{"as_of":"2026-08-09T22:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f467cb497123aa13aee388c8a56b416114227fad52bf2e72c98113601198e9da","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":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":18,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T17:05:22.480219Z","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":"2026-07-03T14:08:21.912213Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-09T17:05:22.480219Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00987","last_updated":"2025-03-12T00:43:45Z","snapshot_observed_at":"2026-08-09T16:57:42.833492Z","submitted_at":"2025-02-03T01:59:45Z","title":"RandLoRA: Full-rank parameter-efficient fine-tuning of large models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T17:05:22.480219Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2502.00987"},"observation_digest":"sha256:c68b006cd4c5c81074a9f6538437de86a8ca4f6462f00aab7f39cb480a08fba4","observation_id":"564d14ce-5b4c-4847-9416-2652b17c7bac","resolution":{"observed_at":"2026-08-09T17:05:22.480219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-08T11:51:09.942047Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07739","last_updated":"2025-05-26T08:53:14Z","snapshot_observed_at":"2026-08-09T04:47:17.333090Z","submitted_at":"2025-02-11T17:59:35Z","title":"HRP: High-Rank Preheating for Superior LoRA Initialization","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T11:51:09.942047Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2502.07739"},"observation_digest":"sha256:b97e5bdb3d7f2e94f9d6951408c121cdb0419f60e5b983bd4437968aa985e939","observation_id":"003ee60f-5673-4d56-a477-a643e2fd7e61","resolution":{"observed_at":"2026-08-08T11:51:09.942047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-07T15:39:36.214177Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14367","last_updated":"2025-05-21T04:18:20Z","snapshot_observed_at":"2026-08-09T09:15:50.680130Z","submitted_at":"2025-05-20T13:49:15Z","title":"Dual Decomposition of Weights and Singular Value Low Rank Adaptation","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T15:39:36.214177Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2505.14367"},"observation_digest":"sha256:d7e56bf063e4b6ebf71952ab58531dae49ad849d23492819a7e0cfe8a047e7a5","observation_id":"a53f9ce5-b36a-4c03-96b6-1357fae0158f","resolution":{"observed_at":"2026-08-07T15:39:36.214177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-07T11:57:28.972955Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.01049","last_updated":"2025-06-01T15:30:37Z","snapshot_observed_at":"2026-08-09T06:54:42.859556Z","submitted_at":"2025-06-01T15:30:37Z","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T11:57:28.972955Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2506.01049"},"observation_digest":"sha256:74a42776c14862dcea6ffc50e47356309fabf736a0c32647d1ebfc4fbc4f3bf8","observation_id":"0746c1e7-aa97-4e50-b269-2fbc6807cd5e","resolution":{"observed_at":"2026-08-07T11:57:28.972955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-07T00:58:07.648517Z","title":"Bałazy, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12394","last_updated":"2025-06-14T08:19:11Z","snapshot_observed_at":"2026-08-09T13:33:33.877997Z","submitted_at":"2025-06-14T08:19:11Z","title":"LARGO: Low-Rank Regulated Gradient Projection for Robust Parameter Efficient Fine-Tuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:07.648517Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2506.12394"},"observation_digest":"sha256:42e46bbc4aff44dda186d047a9e1875680807cf490f544a5cc6195f1ba2794c5","observation_id":"7ee612e8-ae6c-4045-b8b8-51397e35bdc7","resolution":{"observed_at":"2026-08-07T00:58:07.648517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-07T00:43:45.168599Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13187","last_updated":"2025-06-16T07:55:14Z","snapshot_observed_at":"2026-08-08T09:44:47.898265Z","submitted_at":"2025-06-16T07:55:14Z","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T00:43:45.168599Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2506.13187"},"observation_digest":"sha256:e0cfbb66eb151f46d83273e9c0496bc11157210ec1f3b95189beed1624e8ec48","observation_id":"7d63506e-f843-499f-b50b-437159d7e42f","resolution":{"observed_at":"2026-08-07T00:43:45.168599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-06T18:48:50.089318Z","title":"Lora-xs: Low-rank adaptation with ex- tremely small number of parameters.arXiv preprint