{"as_of":"2026-08-11T15:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:944f57e8c42bbc36aca084bb1f2741e75aba7ebae6e29c50ca9ed2f395c4dd87","coverage":[{"denominator":297,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T09:51:03.512451Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.16252/citation-record","integrity":"/paper/2607.16252/integrity","json":"/paper/2607.16252/citation-record.json","paper":"/paper/2607.16252"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:02.560233Z","title":"2019 , eprint=","venue":null,"work_id":null,"year":2019},"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":1,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:02.560233Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:0fcf820c975f87371ea747140b742eb861e9f380966a42a00b46cf1e18c66166","observation_id":"d9ef8802-a4a4-44af-a78d-f44ac1900646","resolution":{"observed_at":"2026-08-02T09:51:02.560233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:02.717261Z","title":"2026 , url=","venue":null,"work_id":null,"year":2026},"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":2,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:02.717261Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:bfd024d07cbb90b5554efa14a0c19ed6c7b1b04adbe7b2463ef8b8a722d08b72","observation_id":"0afc4433-30f0-416c-8003-5a03276d2ddf","resolution":{"observed_at":"2026-08-02T09:51:02.717261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:02.827061Z","title":"Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=","venue":null,"work_id":null,"year":2025},"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":3,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:02.827061Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:053fdb9d57cd0bf777eb5def77e61205998b2b390e679136cd412b012d4885b8","observation_id":"a5969135-e022-4913-b4d0-e2fc5223de4b","resolution":{"observed_at":"2026-08-02T09:51:02.827061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:02.943304Z","title":"Advances in Neural Information Processing Systems , 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":4,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:02.943304Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:406b682ff211a0ba807f51cef7f989e366a85e5975c9aa4ab9334841f7ee68aa","observation_id":"6369c329-c20a-40f0-9f34-432b0307474a","resolution":{"observed_at":"2026-08-02T09:51:02.943304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.095751Z","title":"2026 , eprint=","venue":null,"work_id":null,"year":2026},"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":5,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.095751Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:eced55ad6daa6fda22a7ad8475a89f2bbd797cefa7f7a448903cf7be78850df3","observation_id":"616baf56-9ecd-40ff-ba69-93b5190571b7","resolution":{"observed_at":"2026-08-02T09:51:03.095751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.201991Z","title":"Advances in Neural Information Processing Systems , volume=","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":6,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.201991Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:d082aa54709092ace3a9624118eb3cf3c248170e69ad9e21d6395a6b41e9b976","observation_id":"72b03147-a13d-4613-9157-5549f4ea0688","resolution":{"observed_at":"2026-08-02T09:51:03.201991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.12284","last_updated":"2024-05-03T17:36:07Z","snapshot_observed_at":"2026-08-02T15:00:50.388422Z","submitted_at":"2023-09-21T17:45:42Z","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.12284","snapshot_observed_at":"2026-08-02T09:51:03.291898Z","title":"arXiv preprint arXiv:2309.12284 , 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":7,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.291898Z"},"links":{"cited_paper":"/paper/2309.12284","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:0969cd61bdf6636006eb5bd1c1fdeb9e5ef877dd4f803cc57ca1b24800cf8c8f","observation_id":"c17149ee-5b6b-4ec3-ab29-7cea4b5909da","resolution":{"observed_at":"2026-08-02T09:51:03.291898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03732","last_updated":"2023-11-28T03:23:20Z","snapshot_observed_at":"2026-08-08T21:34:35.024914Z","submitted_at":"2023-11-28T03:23:20Z","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03732","snapshot_observed_at":"2026-08-02T09:51:03.298416Z","title":"arXiv preprint arXiv:2312.03732 , 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":9,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.298416Z"},"links":{"cited_paper":"/paper/2312.03732","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:c99f9db56af020ee6236eb4f38d4a8db11a5725c8448e472b60434aff2ae16d4","observation_id":"cb3af98a-dfae-4b11-87e4-355f820cf599","resolution":{"observed_at":"2026-08-02T09:51:03.298416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.301253Z","title":"2025 , eprint=","venue":null,"work_id":null,"year":2025},"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":10,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.301253Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:d27aeb9b6aead23a271e36a932eab186e145c1be6640c1416d81d109e4f4a5e6","observation_id":"f0f4eeea-383a-4b3e-a6de-3434661713e6","resolution":{"observed_at":"2026-08-02T09:51:03.301253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.303515Z","title":", author=","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":11,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.303515Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:ad2871c3f30d9854016cd1cac2ce96a5fe5cc5991558b14ac038cfb603e547f5","observation_id":"546db04d-de14-46ae-aee7-37c5dca399a3","resolution":{"observed_at":"2026-08-02T09:51:03.303515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-07-06T05:27:13.416519Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-02T09:51:03.306056Z","title":"arXiv preprint arXiv:1701.06538 , 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":12,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.306056Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:2a6c6865ef6b71a9251809c586b14c061a7d1f29536e79a2a1658684222bed50","observation_id":"991d1dd0-3791-41b2-9824-4807c38e7d96","resolution":{"observed_at":"2026-08-02T09:51:03.306056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.308589Z","title":"Advances in neural information processing systems , volume=","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":13,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.308589Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:29140e934f7de4737445f41cea8d354b77ae393ad8504c3dea3fb17a9244da3c","observation_id":"10c0d7ab-c482-4555-8c71-830b105e4ac8","resolution":{"observed_at":"2026-08-02T09:51:03.308589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.311146Z","title":"Advances in neural information processing systems , volume=","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":14,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.311146Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:a769fc6d27d890774d33dce1f48a4b23cff55690da72b2388824214f7af98acf","observation_id":"a242b305-c188-4546-af96-d5df9e061233","resolution":{"observed_at":"2026-08-02T09:51:03.311146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.313475Z","title":null,"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":15,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.313475Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:a30b82da556e080dfb8c030e93ef7857b694de4b777e92f4112ea1711e46f8a7","observation_id":"7e876d0f-560c-491c-88ef-cf99c50b70c8","resolution":{"observed_at":"2026-08-02T09:51:03.313475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.12409","last_updated":"2022-04-22T18:20:48Z","snapshot_observed_at":"2026-08-07T11:26:24.970964Z","submitted_at":"2021-08-27T17:35:06Z","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.12409","snapshot_observed_at":"2026-08-02T09:51:03.315612Z","title":"arXiv