{"as_of":"2026-08-12T23:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fb2bdc291f5581d8cb746c97f74e9bb25391b787dbba1e8aff0ea1fde45dc47b","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T22:49:49.716245Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-21T20:40:36.189460Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2001.02992","last_updated":"2020-01-07T08:31:50Z","snapshot_observed_at":"2026-08-12T20:32:43.703204Z","submitted_at":"2020-01-07T08:31:50Z","title":"Poly-time universality and limitations of deep learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.02992","snapshot_observed_at":"2026-08-10T22:49:49.716245Z","title":"Poly-time universality and limitations of deep learning","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2501.00817","last_updated":"2025-01-08T10:42:53Z","snapshot_observed_at":"2026-08-11T22:41:47.894858Z","submitted_at":"2025-01-01T12:04:06Z","title":"Hardness of Learning Fixed Parities with Neural Networks","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T22:49:49.716245Z"},"links":{"cited_paper":"/paper/2001.02992","citing_paper":"/paper/2501.00817"},"observation_digest":"sha256:bc3d6eea76989cd31d11bfba62ce44b479a98e51d868fc6082bfef146f47789b","observation_id":"961ea479-e4f8-4721-b7c4-e147025c7266","resolution":{"observed_at":"2026-08-10T22:49:49.716245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.02992","last_updated":"2020-01-07T08:31:50Z","snapshot_observed_at":"2026-08-12T20:32:43.703204Z","submitted_at":"2020-01-07T08:31:50Z","title":"Poly-time universality and limitations of deep learning","version":1},"cited_work":{"arxiv_id":"2001.02992","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2001.02992","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Poly-time universality and limitations of deep learning","venue":null,"work_id":"ac6fc2a1-ae70-490d-a335-95f65ea3dca5","year":2001},"citing_paper":{"arxiv_id":"2510.26745","last_updated":"2026-05-18T17:56:38Z","snapshot_observed_at":"2026-08-12T19:37:17.044745Z","submitted_at":"2025-10-30T17:40:22Z","title":"Deep sequence models tend to memorize geometrically; it is unclear why","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-21T20:38:18.005002Z"},"links":{"cited_paper":"/paper/2001.02992","citing_paper":"/paper/2510.26745"},"observation_digest":"sha256:97cc496bea0eb6e2b5e692d7a2903e4aa6baff8df923ef7c32841e4c380c8312","observation_id":"6f7ae1fc-bcf6-46cc-9f20-2ea125d7d72d","resolution":{"observed_at":"2026-05-21T20:40:36.191105Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2001.02992/citation-record","integrity":"/paper/2001.02992/integrity","json":"/paper/2001.02992/citation-record.json","paper":"/paper/2001.02992"},"outbound":[],"paper":{"arxiv_id":"2001.02992","last_updated":"2020-01-07T08:31:50Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T20:32:43.703204Z","submitted_at":"2020-01-07T08:31:50Z","title":"Poly-time universality and limitations of deep learning"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2001.02992."}