{"as_of":"2026-08-12T18:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0a8a730d50bfe57b6066dd7221fd507f3a04f6abbe15167c0d1bfbd8cc2e777e","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":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":20,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T15:50:24.215832Z","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":"2026-07-10T02:06:42.146567Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-11T15:50:24.215832Z","title":"Relora: High-rank training through low-rank updates","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.10663","last_updated":"2025-03-12T09:19:31Z","snapshot_observed_at":"2026-08-12T09:32:56.029527Z","submitted_at":"2024-12-14T03:32:54Z","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T15:50:24.215832Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2412.10663"},"observation_digest":"sha256:8aec435751c0ef6a52f80a9604121056354538a4a70a4d24327d296581c5381f","observation_id":"bd284cb7-e48f-44f4-91c2-705c9cac06ff","resolution":{"observed_at":"2026-08-11T15:50:24.215832Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-11T12:53:33.168970Z","title":"Relora: High- rank training through low-rank updates","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2412.13795","last_updated":"2025-08-04T10:49:54Z","snapshot_observed_at":"2026-08-11T15:11:02.089169Z","submitted_at":"2024-12-18T12:39:53Z","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T12:53:33.168970Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2412.13795"},"observation_digest":"sha256:f4eca1b07860fd3a1b3f1335e316128a2481576ec10179bb401292c784a4fbc4","observation_id":"124b9d85-224e-4ce7-a286-632dcd38daa0","resolution":{"observed_at":"2026-08-11T12:53:33.168970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-11T12:46:10.050201Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13860","last_updated":"2024-12-18T13:53:59Z","snapshot_observed_at":"2026-08-11T15:11:13.849658Z","submitted_at":"2024-12-18T13:53:59Z","title":"Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepali","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T12:46:10.050201Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2412.13860"},"observation_digest":"sha256:22df02168fe890d528585cd6cdbf476fd71644595cc7e917a0af9f313e3c28cb","observation_id":"548fc2f8-53d1-4501-84b9-f062bada8cc4","resolution":{"observed_at":"2026-08-11T12:46:10.050201Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-11T11:04:15.887682Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15891","last_updated":"2024-12-20T13:47:02Z","snapshot_observed_at":"2026-08-11T15:11:14.947889Z","submitted_at":"2024-12-20T13:47:02Z","title":"TelcoLM: collecting data, adapting, and benchmarking language models for the telecommunication domain","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T11:04:15.887682Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2412.15891"},"observation_digest":"sha256:58835679cfab54fc412f07fb5a262268f9f6bcd3df73e7a318b1af9860095f6e","observation_id":"51cc4eb0-ba82-43d3-babd-9b19327521b0","resolution":{"observed_at":"2026-08-11T11:04:15.887682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-09T10:22:03.776369Z","title":"Lialin, N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03006","last_updated":"2025-02-05T09:03:50Z","snapshot_observed_at":"2026-08-11T18:16:57.739385Z","submitted_at":"2025-02-05T09:03:50Z","title":"An Augmented Backward-Corrected Projector Splitting Integrator for Dynamical Low-Rank Training","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T10:22:03.776369Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2502.03006"},"observation_digest":"sha256:1de548626bf8a1a128852456be3842220fa0a6ce9ba5278d60a7595d4d6a5fab","observation_id":"a36d3f0b-9e49-48b6-b50d-bd91059382cd","resolution":{"observed_at":"2026-08-09T10:22:03.776369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-06T20:35:02.852629Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02503","last_updated":"2025-07-03T10:11:22Z","snapshot_observed_at":"2026-08-10T13:12:16.738751Z","submitted_at":"2025-07-03T10:11:22Z","title":"Continual Gradient Low-Rank Projection Fine-Tuning for