preprint arXiv:2108.12409 , 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":16,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.315612Z"},"links":{"cited_paper":"/paper/2108.12409","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:eeb71732f1cb2e302b7ab21f13888685b815470a81d5a0ea306fe7dc8f9be9db","observation_id":"3faced1d-f47f-402e-aba8-224bac0f280b","resolution":{"observed_at":"2026-08-02T09:51:03.315612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.318031Z","title":"2016 , eprint=","venue":null,"work_id":null,"year":2016},"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":17,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.318031Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:a5398146c9380f10d8fab0ce390e021816f407c6581ec40f49e6594517e71a5a","observation_id":"29334eb7-2d8f-4db4-8028-7ac2e4138a4e","resolution":{"observed_at":"2026-08-02T09:51:03.318031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.320552Z","title":null,"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":18,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.320552Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:69db2690bb55883f584a93c02b8e2048afaf2dbddd97c5213eea9724b558b25f","observation_id":"890be5ae-b3d1-49c7-88a6-1a256b4fd5d6","resolution":{"observed_at":"2026-08-02T09:51:03.320552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.322660Z","title":"OpenAI blog , volume=","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":19,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.322660Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:74373286865eaa296302b6c9b32bc16f6225769913bf0ca8bf8b531921fb528d","observation_id":"8035ba1a-0b62-46c3-b16a-24c0efd96319","resolution":{"observed_at":"2026-08-02T09:51:03.322660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.324972Z","title":null,"venue":null,"work_id":null,"year":2025},"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":20,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.324972Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:fe76fbf823cacbd9fd6372e7bd1fcfcbbf9507c06e9483e468687fec3e832fc4","observation_id":"00783083-1192-4192-bd60-1c859aec2b00","resolution":{"observed_at":"2026-08-02T09:51:03.324972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-08-02T09:51:03.327206Z","title":"arXiv preprint arXiv:2307.01952 , 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":21,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.327206Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:2dc5951c6ce340705a7df46f0202062db0a79cb2a8d8ea2e7bbb5d7278a058e4","observation_id":"9e58044d-cfeb-49a5-b2c0-79d2cdae3d82","resolution":{"observed_at":"2026-08-02T09:51:03.327206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.07143","last_updated":"2024-07-13T14:20:07Z","snapshot_observed_at":"2026-08-09T21:43:00.189321Z","submitted_at":"2022-12-14T10:24:50Z","title":"Reproducible scaling laws for contrastive language-image learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.07143","snapshot_observed_at":"2026-08-02T09:51:03.329640Z","title":"arXiv preprint arXiv:2212.07143 , 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":22,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.329640Z"},"links":{"cited_paper":"/paper/2212.07143","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:e203b2f9f6f7827587d7fb3981446171feecdad63623f28f1578a2932a8bebea","observation_id":"ee5a565a-6ed5-4274-8286-a1485c55bbb5","resolution":{"observed_at":"2026-08-02T09:51:03.329640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.332370Z","title":null,"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":23,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.332370Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:10a44ad83e4128701fd5c42e042492b17c25dea831263a7022270aceae1c843d","observation_id":"b0cff2ff-0f7d-4625-93ac-b3ae1d232be1","resolution":{"observed_at":"2026-08-02T09:51:03.332370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.334527Z","title":"Advances in neural information processing systems , volume=","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":24,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.334527Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:32dead8cf629ccd81e3bac7ce4777e93c5f8d28d5f091efc5124f4124714f6b6","observation_id":"a3ad1415-fe6d-4ee0-93d4-53d5239bc3d6","resolution":{"observed_at":"2026-08-02T09:51:03.334527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.336520Z","title":"Advances in neural information processing systems , volume=","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":25,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.336520Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:8aafdac1c27e3a334f838e46d7ace09fc49ea8daf103c8edabb5e8b5a5759a70","observation_id":"66da2159-0cde-40d9-a51e-03b56728985a","resolution":{"observed_at":"2026-08-02T09:51:03.336520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05015","last_updated":"2023-10-11T01:46:35Z","snapshot_observed_at":"2026-08-10T09:36:29.224880Z","submitted_at":"2023-10-08T05:16:28Z","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05015","snapshot_observed_at":"2026-08-02T09:51:03.338653Z","title":"arXiv preprint arXiv:2310.05015 , 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":26,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.338653Z"},"links":{"cited_paper":"/paper/2310.05015","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:259e973b609994da08c5cbf5c5ce1dc73dfadd92cbc751d407b783cacbc3564e","observation_id":"2d2f3485-a7b0-4bc9-bdb3-d0a059dbdee0","resolution":{"observed_at":"2026-08-02T09:51:03.338653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05254","last_updated":"2024-05-09T14:12:45Z","snapshot_observed_at":"2026-08-04T14:59:09.585356Z","submitted_at":"2024-05-08T17:57:39Z","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05254","snapshot_observed_at":"2026-08-02T09:51:03.340861Z","title":"arXiv preprint arXiv:2405.05254 , 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":27,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.340861Z"},"links":{"cited_paper":"/paper/2405.05254","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:6e7f3a18e71d0f0f424fc6a617869f4bfd021c4d72d3be73ff8d809353a75565","observation_id":"72683e7f-bb28-4eb5-b906-475de5930321","resolution":{"observed_at":"2026-08-02T09:51:03.340861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12981","last_updated":"2024-05-21T17:59:29Z","snapshot_observed_at":"2026-08-02T00:33:35.724101Z","submitted_at":"2024-05-21T17:59:29Z","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.12981","snapshot_observed_at":"2026-08-02T09:51:03.342951Z","title":"arXiv preprint arXiv:2405.12981 , 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":28,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.342951Z"},"links":{"cited_paper":"/paper/2405.12981","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:52acb42d7faa1363a6a9b8f81d5f7eb1e0b44027d277c5aff10e8a89126c93c1","observation_id":"347be885-1d25-4ac8-91f9-9c10bb0815f5","resolution":{"observed_at":"2026-08-02T09:51:03.342951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14366","last_updated":"2024-09-07T02:52:29Z","snapshot_observed_at":"2026-08-04T12:08:53.387357Z","submitted_at":"2024-05-23T09:43:52Z","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14366","snapshot_observed_at":"2026-08-02T09:51:03.345462Z","title":"arXiv