{"as_of":"2026-08-15T23:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2976fa22d87d05766e52cf687c2101fbc29e80d47edab7f440ee02e95b2f0494","coverage":[{"denominator":91,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":91,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:16:49.120859Z","state":"measured"},{"denominator":91,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":91,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2608.10144/citation-record","integrity":"/paper/2608.10144/integrity","json":"/paper/2608.10144/citation-record.json","paper":"/paper/2608.10144"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-14T04:16:48.647912Z","title":"GPT-4 technical report.arXiv preprint arXiv:2303.08774, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.647912Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:24045a605ef9a08eae2f44dae80ea369ea9e4b635bddcc9bd14471c2c43c0694","observation_id":"86a552eb-5555-4bcb-92bd-e3d455297d2e","resolution":{"observed_at":"2026-08-14T04:16:48.647912Z","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":"2026-08-14T04:16:48.655254Z","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.655254Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:191900a7d1ff63679ff8a21fa6d57f9f6b8d9edf3bd282d24b9cd68d103b89e2","observation_id":"b3996b3e-4ecd-4d39-8a70-888d02de4195","resolution":{"observed_at":"2026-08-14T04:16:48.655254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10403","last_updated":"2023-09-13T20:35:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-17T17:46:53Z","title":"PaLM 2 Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10403","snapshot_observed_at":"2026-08-14T04:16:48.660716Z","title":"PaLM 2 technical report.arXiv preprint arXiv:2305.10403, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.660716Z"},"links":{"cited_paper":"/paper/2305.10403","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:dfdb27f9414cbf57678a7f796f7c0b7fdac8ec5621efa93c7c02566bba0953cc","observation_id":"2921a5e6-7932-4a7a-9ba7-18db271a7373","resolution":{"observed_at":"2026-08-14T04:16:48.660716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-14T04:16:48.666283Z","title":"Llama 2: Open foundation and fine-tuned chat models.arXiv preprint arXiv:2307.09288, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.666283Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:f996c63498b768b948a10819279b045e31f8c174e01067831263f562705324d0","observation_id":"f74fdfd4-d04b-4f4a-bbd4-a3360bcc7369","resolution":{"observed_at":"2026-08-14T04:16:48.666283Z","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":"2026-08-14T04:16:48.671788Z","title":"The claude 3 model family: Opus, sonnet, haiku","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.671788Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:9e92ce64a0a19ae7d31a422b9b7d06d46ffa45d312c59b6205ac2a2170458ad7","observation_id":"fff49982-1dee-48bb-87ff-2648c24c3c79","resolution":{"observed_at":"2026-08-14T04:16:48.671788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T14:19:26.598265Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-14T04:16:48.676859Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale.arXiv preprint arXiv:2010.11929, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.676859Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:c3753f44d5991dd6df6513ac45a9fb8b05e43637e898ef705543a05f169e3cec","observation_id":"edbf5da5-8f47-4fcd-8d18-9aa63fc13db6","resolution":{"observed_at":"2026-08-14T04:16:48.676859Z","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":"2026-08-14T04:16:48.682539Z","title":"Fine-tuning a llm using reinforcement learning from human feedback for a therapy chatbot application, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.682539Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:9675122ea447fbaf5dbe516965f33dea87e7953994259f46002c4142c9648c7d","observation_id":"e308f6eb-d70d-41f1-9912-3914d2dec667","resolution":{"observed_at":"2026-08-14T04:16:48.682539Z","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":"2026-08-14T04:16:48.688244Z","title":"Towards next-generation intelligent assistants leveraging llm