arXiv:2405.17604, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08044","last_updated":"2025-07-09T23:52:31Z","snapshot_observed_at":"2026-08-08T12:59:27.580998Z","submitted_at":"2025-07-09T23:52:31Z","title":"ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:48:50.089318Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2507.08044"},"observation_digest":"sha256:97d9abe7899f69cb8b42f7b8cb407a7a1c587ca010e2edc08aada75b3f7ffe04","observation_id":"6f27059d-3527-4167-b794-182897c406d0","resolution":{"observed_at":"2026-08-06T18:48:50.089318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-05T14:01:14.342264Z","title":"Lora-xs: Low-rank adaptation with ex- tremely small number of parameters","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.21810","last_updated":"2025-08-29T17:47:27Z","snapshot_observed_at":"2026-08-09T04:52:30.123179Z","submitted_at":"2025-08-29T17:47:27Z","title":"QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T14:01:14.342264Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2508.21810"},"observation_digest":"sha256:3086f825b4edd483e1b13884f1ca6e3487392cfad3f9becd55e121850c5bb354","observation_id":"2dc00892-6803-452d-9cb4-9f7662801d24","resolution":{"observed_at":"2026-08-05T14:01:14.342264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":"2405.17604","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-03T14:08:21.912213Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":"f922348b-9be3-4eb1-95eb-10bd2640adb8","year":2024},"citing_paper":{"arxiv_id":"2604.21901","last_updated":"2026-04-23T17:48:18Z","snapshot_observed_at":"2026-07-06T23:08:23.939574Z","submitted_at":"2026-04-23T17:48:18Z","title":"GiVA: Gradient-Informed Bases for Vector-Based Adaptation","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-05-09T21:30:55.256395Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2604.21901"},"observation_digest":"sha256:0133b09916bb59463f480102132c4f4384269e397dce4caea05e5eb09caad9f1","observation_id":"f63cceec-33f9-4616-a5f3-8d347e7035c8","resolution":{"observed_at":"2026-05-11T14:36:05.771294Z","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":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":"2405.17604","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-03T14:08:21.912213Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":"f922348b-9be3-4eb1-95eb-10bd2640adb8","year":2024},"citing_paper":{"arxiv_id":"2604.27308","last_updated":"2026-04-30T01:43:00Z","snapshot_observed_at":"2026-08-05T18:40:47.957436Z","submitted_at":"2026-04-30T01:43:00Z","title":"BoostLoRA: Growing Effective Rank by Boosting Adapters","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-07T08:00:21.048408Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2604.27308"},"observation_digest":"sha256:a55e64e24d50dca5e1692c6717b57623ce94cba3b8601ce3f99cfb4c532835a5","observation_id":"b31e3173-f2c3-432d-8f4a-6ad463fecbf9","resolution":{"observed_at":"2026-05-12T10:06:27.685175Z","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":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":"2405.17604","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-03T14:08:21.912213Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":"f922348b-9be3-4eb1-95eb-10bd2640adb8","year":2024},"citing_paper":{"arxiv_id":"2605.07706","last_updated":"2026-05-08T13:14:24Z","snapshot_observed_at":"2026-08-08T22:21:27.039403Z","submitted_at":"2026-05-08T13:14:24Z","title":"Bayesian Fine-tuning in Projected Subspaces","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-11T02:00:47.889194Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2605.07706"},"observation_digest":"sha256:bfb9b51412b4cf2504a5e08a751bc97f321c588fbacc917c4215858ded7cf06f","observation_id":"682668c4-6e90-4c81-b554-452f764f9f67","resolution":{"observed_at":"2026-05-11T04:00:56.242653Z","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":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":"2405.17604","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-03T14:08:21.912213Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":"f922348b-9be3-4eb1-95eb-10bd2640adb8","year":2024},"citing_paper":{"arxiv_id":"2605.08174","last_updated":"2026-05-05T05:34:18Z","snapshot_observed_at":"2026-08-03T02:43:36.490717Z","submitted_at":"2026-05-05T05:34:18Z","title":"CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-05-12T01:13:52.117046Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2605.08174"},"observation_digest":"sha256:a3c6c0b2835c3ec31457ea0d58809d9034859d7483917f0065e92730dd3ad7f9","observation_id":"119b54a7-da0e-4d4f-b3b9-f97a1748c54d","resolution":{"observed_at":"2026-05-12T08:21:24.536668Z","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":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":"2405.17604","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-03T14:08:21.912213Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":"f922348b-9be3-4eb1-95eb-10bd2640adb8","year":2024},"citing_paper":{"arxiv_id":"2605.11872","last_updated":"2026-05-12T09:51:55Z","snapshot_observed_at":"2026-08-07T19:55:48.986376Z","submitted_at":"2026-05-12T09:51:55Z","title":"LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-05-13T06:13:14.111718Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2605.11872"},"observation_digest":"sha256:358e7edfec4fb7240f45aec7d15fd7e78b38fe51cc17997b16ca64c1bda0240a","observation_id":"57154df0-c127-481e-bb18-608358ab88c2","resolution":{"observed_at":"2026-05-13T06:17:23.228322Z","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":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":"2405.17604","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-03T14:08:21.912213Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":"f922348b-9be3-4eb1-95eb-10bd2640adb8","year":2024},"citing_paper":{"arxiv_id":"2605.15916","last_updated":"2026-05-15T12:54:56Z","snapshot_observed_at":"2026-07-06T23:27:11.118592Z","submitted_at":"2026-05-15T12:54:56Z","title":"LoCO: Low-rank Compositional Rotation Fine-tuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-20T19:51:58.803015Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2605.15916"},"observation_digest":"sha256:d2f2591b669af01152f5922ff3319dee7d90bcebf4fe8e17327972db4a9d38d6","observation_id":"c9c1d49b-9d53-4825-bf78-22b12c205a4b","resolution":{"observed_at":"2026-05-20T19:53:42.603234Z","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":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":"2405.17604","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-03T14:08:21.912213Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters","venue":null,"work_id":"f922348b-9be3-4eb1-95eb-10bd2640adb8","year":2024},"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":75,"source":"arxiv_source","source_observed_at":"2026-06-27T07:14:08.479610Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2606.12883"},"observation_digest":"sha256:1819a2300f4b871428b6e578d00de92daae55c92123224f52bb9d58eb74ced6f","observation_id":"d4050f35-e33e-4985-a887-ff32a40b16a3","resolution":{"observed_at":"2026-07-03T14:08:21.913678Z","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":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-07-12T05:08:55.438431Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters.arXiv preprint arXiv:2405.17604, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03065","last_updated":"2026-07-03T07:57:31Z","snapshot_observed_at":"2026-08-09T04:51:38.797328Z","submitted_at":"2026-07-03T07:57:31Z","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-12T05:08:55.438431Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2607.03065"},"observation_digest":"sha256:115c6600a5d2bc21936e49b4066bbedb86a8ba8225c9158c0c4e05657ca9048b","observation_id":"a37bc0f4-6b8c-404f-9163-bc7ae9d8beeb","resolution":{"observed_at":"2026-07-12T05:08:55.438431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-02T02:01:48.319847Z","title":"Lora-xs: Low-rank adaptation with extremely small number of parameters.arXiv preprint arXiv:2405.17604, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14506","last_updated":"2026-07-16T02:42:24Z","snapshot_observed_at":"2026-08-02T02:01:47.032587Z","submitted_at":"2026-07-16T02:42:24Z","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T02:01:48.319847Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2607.14506"},"observation_digest":"sha256:c0fa3f972c51d445b835e782eab191abd055eba85489d001a6ab136cf210df0d","observation_id":"6aa1f6c3-3c52-4278-a1c6-b896511050f1","resolution":{"observed_at":"2026-08-02T02:01:48.319847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17604","snapshot_observed_at":"2026-08-02T09:51:03.828809Z","title":"arXiv preprint arXiv:2405.17604 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16252","last_updated":"2026-06-27T03:25:36Z","snapshot_observed_at":"2026-08-08T02:31:05.095460Z","submitted_at":"2026-06-27T03:25:36Z","title":"SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling","version":1},"reference_index":240,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.828809Z"},"links":{"cited_paper":"/paper/2405.17604","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:e1c22df9f8526e2e2819d632038d0b6a44eba8c9f24891edf8f5b1ebec0e6f2f","observation_id":"5a4d4070-8823-4727-9e83-952b02dcbe4a","resolution":{"observed_at":"2026-08-02T09:51:03.828809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.17604/citation-record","integrity":"/paper/2405.17604/integrity","json":"/paper/2405.17604/citation-record.json","paper":"/paper/2405.17604"},"outbound":[],"paper":{"arxiv_id":"2405.17604","last_updated":"2025-08-19T19:14:56Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:20:52.408832Z","submitted_at":"2024-05-27T19:07:13Z","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters"},"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 18 inbound Pith citation observations for arXiv:2405.17604."}