preprint arXiv:2405.14366 , 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":29,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.345462Z"},"links":{"cited_paper":"/paper/2405.14366","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:750919177fc12836b00809f7bb5e70ed63c63b49a65d8ae5af5589f3303d73cc","observation_id":"cb39eb81-8397-4bdb-985c-5218d34daf3d","resolution":{"observed_at":"2026-08-02T09:51:03.345462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09297","last_updated":"2024-10-15T08:45:18Z","snapshot_observed_at":"2026-08-10T21:50:56.589747Z","submitted_at":"2024-06-13T16:33:44Z","title":"MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09297","snapshot_observed_at":"2026-08-02T09:51:03.347596Z","title":"arXiv preprint arXiv:2406.09297 , 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":30,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.347596Z"},"links":{"cited_paper":"/paper/2406.09297","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:297e51e67c38aef39b79a849e0b75344d9bea4f0a7116d507e268be519fe8082","observation_id":"b9024bee-7640-4399-b436-2a17ca8b25cd","resolution":{"observed_at":"2026-08-02T09:51:03.347596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-07T08:38:54.025062Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-02T09:51:03.350732Z","title":"arXiv preprint arXiv:2210.17323 , 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":31,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.350732Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:49c71bf16a6dc0282196dd64f84535989186c6d5228f1bcbc58bb76bd5b3fd67","observation_id":"9f3d7527-e1e0-4084-95ca-aaea21a1ea5f","resolution":{"observed_at":"2026-08-02T09:51:03.350732Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.353112Z","title":"International Conference on Machine Learning , pages=","venue":null,"work_id":null,"year":2023},"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":32,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.353112Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:1b38518838128d4c756ec493eb4ff8a8d1bf13e68769cbf52665931cac64f7aa","observation_id":"1d3639a3-b06f-4002-8591-a382a0826c91","resolution":{"observed_at":"2026-08-02T09:51:03.353112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.355111Z","title":"int8 (): 8-bit matrix multiplication for transformers at scale , author=","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":33,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.355111Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:924004dfa16cdeb0ab6a99c83e0d6dcf57ecdf9080911b95cff1ee9ee89a8d4e","observation_id":"3fc216d1-5817-4ab9-855e-5037784662ce","resolution":{"observed_at":"2026-08-02T09:51:03.355111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02750","last_updated":"2024-07-25T09:16:05Z","snapshot_observed_at":"2026-07-06T17:25:18.238343Z","submitted_at":"2024-02-05T06:06:47Z","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.02750","snapshot_observed_at":"2026-08-02T09:51:03.357469Z","title":"arXiv preprint arXiv:2402.02750 , 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":34,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.357469Z"},"links":{"cited_paper":"/paper/2402.02750","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:de5099c66ed7c0ff7a4c14675f81b77eca6aaaae058165cd8b8006de3bb394e8","observation_id":"d3ec6394-ca44-4a4f-af4e-4d957e94e0c4","resolution":{"observed_at":"2026-08-02T09:51:03.357469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.18079","last_updated":"2025-05-28T18:58:29Z","snapshot_observed_at":"2026-08-09T08:05:16.511956Z","submitted_at":"2024-01-31T18:58:14Z","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.18079","snapshot_observed_at":"2026-08-02T09:51:03.359796Z","title":"arXiv preprint arXiv:2401.18079 , 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":35,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.359796Z"},"links":{"cited_paper":"/paper/2401.18079","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:f20b3b83c4e4421c818a9a0a4e25b4bed87a61b7409b2ad8e8295d7040188dcc","observation_id":"27aab2f4-0d4c-4593-9b3e-55914237ada8","resolution":{"observed_at":"2026-08-02T09:51:03.359796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.362189Z","title":"International conference on machine learning , pages=","venue":null,"work_id":null,"year":2020},"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":36,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.362189Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:60d74089347f9cd470b08db6bac4099dcb00dc159fe7158dad627edcc7d889fa","observation_id":"4c81d019-a7b1-47be-81d2-0ddf2e63ddfd","resolution":{"observed_at":"2026-08-02T09:51:03.362189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04768","last_updated":"2020-06-14T08:15:54Z","snapshot_observed_at":"2026-07-06T09:27:03.809621Z","submitted_at":"2020-06-08T17:37:52Z","title":"Linformer: Self-Attention with Linear Complexity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04768","snapshot_observed_at":"2026-08-02T09:51:03.364603Z","title":"arXiv preprint arXiv:2006.04768 , year=","venue":null,"work_id":null,"year":2006},"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":37,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.364603Z"},"links":{"cited_paper":"/paper/2006.04768","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:469eefe0af2ea93e591cb5c404f4b8b46476ae709484b6a1f0db5da9968971a5","observation_id":"1038e29d-fcaa-4eee-861b-4f8dea734056","resolution":{"observed_at":"2026-08-02T09:51:03.364603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13048","last_updated":"2023-12-11T03:58:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-22T13:57:41Z","title":"RWKV: Reinventing RNNs for the Transformer Era","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13048","snapshot_observed_at":"2026-08-02T09:51:03.367004Z","title":"arXiv preprint arXiv:2305.13048 , 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":38,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.367004Z"},"links":{"cited_paper":"/paper/2305.13048","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:c7e04a3ad3040becc6ff500202c0431b729a68e273d971e2c5a73b9b5b6b1baa","observation_id":"1d048c8e-0b2b-49c7-ae7c-0b878c64acb7","resolution":{"observed_at":"2026-08-02T09:51:03.367004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-02T09:51:03.369467Z","title":"arXiv preprint arXiv:2312.00752 , 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":39,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.369467Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:8221783479591cbf093bd6062bf6168bb437029989a75e781266f3bffce662ed","observation_id":"ca2f9ecb-7c29-4278-800a-118742e0c4e9","resolution":{"observed_at":"2026-08-02T09:51:03.369467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19427","last_updated":"2024-02-29T18:24:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-29T18:24:46Z","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19427","snapshot_observed_at":"2026-08-02T09:51:03.371636Z","title":"arXiv preprint arXiv:2402.19427 , 