techniques","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.688244Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:b12cd76f316bbe8e2807a80f9cffe9223dc014f82d44ef49d355cc4f918a4f17","observation_id":"b09f5654-e292-42dc-b38a-8ac18b1a53c1","resolution":{"observed_at":"2026-08-14T04:16:48.688244Z","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":"2026-08-14T04:16:48.692938Z","title":"Bing chat: The future of search engines?Proceedings of the Association for Information Science and Technology, 60(1):1007–1009, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.692938Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:d4c5f98cd815d69bde27a961b27beecbae189e398f198aa3ecb338e32f43d0bc","observation_id":"22cfa1f3-d4d2-4ecf-be69-0e183563783b","resolution":{"observed_at":"2026-08-14T04:16:48.692938Z","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":"2026-08-14T04:16:48.698453Z","title":"Large language models encode clinical knowledge","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.698453Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:7cfd1412c83bf8521c4c0ece5854ab202e287f0ec1936c4d27466ec93b63d414","observation_id":"df9a6b82-f1a5-4fcd-8c5d-6e68b03f473f","resolution":{"observed_at":"2026-08-14T04:16:48.698453Z","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":"2026-08-14T04:16:48.703451Z","title":"Parameter-Efficient Transfer Learning for NLP","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.703451Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:7cc69af83456db1ebc44ddc6791af72aeb895decd5572bfdb4cf8212a5137ffb","observation_id":"51404f11-e516-42b7-9280-1f7e8f7ec994","resolution":{"observed_at":"2026-08-14T04:16:48.703451Z","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":"2026-08-14T04:16:48.708586Z","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.708586Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:851c3167682636b3c82adf41dbb76855ae0d821b7d3aba03d10799ef058f99ea","observation_id":"d6f0f194-6c77-4993-83ce-9efc21516914","resolution":{"observed_at":"2026-08-14T04:16:48.708586Z","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":"2026-08-14T04:16:48.714732Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.714732Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:4292a562e988bee7632b40e71582af3fe4b06c663e1dfa2347f66d86eb4d8e86","observation_id":"cdbb867e-45d0-4c1c-bcaf-f24b17dc5f75","resolution":{"observed_at":"2026-08-14T04:16:48.714732Z","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":"2026-08-14T04:16:48.720923Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.720923Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:ada00b5bf8ed9fa5bab689b0a279b736179722ecc7fcf07a713401f383f8f8aa","observation_id":"9abad158-d022-4efb-8dad-27666eccbb6c","resolution":{"observed_at":"2026-08-14T04:16:48.720923Z","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":"2026-08-14T04:16:48.726046Z","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models, September 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.726046Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:d3c36c38dbc0840d57caa2bbb19d59f2e06ef1f0578d3379863f27a40500e10e","observation_id":"6dc9630a-b4af-419a-96ae-a748dd0d314e","resolution":{"observed_at":"2026-08-14T04:16:48.726046Z","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":"2026-08-14T04:16:48.731208Z","title":"Parameter-Efficient Fine-Tuning without Introducing New Latency","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.731208Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:acf562a13d4dd49ad9c6acf96ac80a1ff34ff3828c35967903e6f9963c026867","observation_id":"5b869867-aa96-4251-af8d-520b3358767e","resolution":{"observed_at":"2026-08-14T04:16:48.731208Z","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":"2026-08-14T04:16:48.737824Z","title":"LoRA: Low-rank adaptation of large language models.Iclr, 1(2):3, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.737824Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:d1df7585f9eab6b60cda9377dca86a2cc62fe84f55366bcfb1c680e6648b97da","observation_id":"ca192346-8e46-4a84-a7b6-2485ae9a4ea1","resolution":{"observed_at":"2026-08-14T04:16:48.737824Z","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":"2026-08-14T04:16:48.743884Z","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.743884Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:d629b4d04c9d30954fba5103e8ca731def81871fb85a9925da6c30691e26f670","observation_id":"71c8732c-3d62-45c6-87d0-e4520880e56d","resolution":{"observed_at":"2026-08-14T04:16:48.743884Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.904453Z","title":"HydraLoRA: An Asymmetric LoRA architecture for efficient fine-tuning","venue":null,"work_id":"5f6e88b2-4800-4e2e-aea6-c242d1ff2a2b","year":null},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.749005Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:299460523e409977878b59f0fe96f8137ebc93a5f48d1b98c8448757eb584473","observation_id":"dea194a5-e9dd-40f7-b221-5877e7d1de89","resolution":{"observed_at":"2026-08-14T04:16:50.912584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10512","last_updated":"2023-12-20T20:56:14Z","snapshot_observed_at":"2026-08-12T23:46:47.414754Z","submitted_at":"2023-03-18T22:36:25Z","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10512","snapshot_observed_at":"2026-08-14T04:16:48.765402Z","title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.765402Z"},"links":{"cited_paper":"/paper/2303.10512","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:e5eb5de7de1e4fdc9a534b5df08acdc47941ec767cc6f6883f52dcb5031bceee","observation_id":"db84a42d-39ac-44f4-baab-7fbab9ba8aab","resolution":{"observed_at":"2026-08-14T04:16:48.765402Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.877608Z","title":"DyLoRA: Parameter-efficient tuning of pre-trained models using dynamic search-free low-rank adaptation","venue":null,"work_id":"94940614-1c07-4705-b3a6-be8529c5b780","year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.770311Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:312100c74f2b991be1801afc8514aada57baa4165a31e675f3a5d6a936251c7f","observation_id":"1dac6935-d354-4d14-87b5-ccde5fb99fb5","resolution":{"observed_at":"2026-08-14T04:16:50.882437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.860285Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehen- sive Survey.Transactions on Machine Learning Research, October 2024","venue":null,"work_id":"e63f26b4-f32f-40b4-84ed-8a43f71f83c4","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.774856Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:6ddebb54703e995ad08615f03f56eda7d5a7fad8f133e973ef419809285fd150","observation_id":"51a56941-d80f-4b7f-86b4-13b5ed29e91e","resolution":{"observed_at":"2026-08-14T04:16:50.865649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:48.779595Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.779595Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:52ad252c5d062972ee640a3c30a2ba510f7910e0437416ec48ee5c8aad1e45d2","observation_id":"39beeda1-b1bf-4e69-902e-7dbd5f2e59d2","resolution":{"observed_at":"2026-08-14T04:16:48.779595Z","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":"2026-08-14T04:16:48.785017Z","title":"Advances and open problems in federated learning.Foundations and trends in machine learning, 14(1-2):1–210, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.785017Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:dc844bd48b336a2bb2e54ede2c771702b54490c8d6a4a508910d2435bc532d6e","observation_id":"fe098628-78b7-49a7-b9cb-b23e21b906ce","resolution":{"observed_at":"2026-08-14T04:16:48.785017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.08830","last_updated":"2025-05-13T03:23:54Z","snapshot_observed_at":"2026-08-15T21:58:44.996474Z","submitted_at":"2025-05-13T03:23:54Z","title":"Federated Large Language Models: Feasibility, Robustness, Security and Future Directions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.08830","snapshot_observed_at":"2026-08-14T04:16:48.790114Z","title":"Federated large language models: Feasibility, robustness, security and future directions","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.790114Z"},"links":{"cited_paper":"/paper/2505.08830","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:936bf519b915e8d071cc085c3cab6d9a9f7b3cc9df0d193b092d01453d118873","observation_id":"cf631879-5429-498d-84a0-e64c9389fbdc","resolution":{"observed_at":"2026-08-14T04:16:48.790114Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.821699Z","title":"A survey on federated learning systems: Vision, hype and reality for data privacy and protection.IEEE Transactions on Knowledge and Data Engineering, 