LLMs","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T20:35:02.852629Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2507.02503"},"observation_digest":"sha256:067f065a74742f4f1f9bd5f597ea822ec544ff77cbff555500cb4aa5a7c403c4","observation_id":"4855d484-9584-4e62-a1ed-0d5776b9e806","resolution":{"observed_at":"2026-08-06T20:35:02.852629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2509.18993","last_updated":"2026-05-13T13:30:21Z","snapshot_observed_at":"2026-08-02T18:52:22.902766Z","submitted_at":"2025-09-23T13:43:02Z","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-18T14:51:30.312509Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2509.18993"},"observation_digest":"sha256:4a92f396aee1396f19221805b6bee9f5aab7356ee594afe25646586370711a59","observation_id":"153af4f0-3b22-4ad2-8611-541cea8e6175","resolution":{"observed_at":"2026-05-18T14:52:41.324350Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-04T12:51:25.455456Z","title":"Relora: High-rank training through low-rank updates, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.01878","last_updated":"2026-06-26T18:31:10Z","snapshot_observed_at":"2026-08-09T08:33:12.415406Z","submitted_at":"2025-10-02T10:35:38Z","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T12:51:25.455456Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2510.01878"},"observation_digest":"sha256:fd83b6c9118907e497468501d904cbb1ffe7c6b16360af28d892fde61e62c0aa","observation_id":"7cc56b29-0149-4627-a9f8-6ec1316c84be","resolution":{"observed_at":"2026-08-04T12:51:25.455456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2512.12131","last_updated":"2026-05-11T19:05:27Z","snapshot_observed_at":"2026-08-11T00:07:48.019440Z","submitted_at":"2025-12-13T01:50:18Z","title":"BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-16T23:19:02.358348Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2512.12131"},"observation_digest":"sha256:30b510165cda0872f40f01e49e1712939f90aacb339d69d6ad19658cbeb0396b","observation_id":"72a64d4d-f66a-4c27-81ab-6fab3a69a622","resolution":{"observed_at":"2026-05-16T23:21:21.601131Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-08-03T06:01:15.043569Z","title":"ReLoRA: High-Rank Training Through Low-Rank Up- dates.arXiv, cs/2307.05695:1–16,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.00942","last_updated":"2026-05-28T22:25:40Z","snapshot_observed_at":"2026-08-10T20:43:52.684307Z","submitted_at":"2026-02-01T00:00:11Z","title":"SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-03T06:01:15.043569Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2602.00942"},"observation_digest":"sha256:eb594145530648a8e8128525a9b369f653a00357c32320f71e7df9abd61a1a2b","observation_id":"12fe74ee-5dea-4b09-b00c-008f5d16932e","resolution":{"observed_at":"2026-08-03T06:01:15.043569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2604.27308","last_updated":"2026-04-30T01:43:00Z","snapshot_observed_at":"2026-08-11T11:31:19.971355Z","submitted_at":"2026-04-30T01:43:00Z","title":"BoostLoRA: Growing Effective Rank by Boosting Adapters","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-07T08:00:21.048408Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2604.27308"},"observation_digest":"sha256:111f804ebcb36e1b3ae2871c069e0f5681763156d060d03cdf9c39c37849f9e6","observation_id":"efbb39c7-fbc8-4b30-89c7-6eb423aedfeb","resolution":{"observed_at":"2026-05-12T10:06:27.712338Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2605.04079","last_updated":"2026-04-14T16:32:50Z","snapshot_observed_at":"2026-08-11T06:23:45.994277Z","submitted_at":"2026-04-14T16:32:50Z","title":"Efficient Handwriting-Based Alzheimer,s Disease Diagnosis Using a Low-Rank Mixture of Experts Deep Learning Framework","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-10T15:42:17.370111Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2605.04079"},"observation_digest":"sha256:2278faacf911af1b60378ba7a139e4e68e8da73e482fb5a212a56f810cfe9357","observation_id":"7cd5a9d7-dab1-4765-9024-a24209de57f0","resolution":{"observed_at":"2026-05-11T10:01:01.201168Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2605.10288","last_updated":"2026-05-12T10:19:03Z","snapshot_observed_at":"2026-07-06T23:22:18.704329Z","submitted_at":"2026-05-11T09:50:10Z","title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-12T04:47:04.868735Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2605.10288"},"observation_digest":"sha256:115ba3a230b774e2512fa368e1addae1b6bb6b8839ab26ff29928ffa8799d3c0","observation_id":"a766e48a-8ae2-43ec-a7e9-5a9f2b076824","resolution":{"observed_at":"2026-05-12T05:56:26.558486Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2605.10288","last_updated":"2026-05-12T10:19:03Z","snapshot_observed_at":"2026-07-06T23:22:18.704329Z","submitted_at":