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":40,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.371636Z"},"links":{"cited_paper":"/paper/2402.19427","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:28cb32f65129ee051186dc6e75ab7c5d261369c5f54cf06af2739a014ed7b852","observation_id":"c5acb4ad-c3fa-4129-b437-9835a7216160","resolution":{"observed_at":"2026-08-02T09:51:03.371636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14057","last_updated":"2024-07-19T06:34:45Z","snapshot_observed_at":"2026-07-06T18:48:49.546589Z","submitted_at":"2024-07-19T06:34:45Z","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14057","snapshot_observed_at":"2026-08-02T09:51:03.373817Z","title":"arXiv preprint arXiv:2407.14057 , 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":41,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.373817Z"},"links":{"cited_paper":"/paper/2407.14057","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:3d73f13bf3b2a6a2a6ac5cc5d6846915b66551ded1540bd24d4f909d70d3e1d0","observation_id":"421cfbb6-0894-4c99-9f39-701ab756934d","resolution":{"observed_at":"2026-08-02T09:51:03.373817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.20485","last_updated":"2024-07-31T02:02:40Z","snapshot_observed_at":"2026-08-08T00:57:30.556972Z","submitted_at":"2024-07-30T01:13:42Z","title":"A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.20485","snapshot_observed_at":"2026-08-02T09:51:03.376221Z","title":"arXiv preprint arXiv:2407.20485 , 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":42,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.376221Z"},"links":{"cited_paper":"/paper/2407.20485","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:4387854f8078bf7725d9ff993956a912feda81365de07f18e247eb39621b1026","observation_id":"f59c0168-eb65-4900-b7db-bf522100379c","resolution":{"observed_at":"2026-08-02T09:51:03.376221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14469","last_updated":"2024-06-17T03:01:58Z","snapshot_observed_at":"2026-08-07T22:57:56.263839Z","submitted_at":"2024-04-22T17:42:58Z","title":"SnapKV: LLM Knows What You are Looking for Before Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14469","snapshot_observed_at":"2026-08-02T09:51:03.378531Z","title":"arXiv preprint arXiv:2404.14469 , 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":43,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.378531Z"},"links":{"cited_paper":"/paper/2404.14469","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:efc681c422141b35b98e3591f3fd9197f271aaa26c42d5c3a372afabf2d63aae","observation_id":"11dbdad8-5b6d-4fe9-9c3b-880bcd5fb01c","resolution":{"observed_at":"2026-08-02T09:51:03.378531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.381229Z","title":"Advances in Neural Information Processing Systems , volume=","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":44,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.381229Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:64c058029a72fc9736d928441feea42b8cf1674c6c1bb433920ebc2c4e6dd827","observation_id":"1f056050-87c1-4250-87af-e51b66e0326d","resolution":{"observed_at":"2026-08-02T09:51:03.381229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.02150","last_updated":"2019-11-06T00:19:05Z","snapshot_observed_at":"2026-07-06T08:35:01.386074Z","submitted_at":"2019-11-06T00:19:05Z","title":"Fast Transformer Decoding: One Write-Head is All You Need","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.02150","snapshot_observed_at":"2026-08-02T09:51:03.383201Z","title":"arXiv preprint arXiv:1911.02150 , year=","venue":null,"work_id":null,"year":1911},"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":45,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.383201Z"},"links":{"cited_paper":"/paper/1911.02150","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:efaafd4403a01d15d0d7f105c1e119abffdb396c8679bd622d5c4701d46bb404","observation_id":"ef730e95-8480-4c56-acde-e42cbae0321e","resolution":{"observed_at":"2026-08-02T09:51:03.383201Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04434","last_updated":"2024-06-19T06:04:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-05-07T15:56:43Z","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.04434","snapshot_observed_at":"2026-08-02T09:51:03.385980Z","title":"arXiv preprint arXiv:2405.04434 , 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":46,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.385980Z"},"links":{"cited_paper":"/paper/2405.04434","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:14ae470703e04ffedd91437ed6843125abfba58d60be899641c71a3293588eac","observation_id":"5d02d924-b0ff-4237-97e7-b2ddffeab72f","resolution":{"observed_at":"2026-08-02T09:51:03.385980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07056","last_updated":"2024-06-11T08:37:33Z","snapshot_observed_at":"2026-08-10T10:11:23.551415Z","submitted_at":"2024-06-11T08:37:33Z","title":"Effectively Compress KV Heads for LLM","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07056","snapshot_observed_at":"2026-08-02T09:51:03.388419Z","title":"arXiv preprint arXiv:2406.07056 , 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":47,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.388419Z"},"links":{"cited_paper":"/paper/2406.07056","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:c307fd5439eb7d5de6d83d73616f28fea32ec7e2b3dd4102671fd0e45510c52f","observation_id":"906ecff6-6869-4d8a-9b1c-114a7c9ddbb5","resolution":{"observed_at":"2026-08-02T09:51:03.388419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15024","last_updated":"2024-02-09T17:59:40Z","snapshot_observed_at":"2026-07-06T17:21:01.918787Z","submitted_at":"2024-01-26T17:35:45Z","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15024","snapshot_observed_at":"2026-08-02T09:51:03.390763Z","title":"arXiv preprint arXiv:2401.15024 , 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":48,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.390763Z"},"links":{"cited_paper":"/paper/2401.15024","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:e5fc4e143ede87e43617c89c6cd7f50a410809b1dc815312454ad7dba6c3cca4","observation_id":"fefb9260-6692-4b72-8306-f7ccf2912d03","resolution":{"observed_at":"2026-08-02T09:51:03.390763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06694","last_updated":"2024-04-11T01:18:06Z","snapshot_observed_at":"2026-08-08T20:21:38.269492Z","submitted_at":"2023-10-10T15:13:30Z","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06694","snapshot_observed_at":"2026-08-02T09:51:03.393031Z","title":"arXiv preprint arXiv:2310.06694 , 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":49,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.393031Z"},"links":{"cited_paper":"/paper/2310.06694","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:5f89d4f010466fb26da6838cb806a48868df4a7ff532fbb70e127da81da86e14","observation_id":"c6359858-0342-4451-b509-8d88feff6ffb","resolution":{"observed_at":"2026-08-02T09:51:03.393031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11695","last_updated":"2024-05-06T17:47:01Z","snapshot_observed_at":"2026-07-06T15:44:42.776459Z","submitted_at":"2023-06-20T17:18:20Z","title":"A Simple and Effective Pruning Approach for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11695","snapshot_observed_at":"2026-08-02T09:51:03.395317Z","title":"arXiv preprint arXiv:2306.11695 , 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":50,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.395317Z"},"links":{"cited_paper":"/paper/2306.11695","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:032b05c26709d6a7dc325e7fb8669f7bb9ec421c4531e8740abe6ce891e84043","observation_id":"ffb617f8-12f7-4883-a1d5-cd965a4429b7","resolution":{"observed_at":"2026-08-02T09:51:03.395317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.397876Z","title":"arXiv preprint arXiv:2106.10199 , 