35(4):3347–3366, 2021","venue":null,"work_id":"aefddf66-5e52-4ef7-8a89-c6f56db2ed5b","year":2021},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.795589Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:ae44ea7048818028625fbacf322512557accf62feb8133bc3bdcaf632e766082","observation_id":"9404c3c7-2117-46b3-8bc7-ec9f23f13668","resolution":{"observed_at":"2026-08-14T04:16:50.827828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.805732Z","title":"Efficient federated learning for modern NLP","venue":null,"work_id":"5861d74a-c989-42fb-953d-83e566583718","year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.800622Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:b2c9dfe20892b2b40f5722f0c42f646f4a9f044d6d6234508ba458b53050febc","observation_id":"1320001b-1327-41cb-9d58-bcbaacdfdc9d","resolution":{"observed_at":"2026-08-14T04:16:50.811089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13097","last_updated":"2025-06-01T00:41:09Z","snapshot_observed_at":"2026-08-13T17:36:46.600812Z","submitted_at":"2024-10-16T23:50:39Z","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13097","snapshot_observed_at":"2026-08-14T04:16:48.806033Z","title":"Communication-efficient and tensorized federated fine-tuning of large language models.arXiv preprint arXiv:2410.13097, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.806033Z"},"links":{"cited_paper":"/paper/2410.13097","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:048e3e69996dcc2d831227163ee0effc4c70fd2c72443084dcde10596909d395","observation_id":"0cc0e0da-3b62-435e-926b-10d2c3d0fd7f","resolution":{"observed_at":"2026-08-14T04:16:48.806033Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.789249Z","title":"Fedprompt: Communication-efficient and privacy-preserving prompt tuning in federated learning","venue":null,"work_id":"c7ee8039-af2e-4976-88dd-30be8b49a8ad","year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.811450Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:56e8881e1dbbe037ea94f7e8f1510b350ddceacd3c38e366d82d75d8671121f2","observation_id":"4c3d86f6-3b02-46d6-982f-13cba7b4de93","resolution":{"observed_at":"2026-08-14T04:16:50.794157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06123","last_updated":"2023-10-09T19:57:24Z","snapshot_observed_at":"2026-08-13T05:53:32.145848Z","submitted_at":"2023-10-09T19:57:24Z","title":"Text-driven Prompt Generation for Vision-Language Models in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06123","snapshot_observed_at":"2026-08-14T04:16:48.816374Z","title":"Text-driven prompt generation for vision-language models in federated learning.arXiv preprint arXiv:2310.06123, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.816374Z"},"links":{"cited_paper":"/paper/2310.06123","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:e16d3d2152e5ab0db878ddd925434c0573d6e93834f632c50cb36a4b657c0122","observation_id":"d7d04d5d-2318-4903-87ba-54677332640e","resolution":{"observed_at":"2026-08-14T04:16:48.816374Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00247","last_updated":"2023-10-04T18:27:59Z","snapshot_observed_at":"2026-08-14T15:32:15.054415Z","submitted_at":"2023-09-30T04:31:53Z","title":"Bridging the Gap Between Foundation Models and Heterogeneous Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00247","snapshot_observed_at":"2026-08-14T04:16:48.821293Z","title":"Pablo Muñoz, and Ali Jannesari","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.821293Z"},"links":{"cited_paper":"/paper/2310.00247","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:29eabb82c817131591ceae9815c90b332aa75af25ee8e71a28c20da6b4a2ddcd","observation_id":"403d99ee-8fc8-4c0d-8e88-c5793100199a","resolution":{"observed_at":"2026-08-14T04:16:48.821293Z","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":"2026-08-14T04:16:48.826438Z","title":"Rethinking LoRA for data heterogeneous federated learning: Subspace and state alignment.arXiv preprint arXiv:2602.01746, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.826438Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:23bf04bb07ea4f1fddabc469cfa32536544ce61011e121869a8d14df24c820e7","observation_id":"fda0baeb-b061-4060-9b7b-4e187f9a5fff","resolution":{"observed_at":"2026-08-14T04:16:48.826438Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.772856Z","title":"LoRA+: