{"as_of":"2026-08-09T07:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7512fa3acf19217376e8e9448189458d835934089a8c6ce2e68e3fd57dbead0d","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":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T21:56:28.103866Z","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":"2026-07-04T08:19:44.419278Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.01235","last_updated":"2025-06-23T09:29:57Z","snapshot_observed_at":"2026-08-03T17:13:44.553385Z","submitted_at":"2025-02-03T10:50:03Z","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01235","snapshot_observed_at":"2026-08-07T21:56:28.103866Z","title":"One-step full gradient suffices for low-rank fine-tuning, provably and efficiently","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.09376","last_updated":"2025-06-03T01:42:41Z","snapshot_observed_at":"2026-08-09T05:22:18.959697Z","submitted_at":"2025-02-13T14:45:11Z","title":"LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T21:56:28.103866Z"},"links":{"cited_paper":"/paper/2502.01235","citing_paper":"/paper/2502.09376"},"observation_digest":"sha256:d57caccd6e8a4646c2944755c9c31d793fce785ddd0d62683e55501c200f52db","observation_id":"697a3dbe-9bbf-4765-b1d1-41004303ff33","resolution":{"observed_at":"2026-08-07T21:56:28.103866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01235","last_updated":"2025-06-23T09:29:57Z","snapshot_observed_at":"2026-08-03T17:13:44.553385Z","submitted_at":"2025-02-03T10:50:03Z","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01235","snapshot_observed_at":"2026-08-07T13:04:50.710627Z","title":"One-step full gradient suffices for low-rank fine-tuning, provably and efficiently","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23194","last_updated":"2025-08-17T05:48:16Z","snapshot_observed_at":"2026-08-07T12:48:51.160815Z","submitted_at":"2025-05-29T07:33:03Z","title":"Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:04:50.710627Z"},"links":{"cited_paper":"/paper/2502.01235","citing_paper":"/paper/2505.23194"},"observation_digest":"sha256:8427b367cbed931c571e75c606f4704b5b1c8b5eedcd4e9b6abfc47451314b0d","observation_id":"4a5746d7-93e9-4521-a468-ba60d607330b","resolution":{"observed_at":"2026-08-07T13:04:50.710627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01235","last_updated":"2025-06-23T09:29:57Z","snapshot_observed_at":"2026-08-03T17:13:44.553385Z","submitted_at":"2025-02-03T10:50:03Z","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently","version":3},"cited_work":{"arxiv_id":"2502.01235","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01235","snapshot_observed_at":"2026-07-04T08:19:44.419278Z","title":"Zhang, F","venue":null,"work_id":"d02aabd6-6d11-4b1b-9d43-556003ce16d5","year":2025},"citing_paper":{"arxiv_id":"2606.05899","last_updated":"2026-06-04T09:05:59Z","snapshot_observed_at":"2026-07-06T23:45:51.910263Z","submitted_at":"2026-06-04T09:05:59Z","title":"High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T02:14:38.644041Z"},"links":{"cited_paper":"/paper/2502.01235","citing_paper":"/paper/2606.05899"},"observation_digest":"sha256:5779004764652bf65a7d6f59f3bbca1be86b6126e70082225d17f54fd2dba4d6","observation_id":"a3c2d280-9bbc-41f0-88fb-86d9c5507173","resolution":{"observed_at":"2026-07-02T12:16:57.382824Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01235","last_updated":"2025-06-23T09:29:57Z","snapshot_observed_at":"2026-08-03T17:13:44.553385Z","submitted_at":"2025-02-03T10:50:03Z","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently","version":3},"cited_work":{"arxiv_id":"2502.01235","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01235","snapshot_observed_at":"2026-07-04T08:19:44.419278Z","title":"Zhang, F","venue":null,"work_id":"d02aabd6-6d11-4b1b-9d43-556003ce16d5","year":2025},"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":80,"source":"arxiv_source","source_observed_at":"2026-06-27T07:14:08.479610Z"},"links":{"cited_paper":"/paper/2502.01235","citing_paper":"/paper/2606.12883"},"observation_digest":"sha256:ce581a2a737fd55c7b53d786f81dbaeb5b280c41caff97bd647e752fb5a820f1","observation_id":"28f8896a-54b2-4298-94b6-6a50faacb722","resolution":{"observed_at":"2026-07-03T14:08:21.934456Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01235","last_updated":"2025-06-23T09:29:57Z","snapshot_observed_at":"2026-08-03T17:13:44.553385Z","submitted_at":"2025-02-03T10:50:03Z","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently","version":3},"cited_work":{"arxiv_id":"2502.01235","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01235","snapshot_observed_at":"2026-07-04T08:19:44.419278Z","title":"Zhang, F","venue":null,"work_id":"d02aabd6-6d11-4b1b-9d43-556003ce16d5","year":2025},"citing_paper":{"arxiv_id":"2606.22019","last_updated":"2026-06-20T12:48:31Z","snapshot_observed_at":"2026-08-06T19:21:18.734073Z","submitted_at":"2026-06-20T12:48:31Z","title":"Channel Location Constrains the Auditability of Subliminal Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-26T11:52:03.948568Z"},"links":{"cited_paper":"/paper/2502.01235","citing_paper":"/paper/2606.22019"},"observation_digest":"sha256:7fd5011c21ee7952ebf77c1da2e28fa9c5be2ebf6e476343cc6db67813a55ffe","observation_id":"fff784f6-0818-4b94-9f82-4a35e93baf58","resolution":{"observed_at":"2026-07-04T08:19:44.420644Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01235","last_updated":"2025-06-23T09:29:57Z","snapshot_observed_at":"2026-08-03T17:13:44.553385Z","submitted_at":"2025-02-03T10:50:03Z","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01235","snapshot_observed_at":"2026-08-01T00:26:41.122870Z","title":"arXiv preprint arXiv:2502.01235 , 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":31,"source":"arxiv_source","source_observed_at":"2026-08-01T00:26:41.122870Z"},"links":{"cited_paper":"/paper/2502.01235","citing_paper":"/paper/2607.26247"},"observation_digest":"sha256:b1e86d6e54c07a5e4c415c18faf37237c8b67fec1a5506bf120f638b8843d170","observation_id":"8b72c719-4d81-4fd3-983f-4896b623a813","resolution":{"observed_at":"2026-08-01T00:26:41.122870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.01235/citation-record","integrity":"/paper/2502.01235/integrity","json":"/paper/2502.01235/citation-record.json","paper":"/paper/2502.01235"},"outbound":[],"paper":{"arxiv_id":"2502.01235","last_updated":"2025-06-23T09:29:57Z","latest_version":3,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-03T17:13:44.553385Z","submitted_at":"2025-02-03T10:50:03Z","title":"LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2502.01235."}