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":51,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.397876Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:26c18e11a4e89dbe025dc0f8b4457fbd21f4eda3397a5e07cd0bdb7773c18e62","observation_id":"410772a9-49a7-4a89-9f02-ef95340a6da3","resolution":{"observed_at":"2026-08-02T09:51:03.397876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16597","last_updated":"2023-05-26T03:01:07Z","snapshot_observed_at":"2026-08-05T13:15:12.433866Z","submitted_at":"2023-05-26T03:01:07Z","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16597","snapshot_observed_at":"2026-08-02T09:51:03.399956Z","title":"arXiv preprint arXiv:2305.16597 , 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":52,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.399956Z"},"links":{"cited_paper":"/paper/2305.16597","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:ec53b28e8099e2fa3dba7ce1823ea26fb6e9a9ba4ce97acdfde447c28cf0c2ba","observation_id":"48728fb9-b584-4d8f-9f85-12ee20ccf587","resolution":{"observed_at":"2026-08-02T09:51:03.399956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.12406","last_updated":"2020-10-11T11:52:08Z","snapshot_observed_at":"2026-08-08T22:25:43.361051Z","submitted_at":"2020-04-26T15:03:47Z","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.12406","snapshot_observed_at":"2026-08-02T09:51:03.402370Z","title":"arXiv preprint arXiv:2004.12406 , year=","venue":null,"work_id":null,"year":2004},"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":53,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.402370Z"},"links":{"cited_paper":"/paper/2004.12406","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:dd8f2d82974c75d8e6c4ca09df68af84417d860a5fcc4f8981088dc0e8e2e9c6","observation_id":"5e2bfdf3-9b8f-47a9-a323-e5c9f6eb0b44","resolution":{"observed_at":"2026-08-02T09:51:03.402370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.404627Z","title":"Advances in Neural Information Processing Systems , volume=","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":54,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.404627Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:647ef4f80a7c42845458c836947150ea5a4acdccc9c1252f5d80e54d60cfb217","observation_id":"68004874-17e8-4969-8273-d22c5d5492f3","resolution":{"observed_at":"2026-08-02T09:51:03.404627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07560","last_updated":"2023-02-09T10:54:10Z","snapshot_observed_at":"2026-07-06T11:57:58.353688Z","submitted_at":"2021-10-14T17:27:29Z","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07560","snapshot_observed_at":"2026-08-02T09:51:03.406704Z","title":"arXiv preprint arXiv:2110.07560 , 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":55,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.406704Z"},"links":{"cited_paper":"/paper/2110.07560","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:2988859535214fbcf3b2383003cbe016f6d810f1578cc097d3e88ea876a267e0","observation_id":"feec5860-dd8a-47b8-a602-5060ff3262d1","resolution":{"observed_at":"2026-08-02T09:51:03.406704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05687","last_updated":"2021-09-13T03:39:52Z","snapshot_observed_at":"2026-08-05T01:06:28.807438Z","submitted_at":"2021-09-13T03:39:52Z","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05687","snapshot_observed_at":"2026-08-02T09:51:03.409186Z","title":"arXiv preprint arXiv:2109.05687 , 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":56,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.409186Z"},"links":{"cited_paper":"/paper/2109.05687","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:2ef0394817de7bdacdfa948b7aff150d76da53413d509e734a4133eaf0979888","observation_id":"2177b909-a4b4-4057-8ff7-9cd25399783e","resolution":{"observed_at":"2026-08-02T09:51:03.409186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.07463","last_updated":"2021-06-09T14:39:17Z","snapshot_observed_at":"2026-08-10T10:06:48.397353Z","submitted_at":"2020-12-14T12:34:01Z","title":"Parameter-Efficient Transfer Learning with Diff Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.07463","snapshot_observed_at":"2026-08-02T09:51:03.411612Z","title":"arXiv preprint arXiv:2012.07463 , year=","venue":null,"work_id":null,"year":2012},"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":57,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.411612Z"},"links":{"cited_paper":"/paper/2012.07463","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:3e03aeb976eb91b288dc7ef35de2e25c66703f4427267bed08b2abf7c28e9f93","observation_id":"67e534fd-5bfc-4317-b939-9a68970cc497","resolution":{"observed_at":"2026-08-02T09:51:03.411612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.414064Z","title":"Proceedings of the AAAI Conference on Artificial Intelligence , volume=","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":58,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.414064Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:e196652fd8384b2b8a044c3e0d8bae7801ec6205e2f1080019a9088c99b3bee0","observation_id":"20ed5d6b-4696-4bdc-8a75-73a0595c9006","resolution":{"observed_at":"2026-08-02T09:51:03.414064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00121","last_updated":"2021-06-02T13:13:01Z","snapshot_observed_at":"2026-08-10T06:13:20.678193Z","submitted_at":"2021-01-01T00:41:03Z","title":"WARP: Word-level Adversarial ReProgramming","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00121","snapshot_observed_at":"2026-08-02T09:51:03.416138Z","title":"arXiv preprint arXiv:2101.00121 , 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":59,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.416138Z"},"links":{"cited_paper":"/paper/2101.00121","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:c6d62a28a91ad4272ad0cc4ddeb4fbcb62df6dbd14a5431d6ce748648990791d","observation_id":"9c098878-74d2-4fcc-9c87-0cb5d478f839","resolution":{"observed_at":"2026-08-02T09:51:03.416138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-07-06T10:29:18.734092Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-02T09:51:03.418653Z","title":"arXiv preprint arXiv:2101.00190 , 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":60,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.418653Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:e51c2b82c5ca7e981609972eed3ef51fb501f97ee1d293e83a7152018500a53e","observation_id":"5d90199a-bfd5-4e0a-96be-5c9cfee76f11","resolution":{"observed_at":"2026-08-02T09:51:03.418653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.421240Z","title":"AI Open , 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":61,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.421240Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:b785742ebab6ab0c6690799482da70bc2013a900e99c96bf56935cf44e543949","observation_id":"315fd48a-15a8-4f6a-896b-d06d6415075c","resolution":{"observed_at":"2026-08-02T09:51:03.421240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07904","last_updated":"2022-03-16T18:52:36Z","snapshot_observed_at":"2026-08-10T08:11:24.396939Z","submitted_at":"2021-10-15T07:35:58Z","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07904","snapshot_observed_at":"2026-08-02T09:51:03.423549Z","title":"arXiv preprint arXiv:2110.07904 , 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":62,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.423549Z"},"links":{"cited_paper":"/paper/2110.07904","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:700b5f7ff0f8369cfafd982a6c86f5b9b30cc68ed3adb7d1202ceea8e94cc643","observation_id":"93b5082e-d193-4aa9-90f9-b404adc04ab0","resolution":{"observed_at":"2026-08-02T09:51:03.423549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11961","last_updated":"2022-12-01T18:31:43Z","snapshot_observed_at":"2026-08-08T16:04:20.220955Z","submitted_at":"2022-05-24T10:48:33Z","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11961","snapshot_observed_at":"2026-08-02T09:51:03.426216Z","title":"arXiv