Efficient low rank adaptation of large models","venue":null,"work_id":"a5220b59-f467-44af-8eab-1ebee7175c4f","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.831389Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:59bb424c7a4bf0bfe219c183be0ade501037cc003c57b6c7d1596afa81b802c2","observation_id":"b5aafe2a-4524-4c00-90b4-81ddf0017202","resolution":{"observed_at":"2026-08-14T04:16:50.778151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.757181Z","title":"DoRA: Weight-decomposed low-rank adaptation","venue":null,"work_id":"44c70769-8196-458d-bdd9-bb77d2908c7c","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.836113Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:b45e782e404f5dbcb6eb84f93e2b64b947f0e0bacbec381240bb90f1ea0f8264","observation_id":"841df353-edf8-4791-9571-1f60e05d6b37","resolution":{"observed_at":"2026-08-14T04:16:50.762254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.739733Z","title":"LoRA-drop: Efficient LoRA parameter pruning based on output evaluation","venue":null,"work_id":"cc7bc6bf-28c8-4a06-b19d-2c6d0823364b","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.841023Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:71bb314f5c7d1f8fead632f1a6fdab36f3452571dd058bee204e8ca7734a184c","observation_id":"ca56a59a-ab58-467d-888c-820fa3ec3c73","resolution":{"observed_at":"2026-08-14T04:16:50.745991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.721666Z","title":"LLaMA-LoRA neural prompt engineering: A deep tuning framework for automatically generating chinese text logical reasoning thinking chains.Data Intelligence, 2024","venue":null,"work_id":"8835a792-6428-4db9-9639-464203c9d794","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.846566Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:f56130fc6dcdcdb2c46b66e8a0f93243a8824547467beb8889f60021725e4b20","observation_id":"195876e1-6cb5-4c60-99c9-5cb88e37430b","resolution":{"observed_at":"2026-08-14T04:16:50.726938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.704962Z","title":"LoRA training provably converges to a low-rank global minimum or it fails loudly (but it probably won’t fail)","venue":null,"work_id":"63019abb-8d1e-46e9-97db-1d57731bd5e2","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.851296Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:957fbf2252da9cdffe083605b42591ba7bf5a1202db09ff940903c6cfde2eb18","observation_id":"4c687631-ed21-4191-b408-e277f6f14cdf","resolution":{"observed_at":"2026-08-14T04:16:50.710817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.687343Z","title":"Towards building the federated GPT: Federated instruction tuning","venue":null,"work_id":"73f28acd-781e-4a5a-853c-b3a6a50be56f","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.856115Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:fb663d126531afe0ba388e1cfda774c3148776a937f5bc970a210de1b92848b1","observation_id":"0a25ae94-eab1-46be-bf6e-85ab90250a2c","resolution":{"observed_at":"2026-08-14T04:16:50.692854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.22905","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:49.814096Z","title":"Flexlora: Entropy-guided flexible low-rank adaptation.arXiv preprint arXiv:2601.22905, 2026","venue":null,"work_id":"25efebb5-0219-4d92-8657-45a08c57c2d2","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.860817Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:1e43040ee1ccbd175e475a129b7ed6f047c4c34a8b96d826308b63aea3dac2cb","observation_id":"7da8ca57-455b-40e8-aa1b-cf92b30fcbf9","resolution":{"observed_at":"2026-08-14T04:16:49.824744Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.669340Z","title":"Rethinking loRA for privacy-preserving federated learning in large models","venue":null,"work_id":"9684dcd8-b971-474b-91b1-ce0b67912a78","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.865655Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:07865931605cdceb9f0b65e0d3eccbc6aace7b223e917b3d974f62498d1d5d73","observation_id":"5ff77877-8eb1-44a7-9e88-51f8371cdc5d","resolution":{"observed_at":"2026-08-14T04:16:50.675124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.652050Z","title":"Heterogeneous LoRA for federated fine-tuning of on-device foundation