{"as_of":"2026-08-07T01:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2b68bb14ce48df31342de7dadf026c4a59eec49ea3aaa08bc1290c5d33ccaf6b","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-12T00:59:43.488204Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-19T15:35:25.103868Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-05-19T15:37:37.215780Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"cited_work":{"arxiv_id":"2605.08314","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.08314","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","venue":"cs.LG","work_id":"33c14114-3b15-4a4a-874f-6205f76684ae","year":2026},"citing_paper":{"arxiv_id":"2605.15397","last_updated":"2026-05-14T20:30:25Z","snapshot_observed_at":"2026-08-03T23:32:42.112407Z","submitted_at":"2026-05-14T20:30:25Z","title":"ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest","version":1},"reference_index":127,"source":"pdf_text","source_observed_at":"2026-05-19T15:35:25.103868Z"},"links":{"cited_paper":"/paper/2605.08314","citing_paper":"/paper/2605.15397"},"observation_digest":"sha256:d8224e3322226df7f2b4948f7f90c21d9597e4fc3a4aa5411f43024ec49448b6","observation_id":"42280baa-3908-4190-a0fa-e6bfd89f77af","resolution":{"observed_at":"2026-05-19T15:37:37.218149Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2605.08314/citation-record","integrity":"/paper/2605.08314/integrity","json":"/paper/2605.08314/citation-record.json","paper":"/paper/2605.08314"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.05821","last_updated":"2025-08-28T03:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-10T08:41:24Z","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","version":5},"cited_work":{"arxiv_id":"2312.05821","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.05821","snapshot_observed_at":"2026-07-10T02:06:42.147921Z","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","venue":"cs.CL","work_id":"fd990065-5054-4270-85c7-76af94bddb15","year":2023},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"cited_paper":"/paper/2312.05821","citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:a2fe2fe50c522824728efd2c6b8ade132db2c487e44e95f2208bd98ecf7ef096","observation_id":"57f051cf-fece-485c-a0cd-c26758d65b88","resolution":{"observed_at":"2026-05-20T13:49:33.894132Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"SVD-LLM: Truncation-aware singular value decomposition for large language model compression","venue":null,"work_id":"84225e77-87a8-4226-8a92-f9eeb1fb3538","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:c8a31c8e280a3d3b4b57820b16ea0644765d8dbcdf00690d5b41ef3e8ecb28e4","observation_id":"c8ff150d-342d-4c1e-bc17-984812adf0ca","resolution":{"observed_at":"2026-05-14T09:02:22.906128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Accurate and efficient singular value decomposition for LLMs via decay-aware rank allocation and feature-preserved weight update","venue":null,"work_id":"461fb636-6050-4fd2-92e1-90c19fa9f677","year":2026},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:cd95a1728130573406d374d4b9a1cf0f199c6213f51b482726617a4814523ef1","observation_id":"2cc59db5-155d-4424-b3fe-22585d5406f5","resolution":{"observed_at":"2026-05-14T09:02:22.902294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gf-svd:Globalknowledge-infusedsingularvaluedecompositionoflargelanguagemodels.Information Fusion, page 103774","venue":null,"work_id":"3799aae8-2dfc-448b-b2f7-6ff317520473","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:dec917c7b12418d13d924450f1c9520199f2296f367ca2b6b5bbe55d0175b5f3","observation_id":"832e14ef-f3b0-40df-a8ad-4acabf162488","resolution":{"observed_at":"2026-05-14T09:02:22.904206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.03051","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Saes-svd: Self-adaptive suppression of accumulated and local errors for svd-based llm compression","venue":null,"work_id":"f731e831-81ec-4e3a-963c-78d10fa50215","year":2026},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:f4de83284c55789893d70d46dc1322702180410323fd21832b22d1551d6e86e8","observation_id":"35aae4e1-84c9-4e6b-b977-45cf078b2def","resolution":{"observed_at":"2026-05-12T08:31:26.559585Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"DipSVD: Dual-importance protected SVD for efficient LLM