preprint arXiv:2205.11961 , 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":63,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.426216Z"},"links":{"cited_paper":"/paper/2205.11961","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:6b6207e4428cf9dfa80642503a2e4eedecfc961301018de360c83167faded214","observation_id":"f4b12e27-e998-41c4-82d2-bbfd5a2f11f5","resolution":{"observed_at":"2026-08-02T09:51:03.426216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02861","last_updated":"2023-03-06T03:25:59Z","snapshot_observed_at":"2026-08-11T13:56:42.291349Z","submitted_at":"2023-03-06T03:25:59Z","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02861","snapshot_observed_at":"2026-08-02T09:51:03.428540Z","title":"arXiv preprint arXiv:2303.02861 , 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":64,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.428540Z"},"links":{"cited_paper":"/paper/2303.02861","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:5d32aede91139bb6b728dbd2324b8f0b1193a1f8989260f20cab47b5edbfbd5d","observation_id":"2ffbfd06-bb48-48ce-8b67-07008e7f015a","resolution":{"observed_at":"2026-08-02T09:51:03.428540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.431485Z","title":"Advances in Neural Information Processing Systems , volume=","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":65,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.431485Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:bdfcbeab7da1e440ea30630094cd492d731aff4670d11e93bc136c0ef0d1aac8","observation_id":"c770d1b2-70e8-40d4-90cd-685091a947ea","resolution":{"observed_at":"2026-08-02T09:51:03.431485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06243","last_updated":"2024-04-28T20:05:02Z","snapshot_observed_at":"2026-08-11T09:38:23.064157Z","submitted_at":"2023-11-10T18:59:54Z","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06243","snapshot_observed_at":"2026-08-02T09:51:03.433601Z","title":"arXiv preprint arXiv:2311.06243 , 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":66,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.433601Z"},"links":{"cited_paper":"/paper/2311.06243","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:0df1692b062ae76e6355815ca1e07eb183d44dfb142e797d865b63b358e927b0","observation_id":"b8e5371a-9ce3-4f82-ae38-1b7a14c5e7b6","resolution":{"observed_at":"2026-08-02T09:51:03.433601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17484","last_updated":"2024-11-15T08:02:03Z","snapshot_observed_at":"2026-08-11T09:35:32.670358Z","submitted_at":"2024-05-24T16:18:16Z","title":"Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17484","snapshot_observed_at":"2026-08-02T09:51:03.435895Z","title":"arXiv preprint arXiv:2405.17484 , 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":67,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.435895Z"},"links":{"cited_paper":"/paper/2405.17484","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:6af3c97918af23e164e98ba0ae9aa97441a34aee89f0ffbefba11d397495479c","observation_id":"e45ec2d2-c888-485d-bc78-1829020a2c26","resolution":{"observed_at":"2026-08-02T09:51:03.435895Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13245","last_updated":"2023-12-23T17:55:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-22T17:16:38Z","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13245","snapshot_observed_at":"2026-08-02T09:51:03.438377Z","title":"arXiv preprint arXiv:2305.13245 , 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":68,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.438377Z"},"links":{"cited_paper":"/paper/2305.13245","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:953440ece6efeb22658426b4966b27f6e62ecde548f1abbb1467090af7f8b8a0","observation_id":"2d986e66-4542-45a3-83f7-742ace5a3f3d","resolution":{"observed_at":"2026-08-02T09:51:03.438377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.440728Z","title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=","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":69,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.440728Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:9ed0e65ff997fc37a47f963054b1c436834da735f97e8279ce7f60039a357aad","observation_id":"bc9c96e0-93d4-4930-90dc-1c127fbf8c83","resolution":{"observed_at":"2026-08-02T09:51:03.440728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.442781Z","title":null,"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":70,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.442781Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:ae3a46dd7d46d03bfc60db31943ae032711510d51cea83c0b30e9392534dde66","observation_id":"37085926-47c5-4c40-a0bb-e73c4243ccfa","resolution":{"observed_at":"2026-08-02T09:51:03.442781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.445058Z","title":"Findings of ACL 2022 , pages=","venue":null,"work_id":null,"year":2022},"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":71,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.445058Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:4ec50c26498875a461a7ad0a9e57813435fb77ee7a1c99713d97841bbb3633a3","observation_id":"393a159e-4874-4446-ac73-dcff704a1637","resolution":{"observed_at":"2026-08-02T09:51:03.445058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11250","last_updated":"2024-01-01T03:43:41Z","snapshot_observed_at":"2026-08-06T13:53:33.999451Z","submitted_at":"2023-06-20T03:03:04Z","title":"InRank: Incremental Low-Rank Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11250","snapshot_observed_at":"2026-08-02T09:51:03.447212Z","title":"arXiv preprint arXiv:2306.11250 , 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":72,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.447212Z"},"links":{"cited_paper":"/paper/2306.11250","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:53126bb426b52b1b0749d6944db0e2d130d10b077a644c78681398bce52f0d37","observation_id":"206ecc20-c551-482a-88d3-e2b995244b00","resolution":{"observed_at":"2026-08-02T09:51:03.447212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.449631Z","title":"NeurIPS 2023 Workshop on Distribution Shifts: New Frontiers with Foundation Models , year=","venue":null,"work_id":null,"year":2023},"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":73,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.449631Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:7b40397f39022c4661c58c7a34304a2d8bb39d986bf459a72ec656e55c8b6783","observation_id":"df99ceb9-121c-471b-b298-6a8b90dd54be","resolution":{"observed_at":"2026-08-02T09:51:03.449631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00228","last_updated":"2024-04-03T07:15:05Z","snapshot_observed_at":"2026-08-11T01:32:02.605907Z","submitted_at":"2024-03-30T03:16:37Z","title":"InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00228","snapshot_observed_at":"2026-08-02T09:51:03.451799Z","title":"arXiv preprint arXiv:2404.00228 , 