{"as_of":"2026-08-12T04:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b923ca2ca26dd0f66e4afdf4092605b0730c98e9a679fdd991d628f05d4583fc","coverage":[{"denominator":5,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T08:57:37.922572Z","state":"measured"},{"denominator":7,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":7,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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":"2026-08-02T08:47:18.055950Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.30385","snapshot_observed_at":"2026-07-11T21:14:13.772368Z","title":"LLMs without deep neural networks: New architecture, benefits and case study","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04166","last_updated":"2026-07-14T19:56:25Z","snapshot_observed_at":"2026-08-08T03:23:17.754007Z","submitted_at":"2026-07-05T08:09:25Z","title":"Piercing Gilbreath's Conjecture: From Deep Number Theory Insights to Fintech and Cybersecurity","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-11T21:14:13.772368Z"},"links":{"cited_paper":"/paper/2605.30385","citing_paper":"/paper/2607.04166"},"observation_digest":"sha256:b124e570150be4ce9a72085586de3b60e430249e8ce80495d9383cd55a1af59f","observation_id":"9da7235c-a838-410f-aa3e-ea66dfc2e654","resolution":{"observed_at":"2026-07-11T21:14:13.772368Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.30385","snapshot_observed_at":"2026-08-02T08:47:18.055950Z","title":"LLMs without deep neural networks: New architecture, benefits and case study","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04166","last_updated":"2026-07-14T19:56:25Z","snapshot_observed_at":"2026-08-08T03:23:17.754007Z","submitted_at":"2026-07-05T08:09:25Z","title":"Piercing Gilbreath's Conjecture: From Deep Number Theory Insights to Fintech and Cybersecurity","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T08:47:18.055950Z"},"links":{"cited_paper":"/paper/2605.30385","citing_paper":"/paper/2607.04166"},"observation_digest":"sha256:846cabff6abc99a5dee6f34d39ee3c9298f4ad2604a7f34069431a0346f91f6e","observation_id":"e49f98c5-ef99-4026-badc-8e629989419b","resolution":{"observed_at":"2026-08-02T08:47:18.055950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.30385/citation-record","integrity":"/paper/2605.30385/integrity","json":"/paper/2605.30385/citation-record.json","paper":"/paper/2605.30385"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:57:37.922572Z","title":"Concept control for LLM safety using radial basis function representations.ACM Digital Library, pages 220–232, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T08:57:37.922572Z"},"links":{"citing_paper":"/paper/2605.30385"},"observation_digest":"sha256:c9eb78e48951b3e754d991847c5449c0a755a263756ffb19c234b7a325176392","observation_id":"437c946c-c19b-4cd9-8504-058c945d6b86","resolution":{"observed_at":"2026-06-29T08:57:37.922572Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:57:37.922572Z","title":"MLT, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T08:57:37.922572Z"},"links":{"citing_paper":"/paper/2605.30385"},"observation_digest":"sha256:2f2b3784eed7d177facfcc4237d62993b723014da0af2a865fe9a19893895fc4","observation_id":"fcf9268f-9e5a-4a9b-9da2-db47826e5478","resolution":{"observed_at":"2026-06-29T08:57:37.922572Z","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":"2407.1105","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T09:03:15.984125Z","title":"A comprehensive survey on Kolmogorov Arnold networks (KAN).Preprint, pages 1–16, 2025","venue":null,"work_id":"5339d38e-fd2c-4a3f-8b38-03c4a53bc36d","year":2025},"citing_paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T08:57:37.922572Z"},"links":{"citing_paper":"/paper/2605.30385"},"observation_digest":"sha256:4b02b476e9276ae58fa014493e3a2359293d8bc06006fa50c783096348a9b85c","observation_id":"bc6a90cf-21a8-4c88-90ee-536778feccc7","resolution":{"observed_at":"2026-06-29T09:03:15.985655Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-06-29T08:57:37.922572Z","title":"arXiv:2510:06660v1 [Link]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T08:57:37.922572Z"},"links":{"citing_paper":"/paper/2605.30385"},"observation_digest":"sha256:dff8304d021669a0b26e1eb0512b62b47bade1305ba9e0946fa6938033582745","observation_id":"4250f239-017c-46c3-9205-0f7eecf1745b","resolution":{"observed_at":"2026-06-29T08:57:37.922572Z","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":"2602.0579","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T09:03:15.986726Z","title":"Nonlinearity as rank: Generative low-rank adapter with radial basis functions.Preprint, pages 1–31, 2026","venue":null,"work_id":"e95cde8a-3c1a-4815-92f9-ec269b259f21","year":2026},"citing_paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T08:57:37.922572Z"},"links":{"citing_paper":"/paper/2605.30385"},"observation_digest":"sha256:78d30d3b416648ff347dfe266ec10effab663bafcb9865926ccbbd72929b5f4d","observation_id":"2f3001e0-c199-4c7d-9d4b-376f0da1b862","resolution":{"observed_at":"2026-06-29T09:03:15.988875Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.30385","last_updated":"2026-05-28T07:34:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T14:26:23.798226Z","submitted_at":"2026-05-28T07:34:15Z","title":"LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study"},"reference_resolution":{"displayed":5,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":5},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 5 of 5 outbound references and 2 inbound Pith citation observations for arXiv:2605.30385."}