models","venue":null,"work_id":"9b7cf720-5783-4e40-bb9e-5a0a6841fcbc","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.870728Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:87230ec06d83cb959de83a2958fd5f2a1cc02f94d5b96e4340f098d61795dedc","observation_id":"209fce20-2346-45f2-9fdf-02b0bee59c8e","resolution":{"observed_at":"2026-08-14T04:16:50.657062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02346","last_updated":"2024-09-04T00:20:55Z","snapshot_observed_at":"2026-08-14T09:26:49.088473Z","submitted_at":"2024-09-04T00:20:55Z","title":"Robust Federated Finetuning of Foundation Models via Alternating Minimization of LoRA","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02346","snapshot_observed_at":"2026-08-14T04:16:48.876234Z","title":"Robust federated finetuning of foundation models via alternating minimization of lora.arXiv preprint arXiv:2409.02346, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.876234Z"},"links":{"cited_paper":"/paper/2409.02346","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:82c11d930de6e115f2bf4c8cac229a861d34733648c8181845e60c7804963f27","observation_id":"60885078-b15b-4880-9191-3b7862665f4e","resolution":{"observed_at":"2026-08-14T04:16:48.876234Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.634917Z","title":"Selective aggregation for low-rank adaptation in federated learning","venue":null,"work_id":"27eb98c9-3b70-4b32-9a43-3bf90d3bec23","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.882030Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:9004b3b41c95d8d7a6a8e4d7da5a413cba97d9406a7c425a032aeb9d30b31a35","observation_id":"1123cccf-2ec4-4a25-9e14-5255c008a290","resolution":{"observed_at":"2026-08-14T04:16:50.640430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.617327Z","title":"Improving loRA in privacy-preserving federated learning","venue":null,"work_id":"e96081d4-f104-41e0-91ea-68561ef4cced","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.887738Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:e0008de8e953f3510b45c0fdcc6c404a96d0a10abc228c43bbda36ec9cd55c39","observation_id":"df5caaa9-e22d-4120-912f-0d98c118a65b","resolution":{"observed_at":"2026-08-14T04:16:50.623057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.602246Z","title":"FLoRA: Federated fine-tuning large language models with heterogeneous low-rank adaptations.Advances in Neural Information Processing Systems, 37:22513–22533, 2024","venue":null,"work_id":"b26ac4b3-8485-44a1-ac37-dbbb6a32dea2","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.892826Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:d38d210689837db738863c678de3495ffb45d68bf922a8e153b992280e122ccf","observation_id":"496851cc-6492-424f-9a40-9e5a8cd582fd","resolution":{"observed_at":"2026-08-14T04:16:50.606921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:48.897533Z","title":"Federated fine-tuning of large language models under heterogeneous tasks and client resources.Advances in Neural Information Processing Systems, 37:14457–14483, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.897533Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:5821f1673d1797299228d473ca8948e46a5511d0e2d3ed772e1330006c04b164","observation_id":"dc27fd91-e11c-4ee1-85fa-1e7cbaf89e18","resolution":{"observed_at":"2026-08-14T04:16:48.897533Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.573760Z","title":"Federated sketching LoRA: On-device collaborative fine-tuning of large language models","venue":null,"work_id":"6a9b36df-cb03-40bb-bf31-bd719ec49891","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.902730Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:93769b3304a028e69d8807ea69a97b6982f0f89fead572a22d7c43e9441f4dc9","observation_id":"b9a0c3bd-078f-4a6c-a08d-614efa148746","resolution":{"observed_at":"2026-08-14T04:16:50.580420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.557219Z","title":"Practical sketching algorithms for low-rank matrix approximation.SIAM Journal on Matrix Analysis and Applications, 38(4):1454–1485, 2017","venue":null,"work_id":"8f50f7a3-d40f-49d9-a5ba-b0ffc0cfbf50","year":2017},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.907707Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:85879c503ae638d2b73a4a6e3b538ba2cec566f49c4a7ad8dcbaee9329386c44","observation_id":"9391a5fd-fafe-4e8e-99f6-8c00730f1974","resolution":{"observed_at":"2026-08-14T04:16:50.562102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.540310Z","title":"Towards