"2026-05-11T09:50:10Z","title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-13T06:20:42.781613Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2605.10288"},"observation_digest":"sha256:fda97f18dcf560fe259b6462c2374bea52610b8e938f7e2632814d90355ab485","observation_id":"f7fd6c88-2410-4ba7-9801-36ce7eeaedf4","resolution":{"observed_at":"2026-05-13T06:22:23.298870Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2605.18541","last_updated":"2026-05-18T15:22:26Z","snapshot_observed_at":"2026-08-02T14:46:31.423931Z","submitted_at":"2026-05-18T15:22:26Z","title":"LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-20T11:16:01.428052Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2605.18541"},"observation_digest":"sha256:a60764a01523bfdd7d095d24e26f8cf3871ff1c49a7eb9c09b43d60ee2296be7","observation_id":"918267e3-1286-4dae-8b4a-451ed8315c89","resolution":{"observed_at":"2026-05-20T11:18:13.754377Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2605.21147","last_updated":"2026-05-20T13:19:28Z","snapshot_observed_at":"2026-07-06T23:31:37.061253Z","submitted_at":"2026-05-20T13:19:28Z","title":"SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-21T05:59:59.183023Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2605.21147"},"observation_digest":"sha256:ce73dd0b7839f98ebdab83df88e280b41afae71deb6b8a7daa62c80accbd17ed","observation_id":"275a1496-00d5-4c9a-acbf-212331581b3d","resolution":{"observed_at":"2026-05-21T06:03:59.402280Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"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":50,"source":"arxiv_source","source_observed_at":"2026-06-27T22:55:09.477413Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2606.07404"},"observation_digest":"sha256:306c4cc059bf61b871bdbba643a4a818e9f65fb0a97a16d4542ef9c7a361f005","observation_id":"1ec04512-5d60-49ed-8607-45542a854e0a","resolution":{"observed_at":"2026-07-02T16:07:09.438425Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2606.28932","last_updated":"2026-06-27T14:07:45Z","snapshot_observed_at":"2026-07-07T00:02:57.622708Z","submitted_at":"2026-06-27T14:07:45Z","title":"DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-30T09:49:22.481708Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2606.28932"},"observation_digest":"sha256:6ec5b39e8fabf701596a3d5befdb7fe9835e4077b31924028e8aef013eacc942","observation_id":"98a906c3-101e-4d0d-883f-bf05af8b81da","resolution":{"observed_at":"2026-06-30T09:54:35.108636Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2606.29184","last_updated":"2026-06-28T04:08:09Z","snapshot_observed_at":"2026-08-04T15:21:29.245858Z","submitted_at":"2026-06-28T04:08:09Z","title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-30T07:55:13.502149Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2606.29184"},"observation_digest":"sha256:f8c7a3688a964c439cbb6bbc0431fe224f2d2e1adcfada535f49d65074601118","observation_id":"a5849019-1966-4811-8489-8451812f13aa","resolution":{"observed_at":"2026-06-30T08:04:28.505504Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","version":4},"cited_work":{"arxiv_id":"2307.05695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.05695","snapshot_observed_at":"2026-07-10T02:06:42.146567Z","title":"Relora: High- rank training through low-rank updates","venue":"cs.CL","work_id":"186ed055-b204-4457-b3c3-9da3ea7598a0","year":2023},"citing_paper":{"arxiv_id":"2607.08754","last_updated":"2026-07-09T17:51:50Z","snapshot_observed_at":"2026-08-08T05:23:36.079237Z","submitted_at":"2026-07-09T17:51:50Z","title":"SLORR: Simple and Efficient In-Training Low-Rank Regularization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-10T01:58:58.772489Z"},"links":{"cited_paper":"/paper/2307.05695","citing_paper":"/paper/2607.08754"},"observation_digest":"sha256:3b66b8f099f4299ee46fa2bc8b2853bba8b45c6309bdd51b42d18cbdedcfe253","observation_id":"00fcfe97-d5a6-46c4-b795-1c29530050b0","resolution":{"observed_at":"2026-07-10T02:06:42.147808Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2307.05695/citation-record","integrity":"/paper/2307.05695/integrity","json":"/paper/2307.05695/citation-record.json","paper":"/paper/2307.05695"},"outbound":[],"paper":{"arxiv_id":"2307.05695","last_updated":"2023-12-10T16:21:29Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T00:08:18.803043Z","submitted_at":"2023-07-11T18:02:09Z","title":"ReLoRA: High-Rank Training Through Low-Rank Updates"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2307.05695."}