{"as_of":"2026-08-15T19:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4d555741a494ce43c9eb301f9d29267bf247fb18143db4483f7a26028e22565f","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:54:42.444889Z","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":"2026-05-18T10:02:31.731647Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.17465","last_updated":"2025-01-10T14:22:02Z","snapshot_observed_at":"2026-08-12T23:15:26.466256Z","submitted_at":"2024-07-24T17:58:42Z","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17465","snapshot_observed_at":"2026-08-12T12:58:57.081120Z","title":"u-mup: The unit-scaled maximal update parametrization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.17470","last_updated":"2024-12-31T16:25:39Z","snapshot_observed_at":"2026-08-15T07:17:21.654510Z","submitted_at":"2024-11-25T18:59:04Z","title":"Towards Precise Scaling Laws for Video Diffusion Transformers","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T12:58:57.081120Z"},"links":{"cited_paper":"/paper/2407.17465","citing_paper":"/paper/2411.17470"},"observation_digest":"sha256:aa7e43c15b9c0bd7537da20708e80cd20afc13aabbf90efd8aaace30e1a38d92","observation_id":"121e8797-2caf-4cb6-9959-b24eda427fd7","resolution":{"observed_at":"2026-08-12T12:58:57.081120Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17465","last_updated":"2025-01-10T14:22:02Z","snapshot_observed_at":"2026-08-12T23:15:26.466256Z","submitted_at":"2024-07-24T17:58:42Z","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17465","snapshot_observed_at":"2026-08-15T19:54:42.444889Z","title":"Prince, Bj ¨orn Deiseroth, Andres Felipe Cruz-Salinas, Carlo Luschi, Samuel Weinbach, and Douglas Orr","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.15025","last_updated":"2025-06-17T23:57:30Z","snapshot_observed_at":"2026-08-15T19:43:21.687596Z","submitted_at":"2025-06-17T23:57:30Z","title":"Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T19:54:42.444889Z"},"links":{"cited_paper":"/paper/2407.17465","citing_paper":"/paper/2506.15025"},"observation_digest":"sha256:093c59140215a6bc92c6a3bea85777d49c1ea0fc5f281f95a4b094117c3ddc8f","observation_id":"b3f8b846-6e14-4517-be05-f687fba975d8","resolution":{"observed_at":"2026-08-15T19:54:42.444889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17465","last_updated":"2025-01-10T14:22:02Z","snapshot_observed_at":"2026-08-12T23:15:26.466256Z","submitted_at":"2024-07-24T17:58:42Z","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","version":3},"cited_work":{"arxiv_id":"2407.17465","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.17465","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"u-µp: The unit- scaled maximal update parametrization.arXiv preprint arXiv:2407.17465","venue":null,"work_id":"ceefab8a-2f82-4c5c-9707-1b9ca6fcbc6b","year":null},"citing_paper":{"arxiv_id":"2510.04212","last_updated":"2026-04-18T01:36:25Z","snapshot_observed_at":"2026-08-11T09:38:23.812338Z","submitted_at":"2025-10-05T14:01:24Z","title":"Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-18T10:01:56.131253Z"},"links":{"cited_paper":"/paper/2407.17465","citing_paper":"/paper/2510.04212"},"observation_digest":"sha256:71b70e7a57f3d39e2fa6441a47843d3a84de3e19430460c1440834230c9193c9","observation_id":"c8ce8386-332b-4824-a827-d4101c1410d5","resolution":{"observed_at":"2026-05-18T10:02:31.733884Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17465","last_updated":"2025-01-10T14:22:02Z","snapshot_observed_at":"2026-08-12T23:15:26.466256Z","submitted_at":"2024-07-24T17:58:42Z","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17465","snapshot_observed_at":"2026-08-01T04:48:12.346022Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22444","last_updated":"2026-07-24T16:06:38Z","snapshot_observed_at":"2026-08-07T12:35:33.045317Z","submitted_at":"2026-07-24T16:06:38Z","title":"Hyperball May Not Be a Free Lunch","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-01T04:48:12.346022Z"},"links":{"cited_paper":"/paper/2407.17465","citing_paper":"/paper/2607.22444"},"observation_digest":"sha256:e51e81a0009c0f920669f08b826811f51eb6318a14328e3386f805e4f1691989","observation_id":"0e7143be-abcd-479d-a343-a5401669593c","resolution":{"observed_at":"2026-08-01T04:48:12.346022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2407.17465/citation-record","integrity":"/paper/2407.17465/integrity","json":"/paper/2407.17465/citation-record.json","paper":"/paper/2407.17465"},"outbound":[],"paper":{"arxiv_id":"2407.17465","last_updated":"2025-01-10T14:22:02Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T23:15:26.466256Z","submitted_at":"2024-07-24T17:58:42Z","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2407.17465."}