federated low-rank adaptation of language models with rank hetero- geneity","venue":null,"work_id":"aa6ed672-be89-4310-b94b-a698bcc2477b","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.912717Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:647ad3ccf1316f9243e4294ee9e9ca8829ea167cfa0ef4b4bc986b8b005d6f84","observation_id":"77c0f445-5c86-49ee-8003-508a762ab1e0","resolution":{"observed_at":"2026-08-14T04:16:50.545522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.524988Z","title":"RB-LoRA: Rank-balanced aggregation for low-rank adaptation with federated fine-tuning","venue":null,"work_id":"aa0c704d-2fb5-46f0-b6cc-5f8a496f59f2","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.917165Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:078db4e4fc01c006d0e3c4d038056a00c0f6cbb5e5b0cb446424d37f497aeec7","observation_id":"c067bfcf-c9d3-4dd9-b60f-4efdf66cc504","resolution":{"observed_at":"2026-08-14T04:16:50.529936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.510646Z","title":"Fedsrd: Sparsify-reconstruct- decompose for communication-efficient federated large language models fine-tuning","venue":null,"work_id":"f7db4848-467d-4b69-bfaf-e85a39bf3aaf","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.922160Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:ff2da89672edcf3c4a4a57149b8a22cc73079e7dbfcdb5f152deaff055644e95","observation_id":"82035104-a4f5-42a4-84a2-bdc460dd96e7","resolution":{"observed_at":"2026-08-14T04:16:50.515095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.494453Z","title":"Adaptive rank allocation for federated parameter-efficient fine-tuning of language models.IEEE Transactions on Computers, 2026","venue":null,"work_id":"50240284-127b-4910-a668-69b628db8a8d","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.927135Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:3e26a69f3a00b0c910a52661090f990934f42589e82506ca3cd7f34449e11031","observation_id":"136a142d-11b5-48fc-8a91-a1ad39e37c98","resolution":{"observed_at":"2026-08-14T04:16:50.500283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:48.932718Z","title":"Sparse low-rank adaptation of pre-trained language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.932718Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:42324de416ee5c0c4e65e35f2c294793e818db47e779fa68b0a10f9e52f5a82d","observation_id":"19a918ec-8ced-4e1e-8075-3e444e505ed1","resolution":{"observed_at":"2026-08-14T04:16:48.932718Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.467676Z","title":"Robust federated finetuning of LLMs via alternating optimization of LoRA.Advances in Neural Information Processing Systems, 38:120038–120090, 2026","venue":null,"work_id":"d1bd0f8c-420f-452d-82b2-037900b895e0","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.939010Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:233ca221904c47dddc813a4a126a5bdda704714cdde4db044723c839949db2ec","observation_id":"c693a8ca-06d4-4708-bea3-d973277f2e62","resolution":{"observed_at":"2026-08-14T04:16:50.472671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-14T04:16:48.944043Z","title":"Roberta: A robustly optimized bert pretraining approach.arXiv preprint arXiv:1907.11692, 2019","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.944043Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:699a8f7f533c30a557548608c6a2a1bbf5dc2d2c1206f645486329883786a11f","observation_id":"aa8d87dc-f5d1-4d32-8a00-9feb22b6ef0c","resolution":{"observed_at":"2026-08-14T04:16:48.944043Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.452496Z","title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":"1e4ba9c4-7349-464d-8fd5-34d9163b7c4c","year":2018},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.949355Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:f28ad9e5e783adb015952fed482257186b1451b64580e48182440c752c7d0bea","observation_id":"6fd3394d-1a4a-4873-8cdb-07801712dd3e","resolution":{"observed_at":"2026-08-14T04:16:50.457311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.437910Z","title":"Federated learning for open