02ccd5d1e88c5cff6ba48bc82c7225f","observation_id":"e9401236-9a44-4856-84cb-3d8a18289cd5","resolution":{"observed_at":"2026-08-16T00:08:33.716870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-16T00:08:33.572696Z","title":null,"venue":null,"work_id":"e38a86ae-91c0-4cf7-8ed1-c1c434704c29","year":null},"citing_paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T00:08:33.467330Z"},"links":{"citing_paper":"/paper/2608.12597"},"observation_digest":"sha256:bc46fa5d1c7c3b1d0ab8a28fb649355dc4b38f353357f1eeec9c967f9061ceb5","observation_id":"0d86c5c1-2936-48e9-87b0-c603b0047f14","resolution":{"observed_at":"2026-08-16T00:08:33.651930Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.12597","last_updated":"2026-08-12T21:09:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T23:10:38.746431Z","submitted_at":"2026-08-12T21:09:54Z","title":"Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":17},"total_outbound_references":24},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2608.12597."}