{"as_of":"2026-08-07T19:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:24ef780c628cb8fa54a465b32bfab9620ddb494a16491a07ac91214fd7387b2a","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:49:01.606633Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T18:16:30.548575Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.11742","last_updated":"2021-06-10T16:24:03Z","snapshot_observed_at":"2026-07-06T10:43:55.668836Z","submitted_at":"2021-02-23T15:10:15Z","title":"Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.11742","snapshot_observed_at":"2026-08-07T12:49:01.606633Z","title":"simplicity bias","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.24060","last_updated":"2025-05-29T23:03:33Z","snapshot_observed_at":"2026-08-07T12:34:20.944521Z","submitted_at":"2025-05-29T23:03:33Z","title":"Characterising the Inductive Biases of Neural Networks on Boolean Data","version":1},"reference_index":1952,"source":"pdf_text","source_observed_at":"2026-08-07T12:49:01.606633Z"},"links":{"cited_paper":"/paper/2102.11742","citing_paper":"/paper/2505.24060"},"observation_digest":"sha256:03bb8d5ea75c04098715c05bc36787561b3b93b4de5b8bcdd6f7852c6d1a7a1a","observation_id":"6680115e-63c0-4c6f-84a6-2245eed6da38","resolution":{"observed_at":"2026-08-07T12:49:01.606633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.11742","last_updated":"2021-06-10T16:24:03Z","snapshot_observed_at":"2026-07-06T10:43:55.668836Z","submitted_at":"2021-02-23T15:10:15Z","title":"Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed","version":2},"cited_work":{"arxiv_id":"2102.11742","doi":"10.48550/arxiv.2102.11742","metadata_source":"pith","pith_arxiv_id":"2102.11742","snapshot_observed_at":"2026-08-06T18:16:30.548575Z","title":"Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed","venue":"cs.LG","work_id":"d9a5c2af-44e5-40f3-ba95-a7e077e3043a","year":2021},"citing_paper":{"arxiv_id":"2507.19680","last_updated":"2025-07-25T21:19:37Z","snapshot_observed_at":"2026-08-07T16:14:29.307306Z","submitted_at":"2025-07-25T21:19:37Z","title":"Feature learning is decoupled from generalization in high capacity neural networks","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T14:17:37.193874Z"},"links":{"cited_paper":"/paper/2102.11742","citing_paper":"/paper/2507.19680"},"observation_digest":"sha256:e7817eb483b3fb7c29b195cda45767f89c8e956c7751149834996335ebb1d5e0","observation_id":"6940197f-a7b6-4a1d-82a7-3a7610951614","resolution":{"observed_at":"2026-08-06T14:17:37.581135Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2102.11742/citation-record","integrity":"/paper/2102.11742/integrity","json":"/paper/2102.11742/citation-record.json","paper":"/paper/2102.11742"},"outbound":[],"paper":{"arxiv_id":"2102.11742","last_updated":"2021-06-10T16:24:03Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:43:55.668836Z","submitted_at":"2021-02-23T15:10:15Z","title":"Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2102.11742."}