{"as_of":"2026-08-09T23:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d48573c24d7bc5bb4b0ee388ab7b0836b98b46bdbbeba01a3ae5f3e93d151cba","coverage":[{"denominator":9,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-02T16:07:05.189001Z","state":"measured"},{"denominator":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"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/2607.00329/citation-record","integrity":"/paper/2607.00329/integrity","json":"/paper/2607.00329/citation-record.json","paper":"/paper/2607.00329"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1126/science.adi5639","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Mechanism for feature learning in neural networks and backpropagation-free machine learning models","venue":"Science","work_id":"5b10646c-ed3d-46ba-abc3-6260539fe2ba","year":2024},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:3e85e24d90e76789b63ee4b8460da5ce3b45ea56ec0b14be78510e704935cd43","observation_id":"c69dbda7-e970-40cd-9340-202bb5d5c068","resolution":{"observed_at":"2026-07-02T16:07:07.943092Z","resolver_source":"doi","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":"2026-07-09T09:49:33.711283+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-09T09:49:33.711283+00:00","source":"openalex_status_cache"},{"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":"2026-07-05T23:21:36.225368Z","title":"Kernel methods","venue":null,"work_id":"21453977-84aa-41bb-a4ef-d732ebe1d9b9","year":2016},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:0a64649232e24a495c17288d2ab4122b2fd66943b4487142b201d227e5916569","observation_id":"3c4c764c-0f49-4f5f-88bf-1e9912991d6a","resolution":{"observed_at":"2026-07-05T23:21:36.226822Z","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":"2026-07-05T23:21:36.232160Z","title":"Wahba.Spline Models for Observational Data, volume 59 ofCBMS-NSF Regional Conference Series in Applied Mathematics","venue":null,"work_id":"0b32fa62-fac2-45f9-a5da-dc9c1c039675","year":1990},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:d7fffbe50303a6dd22eb8a3202331333baeabf96b1e243f3da7ab05d515fe098","observation_id":"3a454221-e4ca-416b-b5cb-fee7c6328e97","resolution":{"observed_at":"2026-07-05T23:21:36.234120Z","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":"2407.20199","last_updated":"2025-07-09T04:06:02Z","snapshot_observed_at":"2026-08-09T15:22:12.820309Z","submitted_at":"2024-07-29T17:28:58Z","title":"Emergence in non-neural models: grokking modular arithmetic via average gradient outer product","version":3},"cited_work":{"arxiv_id":"2407.20199","doi":"10.48550/arxiv.2407.20199","metadata_source":"arxiv_reference","pith_arxiv_id":"2407.20199","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2407.20199 , year=","venue":"arXiv (Cornell University)","work_id":"22faa262-6492-4d72-a7af-87ca517bfd9f","year":2024},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"cited_paper":"/paper/2407.20199","citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:c495355a9660bb840e11fe96e49e3c1ce18e08649565ffd2c5b798545a746e21","observation_id":"8b641fd5-8c62-4355-b149-a2c948b7657a","resolution":{"observed_at":"2026-07-02T16:07:08.195458Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03708","last_updated":"2025-05-28T19:52:55Z","snapshot_observed_at":"2026-08-09T20:04:49.664257Z","submitted_at":"2025-02-06T01:41:48Z","title":"Toward universal steering and monitoring of AI models","version":2},"cited_work":{"arxiv_id":"2502.03708","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.03708","snapshot_observed_at":"2026-07-02T16:07:08.191129Z","title":"Toward universal steering and monitoring of ai models","venue":null,"work_id":"f7d70242-10c6-4575-8442-50778d535e2f","year":2025},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"cited_paper":"/paper/2502.03708","citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:43943e6eef52f4ec90a59092362bb8cc20b2fc5cb9cdc576c1d6913cf32e72e6","observation_id":"04d420b4-6eaa-4b4d-852c-80852e9f932d","resolution":{"observed_at":"2026-07-02T16:07:08.192626Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1073/pnas.2411325122","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Linear recursive feature machines provably recover low-rank matrices.Proceedings of the National Academy of Sciences, 122 (13):e2411325122","venue":"Proceedings of the National Academy of Sciences","work_id":"26c56a51-80f0-4469-806e-f8e74bd30e7b","year":2025},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:920cfdd6d1a5a3a74900bca1c08865f3d3d10f418cabe38c79870fda2126d115","observation_id":"d626de17-d773-43e0-b827-7638e0f39ece","resolution":{"observed_at":"2026-07-02T16:07:07.940755Z","resolver_source":"doi","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":"2026-07-05T23:21:36.219391Z","title":"Average gradient outer product as a mechanism for deep neural collapse","venue":null,"work_id":"954ead8a-230e-41b0-86dc-c749a029e881","year":2024},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:87163574a5d13c7983f50c7128a10dfa13f9876c07a4d4f2e368a42ad86eec60","observation_id":"fc9eb094-7ef2-46f1-abb1-b209d3586997","resolution":{"observed_at":"2026-07-05T23:21:36.221075Z","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":"2026-07-05T23:21:36.222857Z","title":"The k-inverse rfm framework","venue":null,"work_id":"296130d7-fac6-43eb-b4c9-e0896df7623e","year":2025},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:d1f7390efb07e40e5efe0ce8c3b2fe16231d955fc9760e066eeec6bcb712fb1b","observation_id":"d36fdbdb-a93c-4f4f-9548-12515e555f14","resolution":{"observed_at":"2026-07-05T23:21:36.225140Z","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":"2026-07-05T23:21:36.229615Z","title":"Deep learning through the lens of example difficulty","venue":null,"work_id":"a62c0e5e-7728-4c8d-b06d-9783e0fb7327","year":2021},"citing_paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-02T16:07:05.189001Z"},"links":{"citing_paper":"/paper/2607.00329"},"observation_digest":"sha256:4f18a3f0b827621af822ca72e80227587b76de380a51f9ff9e445bed79eb62b8","observation_id":"9caff14a-8a48-4357-a426-415a675595bf","resolution":{"observed_at":"2026-07-05T23:21:36.231470Z","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"}}],"paper":{"arxiv_id":"2607.00329","last_updated":"2026-07-01T02:08:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T03:37:30.563746Z","submitted_at":"2026-07-01T02:08:05Z","title":"K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks"},"reference_resolution":{"displayed":9,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":3,"verified_fuzzy":5},"total_outbound_references":9},"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 9 of 9 outbound references and 0 inbound Pith citation observations for arXiv:2607.00329."}