compression","venue":null,"work_id":"58601ddf-34b7-4770-85ea-0b67e2f10fc9","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:d76091c0374e3a805e7c71fe6c3acfa3919d0b650bec597d575d4c0993dc05c6","observation_id":"48b59115-9651-422d-8432-52e4057fda94","resolution":{"observed_at":"2026-05-14T09:02:22.911340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Modegpt:Modulardecompositionforlargelanguagemodelcompression","venue":null,"work_id":"ddf14eda-036b-4a90-a124-4b5259bce294","year":2024},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:340e2a9e76d6809cb4574932874c310e52100b123ac89da6ecb2fd79d66f37f0","observation_id":"febd66eb-90ac-4a63-b9c3-8c6bd15518c7","resolution":{"observed_at":"2026-05-14T09:02:22.925811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"SVD-LLMv2:Optimizingsingular value truncation for large language model compression","venue":null,"work_id":"ee970bb0-fd75-46b3-92bb-23350a09d6a0","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:5a8231f8c0656c224ac03ac93dd6415c72c32991b6a8d3f2fcbbe39d3de41096","observation_id":"1154a2f1-6760-471f-9522-d087166cefc3","resolution":{"observed_at":"2026-05-14T09:02:22.923995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dobi-svd: Differentiable svd for LLM compression and some new perspectives","venue":null,"work_id":"970e5aed-a9c4-43b4-a604-cbfbad4948ee","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:ba28e248ce6ced077bdd3da2c1ad3cacaca0713c71dadf4fa799ae760991d8c6","observation_id":"1fc085b1-dee0-45ac-98c8-68ed693e5009","resolution":{"observed_at":"2026-05-14T09:02:22.927648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"AdaSVD: Adaptive singular value decomposition for large language models","venue":null,"work_id":"9dca508e-78cd-43b9-8b15-a58187749164","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:785f142b33f46f93ab51f3ac347bebe9cfa5e321245dc8bf2680c4e2e545077e","observation_id":"da39ce24-eb5b-4a53-bd9b-a527d31a942b","resolution":{"observed_at":"2026-05-14T09:02:22.929385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2509.25622","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T07:49:39.860927Z","title":"Layer-wisedynamicrankforcompressing large language models","venue":null,"work_id":"6abc6147-a78f-4c46-8f06-547b5ca1d11e","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:1e9d150c85b992850055b8ff7aba9a87830c5103f44d6832f7aecf5c60c95868","observation_id":"ae1393c9-a8a8-46af-bfc7-8df356d97a85","resolution":{"observed_at":"2026-05-12T08:31:26.519766Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03765","last_updated":"2024-10-02T14:30:02Z","snapshot_observed_at":"2026-08-06T07:00:06.275123Z","submitted_at":"2024-10-02T14:30:02Z","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","version":1},"cited_work":{"arxiv_id":"2410.03765","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.03765","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Basis sharing: Cross- layer parameter sharing for large language model compression.arXiv preprint arXiv:2410.03765","venue":null,"work_id":"5b4631d0-8490-44f5-b183-9524f2456b1d","year":2024},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"cited_paper":"/paper/2410.03765","citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:06a316bc286b3fcc0cb01344f2f6ced3068accaa77207500c2680f08612db576","observation_id":"2252d99c-f38f-48bc-88a6-31e38ab62154","resolution":{"observed_at":"2026-05-12T08:31:26.524701Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Data-awarelow-rankcompression for large {nlp} models","venue":null,"work_id":"f52dd4cf-7e70-4d04-a919-a123b5cd6a4b","year":2021},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:abcdddc73358b1b43431c15c4882e64216a150eb1de9ac1ce4e8866e1497854f","observation_id":"212cbc6b-e8ea-4824-a079-42261294164d","resolution":{"observed_at":"2026-05-14T09:02:22.920049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adaptive rank selections for low-rank approximation of language models","venue":null,"work_id":"d7b1ad8f-7e6e-4bbd-9d1c-ffd322e2a592","year":2024},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:be32ccfc22ee3e1242d07c97ba4a5008c02ef54ae0e0cde33a0cf60833694faa","observation_id":"44f59588-9b72-459c-97b0-96c75767b4ae","resolution":{"observed_at":"2026-05-14T09:02:22.916519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.00112","last_updated":"2022-06-30T21:57:07Z","snapshot_observed_at":"2026-07-06T13:26:38.135401Z","submitted_at":"2022-06-30T21:57:07Z","title":"Language model compression with weighted low-rank factorization","version":1},"cited_work":{"arxiv_id":"2207.00112","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2207.00112","snapshot_observed_at":"2026-07-04T10:19:47.498950Z","title":"Language model compression with weighted low-rank factorization.arXiv preprint