{"as_of":"2026-08-10T14:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5cda6558af775b5e61f1df20a23b477b4fdf7e457490ccc4a72a921d4a29bc7c","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T19:58:26.557007Z","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":"2026-07-02T16:07:09.409008Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.23819","last_updated":"2024-10-31T11:04:07Z","snapshot_observed_at":"2026-08-10T11:58:55.034699Z","submitted_at":"2024-10-31T11:04:07Z","title":"Weight decay induces low-rank attention layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.23819","snapshot_observed_at":"2026-08-08T19:58:26.557007Z","title":"Weight decay induces low-rank attention layers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05300","last_updated":"2025-05-23T17:22:54Z","snapshot_observed_at":"2026-08-09T04:49:29.861223Z","submitted_at":"2025-02-07T20:10:05Z","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T19:58:26.557007Z"},"links":{"cited_paper":"/paper/2410.23819","citing_paper":"/paper/2502.05300"},"observation_digest":"sha256:1917590b00698257bec2a5be56ef6e30792de4ea98da08488f48c155c23cf961","observation_id":"e6cd0852-1bdd-4edd-8e26-659ecad58608","resolution":{"observed_at":"2026-08-08T19:58:26.557007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.23819","last_updated":"2024-10-31T11:04:07Z","snapshot_observed_at":"2026-08-10T11:58:55.034699Z","submitted_at":"2024-10-31T11:04:07Z","title":"Weight decay induces low-rank attention layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.23819","snapshot_observed_at":"2026-08-07T13:32:31.007337Z","title":"Weight decay induces low-rank attention layers, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21487","last_updated":"2025-05-27T17:54:07Z","snapshot_observed_at":"2026-08-07T13:24:37.243429Z","submitted_at":"2025-05-27T17:54:07Z","title":"Hardware-Efficient Attention for Fast Decoding","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T13:32:31.007337Z"},"links":{"cited_paper":"/paper/2410.23819","citing_paper":"/paper/2505.21487"},"observation_digest":"sha256:44a0d0a299e261ac21b1909f7f5f4a23201a99d22481a874ff94869d9517805a","observation_id":"e5f0562a-5d2d-4c4f-aa66-386544c71ac7","resolution":{"observed_at":"2026-08-07T13:32:31.007337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.23819","last_updated":"2024-10-31T11:04:07Z","snapshot_observed_at":"2026-08-10T11:58:55.034699Z","submitted_at":"2024-10-31T11:04:07Z","title":"Weight decay induces low-rank attention layers","version":1},"cited_work":{"arxiv_id":"2410.23819","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.23819","snapshot_observed_at":"2026-07-02T16:07:09.409008Z","title":"Kobayashi, Y","venue":null,"work_id":"8de2c116-dbe7-4c5e-8761-a5d5471fba5c","year":2024},"citing_paper":{"arxiv_id":"2606.07404","last_updated":"2026-06-05T15:48:42Z","snapshot_observed_at":"2026-07-06T23:47:05.104295Z","submitted_at":"2026-06-05T15:48:42Z","title":"Reversible Foundations: Training a 120B Sparse MoE through State-Preserving Scaling","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-06-27T22:55:09.477413Z"},"links":{"cited_paper":"/paper/2410.23819","citing_paper":"/paper/2606.07404"},"observation_digest":"sha256:a6053103999b5500694edfe721a55ccf0e2b67b6a03d91a7cbc21e7391069628","observation_id":"980c0097-80fc-463b-98e3-d57fca6188e6","resolution":{"observed_at":"2026-07-02T16:07:09.410275Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.23819/citation-record","integrity":"/paper/2410.23819/integrity","json":"/paper/2410.23819/citation-record.json","paper":"/paper/2410.23819"},"outbound":[],"paper":{"arxiv_id":"2410.23819","last_updated":"2024-10-31T11:04:07Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T11:58:55.034699Z","submitted_at":"2024-10-31T11:04:07Z","title":"Weight decay induces low-rank attention layers"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.23819."}