{"as_of":"2026-08-08T05:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3c24d4d2ef3dbd98f3bf71b9ce302db10e6834b19b139faa5dd8058696f08c31","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":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T20:37:27.957110Z","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":"2026-07-03T14:08:21.901987Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2602.04998","last_updated":"2026-05-19T00:07:35Z","snapshot_observed_at":"2026-08-04T11:18:43.351216Z","submitted_at":"2026-02-04T19:36:20Z","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","version":2},"cited_work":{"arxiv_id":"2602.04998","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.04998","snapshot_observed_at":"2026-07-03T14:08:21.901987Z","title":"Learning rate matters: Vanilla lora may suffice for llm fine-tuning","venue":"cs.LG","work_id":"a4431fdf-7da3-46b4-80d9-3bbfdbe43c9a","year":2026},"citing_paper":{"arxiv_id":"2602.22911","last_updated":"2026-07-09T08:44:52Z","snapshot_observed_at":"2026-08-02T20:37:26.270680Z","submitted_at":"2026-02-26T11:55:25Z","title":"CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation with Non-linearity Retained at Inference","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-15T18:55:02.067855Z"},"links":{"cited_paper":"/paper/2602.04998","citing_paper":"/paper/2602.22911"},"observation_digest":"sha256:95b7bbe26e9b4db9eda6be7e03e9673f1a55931d5a65013f0f2794cc7831f2c1","observation_id":"baad59e7-3ae2-4ee3-9e25-1e74354d4a1f","resolution":{"observed_at":"2026-05-20T02:04:51.678500Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2602.04998","last_updated":"2026-05-19T00:07:35Z","snapshot_observed_at":"2026-08-04T11:18:43.351216Z","submitted_at":"2026-02-04T19:36:20Z","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.04998","snapshot_observed_at":"2026-08-02T20:37:27.957110Z","title":"Learning rate matters: Vanilla lora may suffice for llm fine-tuning.arXiv preprint arXiv:2602.04998, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2602.22911","last_updated":"2026-07-09T08:44:52Z","snapshot_observed_at":"2026-08-02T20:37:26.270680Z","submitted_at":"2026-02-26T11:55:25Z","title":"CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation with Non-linearity Retained at Inference","version":7},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T20:37:27.957110Z"},"links":{"cited_paper":"/paper/2602.04998","citing_paper":"/paper/2602.22911"},"observation_digest":"sha256:3ba16826e9a8f1eb928b82283cddf1c3552c75b1add4e6c76a89b605929456ba","observation_id":"cd955bd4-0fb0-49ce-99df-314e580067f2","resolution":{"observed_at":"2026-08-02T20:37:27.957110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.04998","last_updated":"2026-05-19T00:07:35Z","snapshot_observed_at":"2026-08-04T11:18:43.351216Z","submitted_at":"2026-02-04T19:36:20Z","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","version":2},"cited_work":{"arxiv_id":"2602.04998","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.04998","snapshot_observed_at":"2026-07-03T14:08:21.901987Z","title":"Learning rate matters: Vanilla lora may suffice for llm fine-tuning","venue":"cs.LG","work_id":"a4431fdf-7da3-46b4-80d9-3bbfdbe43c9a","year":2026},"citing_paper":{"arxiv_id":"2606.12883","last_updated":"2026-06-11T04:19:32Z","snapshot_observed_at":"2026-08-02T22:02:12.932569Z","submitted_at":"2026-06-11T04:19:32Z","title":"The Hidden Power of Scaling Factor in LoRA Optimization","version":1},"reference_index":131,"source":"arxiv_source","source_observed_at":"2026-06-27T07:14:08.479610Z"},"links":{"cited_paper":"/paper/2602.04998","citing_paper":"/paper/2606.12883"},"observation_digest":"sha256:86509a2a04bfd7fc69747ecfb7f9074e7b17dc65b655137c5f1877755852a982","observation_id":"dcb6b5d9-9f97-442e-917e-8c32da8fce70","resolution":{"observed_at":"2026-07-03T14:08:21.903465Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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"}},{"citation":{"cited_paper":{"arxiv_id":"2602.04998","last_updated":"2026-05-19T00:07:35Z","snapshot_observed_at":"2026-08-04T11:18:43.351216Z","submitted_at":"2026-02-04T19:36:20Z","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.04998","snapshot_observed_at":"2026-08-02T15:39:38.407161Z","title":"Learning rate matters: Vanilla lora may suffice for llm fine-tuning.arXiv:2602.04998,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.11889","last_updated":"2026-07-17T09:32:58Z","snapshot_observed_at":"2026-08-06T12:28:12.211551Z","submitted_at":"2026-04-24T17:00:53Z","title":"Scaling Point-in-Time Language Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T15:39:38.407161Z"},"links":{"cited_paper":"/paper/2602.04998","citing_paper":"/paper/2607.11889"},"observation_digest":"sha256:16f1bf566b8a30e79f7d65afe0ecccf55e49355397f7febaa82719fa1eb56b95","observation_id":"4a83669e-bd95-4d7a-bf67-c65b80da2199","resolution":{"observed_at":"2026-08-02T15:39:38.407161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.04998","last_updated":"2026-05-19T00:07:35Z","snapshot_observed_at":"2026-08-04T11:18:43.351216Z","submitted_at":"2026-02-04T19:36:20Z","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.04998","snapshot_observed_at":"2026-08-01T00:26:40.999766Z","title":"arXiv preprint arXiv:2602.04998 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26247","last_updated":"2026-07-28T20:32:04Z","snapshot_observed_at":"2026-08-03T17:13:17.383834Z","submitted_at":"2026-07-28T20:32:04Z","title":"Between Gradient and Natural Gradient: A Continuum of LoRA Initializations","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-01T00:26:40.999766Z"},"links":{"cited_paper":"/paper/2602.04998","citing_paper":"/paper/2607.26247"},"observation_digest":"sha256:e2f87bdeb8f734c14da7a7a498e579c9fdfea48e39954f69b7fc0b7cbb5d2f84","observation_id":"afb31c7d-84aa-4028-893a-3f5a1f372c10","resolution":{"observed_at":"2026-08-01T00:26:40.999766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2602.04998/citation-record","integrity":"/paper/2602.04998/integrity","json":"/paper/2602.04998/citation-record.json","paper":"/paper/2602.04998"},"outbound":[],"paper":{"arxiv_id":"2602.04998","last_updated":"2026-05-19T00:07:35Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T11:18:43.351216Z","submitted_at":"2026-02-04T19:36:20Z","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2602.04998."}