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":74,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.451799Z"},"links":{"cited_paper":"/paper/2404.00228","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:557f38c5e82820512e9ecdab644a5393c296285a4bb8c3da288275213366f2db","observation_id":"ee24cbef-c9ea-4adc-bd0d-1363318a25dc","resolution":{"observed_at":"2026-08-02T09:51:03.451799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11260","last_updated":"2024-02-17T12:25:31Z","snapshot_observed_at":"2026-07-06T17:31:33.340510Z","submitted_at":"2024-02-17T12:25:31Z","title":"MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11260","snapshot_observed_at":"2026-08-02T09:51:03.454276Z","title":"arXiv preprint arXiv:2402.11260 , 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":75,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.454276Z"},"links":{"cited_paper":"/paper/2402.11260","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:56740cd1354784a7470f7a75ed9b71dfc6d1cb1eaf8f101a9bc3d7dfd4b872f2","observation_id":"e689aed8-3166-4d44-bffe-c2b2249fa9fc","resolution":{"observed_at":"2026-08-02T09:51:03.454276Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12220","last_updated":"2024-12-06T23:18:31Z","snapshot_observed_at":"2026-08-11T03:43:11.598710Z","submitted_at":"2024-02-19T15:26:19Z","title":"Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12220","snapshot_observed_at":"2026-08-02T09:51:03.456655Z","title":"arXiv preprint arXiv:2402.12220 , 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":76,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.456655Z"},"links":{"cited_paper":"/paper/2402.12220","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:2f37d7c7623f12152526d979831b28033cc79827be84e8be160707386fb80f41","observation_id":"03776e9e-3188-4539-98cc-2ce1b3a58af0","resolution":{"observed_at":"2026-08-02T09:51:03.456655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.458984Z","title":"Proceedings of the national academy of sciences , volume=","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":77,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.458984Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:0bf7d65ddc07c6716423485109b780faf7cb9cffd894b70ea1ec2f54f3f76f64","observation_id":"b7e63196-a61d-4886-ae1d-9b7ae8fbfe40","resolution":{"observed_at":"2026-08-02T09:51:03.458984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.461052Z","title":"Proceedings of the European conference on computer vision , pages=","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":78,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.461052Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:33857bdfec09aec6659622654e6cd5a478d198059583fa1ff60c6d90b6d3ad16","observation_id":"085c1aa1-a536-4dce-bd42-31afa7390194","resolution":{"observed_at":"2026-08-02T09:51:03.461052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.463414Z","title":"Proceedings of Conference on Empirical Methods in Natural Language Processing , pages=","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":79,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.463414Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:d05a06503cb1009d45b14b51ebf08b268a9368441edccf3f699f05b64a73b678","observation_id":"aea45aab-6477-491e-b739-65c0d75e2251","resolution":{"observed_at":"2026-08-02T09:51:03.463414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.465541Z","title":"Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pages=","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":80,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.465541Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:6351b8f0038cd573672133f6e27cab71d6a937b098aff4978ef17e49989f1239","observation_id":"f959ba4d-d80a-4cca-bafc-941993a7e9fe","resolution":{"observed_at":"2026-08-02T09:51:03.465541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.467915Z","title":"Proceedings of Conference on Empirical Methods in Natural Language Processing , pages=","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":81,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.467915Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:6242a886818250417292dbfc4bcfcf761fad93798eda209aa51b17a409df2fff","observation_id":"755d33ea-fba2-44c0-9243-eca0878a85ed","resolution":{"observed_at":"2026-08-02T09:51:03.467915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.470015Z","title":"Advances in Neural Information Processing Systems , volume=","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":82,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.470015Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:049a4ed37d1c30053caeb644224bc51e27b5a01b16261a8e817b7f228f993c79","observation_id":"c258db95-4464-493d-ac06-934a175ada4f","resolution":{"observed_at":"2026-08-02T09:51:03.470015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.472282Z","title":"Proceedings of Conference on Empirical Methods in Natural Language Processing , pages=","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":83,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.472282Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:ef09cbd908e956e78cbd97a7d70a7e616df052e30849c535ce9c4c8e6de6f005","observation_id":"9bb83b94-7095-4ff2-b978-50c4c910d3f1","resolution":{"observed_at":"2026-08-02T09:51:03.472282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.474552Z","title":"Findings of the Association for Computational Linguistics: ACL 2022 , pages=","venue":null,"work_id":null,"year":2022},"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":84,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.474552Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:c827c30e7714142f195029f70e012c05b1008b32cab39f53450c35e53d0f3c60","observation_id":"058b9474-aa3c-4fe7-ad01-60d23c238744","resolution":{"observed_at":"2026-08-02T09:51:03.474552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.476602Z","title":"Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pages=","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":85,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.476602Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:398d4a2eafa1a65c5a9090dabd830d73de2d098c4bad81f093acee2e911f4038","observation_id":"f6c57eaf-90c2-466a-bb66-0cceab6af3c4","resolution":{"observed_at":"2026-08-02T09:51:03.476602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16767","last_updated":"2024-02-26T17:35:44Z","snapshot_observed_at":"2026-08-09T20:13:27.041003Z","submitted_at":"2024-02-26T17:35:44Z","title":"CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16767","snapshot_observed_at":"2026-08-02T09:51:03.478546Z","title":"arXiv preprint arXiv:2402.16767 , 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":86,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.478546Z"},"links":{"cited_paper":"/paper/2402.16767","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:fd6236910b65c0f9e8d63a3696c0eca1478f13cb12c7b3aa5df38f00f66d1b3c","observation_id":"793f8bcb-5721-4d62-bbb0-543914ad0d5e","resolution":{"observed_at":"2026-08-02T09:51:03.478546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.480924Z","title":"International Conference on Learning Representations , 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":87,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.480924Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:3c871f9c09a806f892ef3cc71c8ee6237cce76181e247d6087111e0e264e55be","observation_id":"d78a4d29-87aa-49c5-bf7b-ccd9027716ff","resolution":{"observed_at":"2026-08-02T09:51:03.480924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.482945Z","title":"International Conference on Learning Representations , 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":88,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.482945Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:eacc25144f04e9a177d47a09687de1fbf61520b2a9d356c97aca89bf8f9d118a","observation_id":"d5155497-f5ec-4fcc-b983-f82587205943","resolution":{"observed_at":"2026-08-02T09:51:03.482945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.484945Z","title":"Proceedings