arXiv:2207.00112","venue":null,"work_id":"e0e91694-b244-460a-a49e-7b2c1ff42979","year":2022},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"cited_paper":"/paper/2207.00112","citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:cc18742a7d07440e4b27d88e5879b5dfa56f73a397091f434a10655e3602d06c","observation_id":"9a78fc8d-3cc2-4a59-982a-a90173837b45","resolution":{"observed_at":"2026-05-12T08:31:26.548872Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.17974","last_updated":"2025-05-23T14:41:52Z","snapshot_observed_at":"2026-07-06T21:29:20.697252Z","submitted_at":"2025-05-23T14:41:52Z","title":"Generalized Fisher-Weighted SVD: Scalable Kronecker-Factored Fisher Approximation for Compressing Large Language Models","version":1},"cited_work":{"arxiv_id":"2505.17974","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.17974","snapshot_observed_at":"2026-07-17T00:20:38.751091Z","title":"Generalized fisher-weighted svd: Scalable kronecker-factored fisher approximation for compressing large language models","venue":null,"work_id":"9a360780-6d22-4cab-ac57-6eb5f02cd520","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"cited_paper":"/paper/2505.17974","citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:45877c1becbb28887f6eb5baad905cf553dffbd32099743b3de839fd31b88395","observation_id":"b36a9964-d035-46c9-9975-596dd2334891","resolution":{"observed_at":"2026-07-17T00:20:38.751091Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient one-shot compression via low-rank local feature distillation","venue":null,"work_id":"62f38c19-c1be-47a1-b870-3bf6d6b8a3d4","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:164a577e03390f435fd433c8da1b68468cd3ae859d0aaefe495d728567ec84b0","observation_id":"d1c8e946-ce32-44f0-a260-0504e260f081","resolution":{"observed_at":"2026-05-14T09:02:22.918389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dobi-svd: Differen- tiablesvdforllmcompressionandsomenewperspectives","venue":null,"work_id":"512f1f36-e76c-4647-99f0-fdba0191d5c5","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:e00bb9a294ae41250577ba954d1ba5960eddf8ed61a6394f0676ff97d7e8f849","observation_id":"ea6f77e1-6073-4434-8a60-72bdfa948ca9","resolution":{"observed_at":"2026-05-14T09:02:22.921871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2604.02119","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T22:57:26.737933Z","title":"Aa-svd: Anchored and adaptive svd for large language model compression","venue":null,"work_id":"f6169377-d576-48fd-97b7-2aa4e97d8541","year":2026},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:c4a5c8f7af621574f8e451f3e653111c989fe601cedf0dc89d372b17643c4200","observation_id":"fd7b9590-4a85-4f3e-a912-8beb5b72b3d5","resolution":{"observed_at":"2026-05-12T08:31:26.534108Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.02848","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zero sum svd: Balancing loss sensitivity for low rank llm compression","venue":null,"work_id":"8d073068-ed52-44c4-bd8c-a5bbb1d845a1","year":2026},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:da91e7372c11625664713d9033778e883886f9bca6eef8e94b64ed3aedf87f38","observation_id":"7a0de046-1c0d-41d0-808a-0174984ded94","resolution":{"observed_at":"2026-05-12T08:31:26.564527Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Abdelfattah, and Kai-Chiang Wu","venue":null,"work_id":"e48dae36-fc36-490e-a821-d1712538e318","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:4eb2e34bc05f534ac725239b57e6dc4b834e701807d4eae2e6c0e490debd7cca","observation_id":"be3ff320-1f61-43fd-bd74-b91e8b21d444","resolution":{"observed_at":"2026-05-14T09:02:22.932684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.18893","last_updated":"2026-05-27T05:57:00Z","snapshot_observed_at":"2026-07-06T20:57:57.039376Z","submitted_at":"2025-03-24T17:06:37Z","title":"xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction","version":2},"cited_work":{"arxiv_id":"2503.18893","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.18893","snapshot_observed_at":"2026-07-10T01:36:44.285178Z","title":"Arthur Conmy, Augustine Mavor-Parker, Aengus Lynch, Stefan Heimersheim, and Adrià Garriga- Alonso","venue":"cs.CL","work_id":"16dc86cb-7b66-400c-be1f-dd459db6f94e","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"cited_paper":"/paper/2503.18893","citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:0567a8fe25449f8161519b1fed0134f268e654f4fb1a6173224c9708ecfcdd10","observation_id":"c136ed24-8591-49dd-b7a3-8a79b3aedca4","resolution":{"observed_at":"2026-05-28T02:04:08.438618Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.16292","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T19:12:34.672154Z","title":"Qsvd: Efficient low-rank approximation for unified query-key-value weight compression in low-precision vision-language models","venue":null,"work_id":"0c06e747-1e90-4bdd-89e7-3853e69bafd3","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:c902aec60186e38d45dab7b31c67ba46a290e3f722106a3f724ede9d08d2b800","observation_id":"1b763f91-f068-413c-a0d8-82af8bd1fcc2","resolution":{"observed_at":"2026-05-12T08:31:26.574354Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Eigen attention: Attention in low-rankspaceforkvcachecompression","venue":null,"work_id":"c9120979-df88-4b70-b267-020fe97e1db9","year":2024},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:42a7f34dcff6910c9334c9a4c85cba9d7ebabf4ba8283bdde5239907f160b9c0","observation_id":"347326f6-2de4-4b54-a3a3-55255101d7bd","resolution":{"observed_at":"2026-05-14T09:02:22.931010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Blind restoration of high-resolution ultrasound video","venue":null,"work_id":"a4699726-61d8-4352-b44e-8962f71397f6","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:8a5253c0fc4d444f7482c5c15075ae64ed7b9fdd6529ec55d73d3ff1ce35c3f4","observation_id":"22000344-12d1-4a3f-9616-74d57476fa4f","resolution":{"observed_at":"2026-05-14T09:02:22.907946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sada:Stability-guidedadaptivediffusionacceleration","venue":null,"work_id":"85eda78a-af10-4241-83ed-d26cb6fdd2d4","year":null},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:3b30f83cac99f866abb131b50c6a499d12f34e9b76fd3d9e7456b3138f1bc2a4","observation_id":"c37f2696-628f-48b2-957e-c8f6c0f1901b","resolution":{"observed_at":"2026-05-14T09:02:22.909613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Acceleratingdenoisinggenerativemodelsisaseasyaspredicting second-order difference","venue":null,"work_id":"4c7a5ce8-31d0-4aac-b384-02d3fa3d02c8","year":null},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:85d23e882e88dc9a06c8cc71a13630e591253638498b6957cc19c56bd6929a50","observation_id":"ed508b06-597f-41fc-8973-43403649c53f","resolution":{"observed_at":"2026-05-14T09:02:22.913024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2604.01552","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zeus: Accelerating diffusion models with only second-order predictor","venue":null,"work_id":"d0bce33e-7d2c-41f3-b65f-4a916d6c4989","year":2026},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:008637c68f23584b3e1361f1b8cb7a0ee391af8b463606e359bc521f889bbd9c","observation_id":"7964839a-4ca7-42b4-a804-0fbedde5af2c","resolution":{"observed_at":"2026-05-12T08:31:26.544330Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient localization and spatial distribution modelingofcanopypalmsusinguavimagery.IEEETransactionsonGeoscienceandRemoteSensing","venue":null,"work_id":"b07dfe1f-9f61-4043-8f58-d116e6b2ea92","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:727681cd338b4dcd4e12eb41364ecfcd427111d793fe8c2005deeb4b9b83972a","observation_id":"f6982b45-32d9-41ed-9bdd-7e9a8105d1fd","resolution":{"observed_at":"2026-05-14T09:02:22.914827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scalable dual coordinate descent for kernel methods","venue":null,"work_id":"d8625b61-1450-4d5f-877e-88281a3563b5","year":2025},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:bf21075cd9028ca2ac143b4facf37bdbac79fada2942f91e388f20e77834309b","observation_id":"616849df-c74d-42ee-af31-d78b574e37a4","resolution":{"observed_at":"2026-05-14T09:02:22.900449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1421.0343","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Enhanced cyclic coordinate descent methods for elastic net penalized linear models.Advances in Neural Information Processing Systems, 38:137240–137281","venue":null,"work_id":"2a8f014a-4d67-4842-ab14-973a702fa4d7","year":2026},"citing_paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-12T00:59:43.488204Z"},"links":{"citing_paper":"/paper/2605.08314"},"observation_digest":"sha256:0d36bb161a6a7d7bd55b01e44dfca310c43e367e09202c432c67ef2b59c6e2c4","observation_id":"f01b762f-393d-4d68-bc81-facdb3ae7f54","resolution":{"observed_at":"2026-05-12T08:31:26.569261Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.08314","last_updated":"2026-05-08T14:20:42Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T20:58:18.012548Z","submitted_at":"2026-05-08T14:20:42Z","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":12,"verified_fuzzy":19},"total_outbound_references":31},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2605.08314."}