of Conference on Empirical Methods in Natural Language Processing , pages=","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":89,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.484945Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:1f9c57f1f47c52617eaae861a4b1b15afc7bf7ed71b8f21f95969a94d7ff3d53","observation_id":"28c03cfa-42b3-4889-a3dd-92615a8c5cf2","resolution":{"observed_at":"2026-08-02T09:51:03.484945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01244","last_updated":"2024-05-25T12:17:29Z","snapshot_observed_at":"2026-08-10T06:04:30.032752Z","submitted_at":"2024-03-02T16:11:23Z","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01244","snapshot_observed_at":"2026-08-02T09:51:03.487344Z","title":"arXiv preprint arXiv:2403.01244 , 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":90,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.487344Z"},"links":{"cited_paper":"/paper/2403.01244","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:b4b1b4a976646d41074f8faf715e56ef6fa1a777ed375e8c33317cfbc0152754","observation_id":"3b8f4f8d-df66-4b15-b85c-7489c7ae80cc","resolution":{"observed_at":"2026-08-02T09:51:03.487344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16789","last_updated":"2024-11-25T05:27:13Z","snapshot_observed_at":"2026-08-06T00:13:40.325158Z","submitted_at":"2024-04-25T17:38:57Z","title":"Continual Learning of Large Language Models: A Comprehensive Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16789","snapshot_observed_at":"2026-08-02T09:51:03.489576Z","title":"arXiv preprint arXiv:2404.16789 , 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":91,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.489576Z"},"links":{"cited_paper":"/paper/2404.16789","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:4bf9aeb73bdd9f4170e5d3d8d26289696c8b204f1e7318a72ff34acd8f7b6a6d","observation_id":"73b8ebf3-d160-4fa8-860d-b5341ee0a915","resolution":{"observed_at":"2026-08-02T09:51:03.489576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.491908Z","title":"2024 , url=","venue":null,"work_id":null,"year":2024},"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":92,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.491908Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:cfa4e7341119247310723c0012c84b71fd4b0b9890d8008d727b7881b162842c","observation_id":"20eebc25-91b2-4c29-8b70-64d4bb3a7a5b","resolution":{"observed_at":"2026-08-02T09:51:03.491908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.493998Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":2024},"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":93,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.493998Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:4d8ee4c437b41bc5e3a611aacc61b78d5ec95334623f202b6be4476441839089","observation_id":"1a2e43c0-cba5-4a72-964c-9080c8df58b6","resolution":{"observed_at":"2026-08-02T09:51:03.493998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-11T01:48:59.557045Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-02T09:51:03.496049Z","title":"arXiv preprint arXiv:2412.19437 , 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":94,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.496049Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:c39d961a35f2f3e235307bc279ae10024f31c3d46e43ee07081269f382d04ad7","observation_id":"d6137203-0ceb-4a26-ad78-3494a762c8e2","resolution":{"observed_at":"2026-08-02T09:51:03.496049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.498588Z","title":null,"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":95,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.498588Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:9c30ce152c52646fadca9581f849bbb8dc29b0277bfac74f623c1b3182f577d5","observation_id":"686a8777-afe9-49ca-a3b0-f9b773ae6508","resolution":{"observed_at":"2026-08-02T09:51:03.498588Z","resolver_source":null,"status":"parse_uncertain"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.500849Z","title":"Introducing","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":96,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.500849Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:e158b0d47dc417052be8ea707af49882176c342feb7d50df0ce58bea4cb1ebcf","observation_id":"fbc89610-fecd-4710-a771-355ac107dad4","resolution":{"observed_at":"2026-08-02T09:51:03.500849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.503235Z","title":null,"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":97,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.503235Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:4f07d86e68a837db0f824c72223f0b738600086f2dfcf77ca33f54100a326312","observation_id":"4c587fbd-cca9-4a41-9e4a-010fccf079a4","resolution":{"observed_at":"2026-08-02T09:51:03.503235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:51:03.505430Z","title":null,"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":98,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.505430Z"},"links":{"citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:f0ecfd631c5b85268b2464bad422fd0ea7edfb5bebc6c2ba167d447881518862","observation_id":"c5492e16-77ca-4a10-bb27-fae137b7160a","resolution":{"observed_at":"2026-08-02T09:51:03.505430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05530","last_updated":"2024-12-16T17:39:39Z","snapshot_observed_at":"2026-07-06T17:41:42.995949Z","submitted_at":"2024-03-08T18:54:20Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05530","snapshot_observed_at":"2026-08-02T09:51:03.507908Z","title":"arXiv preprint arXiv:2403.05530 , 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":99,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.507908Z"},"links":{"cited_paper":"/paper/2403.05530","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:1cb02c68496feb023d9c96bb1e39f75a0695720b557b342c2fceb59fa3ce8917","observation_id":"d23a61ea-9159-4a90-9a98-a93133005b71","resolution":{"observed_at":"2026-08-02T09:51:03.507908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-02T09:51:03.510157Z","title":"arXiv preprint arXiv:2302.13971 , 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":100,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.510157Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:17185f0131f04db5edac36664386a590a0def0f69949dbd218b5609fb015e238","observation_id":"1ec9fc38-7398-4774-a126-e105f352bd40","resolution":{"observed_at":"2026-08-02T09:51:03.510157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-08-09T21:25:20.369782Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-02T09:51:03.512451Z","title":"arXiv preprint arXiv:2309.16609 , 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":101,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.512451Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:5c2ed76a2d8b1c7eda4ee14ee27d6b0de3f70633dc27338c2aecc4237e72cab5","observation_id":"abd61e8e-9dd8-4bf8-9d1c-ff612c38facc","resolution":{"observed_at":"2026-08-02T09:51:03.512451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.16252","last_updated":"2026-06-27T03:25:36Z","latest_version":1,"primary_category":"cs.LG","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"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":99,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":297},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 100 of 297 outbound references and 0 inbound Pith citation observations for arXiv:2607.16252."}