banking","venue":null,"work_id":"d41f46c5-feb6-472d-bd81-d535e5e5fe2c","year":2020},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.954373Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:96248938438f9e59fa39fa4e63f32b25969172e4ce7c938047eac213d6e131fc","observation_id":"b963033a-7efa-460f-970e-79344db4b548","resolution":{"observed_at":"2026-08-14T04:16:50.442717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.423754Z","title":null,"venue":null,"work_id":"6c3c9848-ca2b-45ce-a217-f80af5deb007","year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.958660Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:54c8baf9eb57c8dac64382492ac748a814f75aa4e8f9a83f088b8aecd9159dcc","observation_id":"e5f312f8-c525-4375-ab9d-7efdee0feace","resolution":{"observed_at":"2026-08-14T04:16:50.427924Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.407021Z","title":"Specificity-preserving federated learning for mr image reconstruction.IEEE Transactions on Medical Imaging, 42(7):2010–2021, 2022","venue":null,"work_id":"f6abae3e-db81-4f80-9c3a-ccfde261f6a0","year":2010},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.963417Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:de766251fee637e05bcaf88a542d2d8f0975d579eea5a7cc9d5ee758b4ed4905","observation_id":"567e2a8d-3c69-40a0-8320-6178f77b13fb","resolution":{"observed_at":"2026-08-14T04:16:50.412060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.392762Z","title":"Roth, Wenqi Li, Dong Yang, Can Zhao, Vishwesh Nath, Daguang Xu, Qi Dou, and Ziyue Xu","venue":null,"work_id":"45c49faf-7199-4567-8a3b-779a06b3243e","year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.968200Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:fa4a821d4854bf662a7a93940c9bf68978bb81b7a751a5f14e0698837e3d2290","observation_id":"94910313-68e2-401e-b51c-1bd5554ca0a3","resolution":{"observed_at":"2026-08-14T04:16:50.397047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.376559Z","title":"Learning federated visual prompt in null space for mri reconstruction","venue":null,"work_id":"dfb9621a-1f5d-495d-a26a-6666574b0fda","year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.972705Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:2da4d760bca6bece4f57a7d098ee77f2325925fb74b8e1db162640b7e270305e","observation_id":"c0110c60-92dc-47b4-933b-d811fa6eadc6","resolution":{"observed_at":"2026-08-14T04:16:50.381805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.362056Z","title":"Cross-modal vertical federated learning for mri reconstruction.IEEE Journal of Biomedical and Health Informatics, 2024","venue":null,"work_id":"6c6c4c6b-9b36-4310-b146-69b5e35f0b3f","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.977311Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:86ca7a7098e985966922565ce21ff9445684915694d0cd04f4e8a5d31e6b163f","observation_id":"b3cdf7d5-3eb0-42eb-a3b3-b1ef532fff79","resolution":{"observed_at":"2026-08-14T04:16:50.366548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09831","last_updated":"2025-05-09T03:11:55Z","snapshot_observed_at":"2026-08-12T23:42:53.748007Z","submitted_at":"2024-06-14T08:40:58Z","title":"Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security","version":2},"cited_work":{"arxiv_id":"2406.09831","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.09831","snapshot_observed_at":"2026-08-14T04:16:49.702745Z","title":"Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security","venue":"cs.LG","work_id":"cf59e47e-7aa8-4304-832c-cf8d560bf9b9","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.983333Z"},"links":{"cited_paper":"/paper/2406.09831","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:3e7ef3984dcd048f973ea91e48a6bb3150148c1fd3308eb4ecc8e216ef121c7f","observation_id":"7ddbab07-77c6-4200-a17f-cdc750ae91ed","resolution":{"observed_at":"2026-08-14T04:16:49.710294Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10049","last_updated":"2023-10-16T04:17:13Z","snapshot_observed_at":"2026-08-13T05:48:51.238622Z","submitted_at":"2023-10-16T04:17:13Z","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10049","snapshot_observed_at":"2026-08-14T04:16:48.988150Z","title":"FATE-LLM: An industrial grade federated learning framework for large language models.arXiv preprint arXiv:2310.10049, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.988150Z"},"links":{"cited_paper":"/paper/2310.10049","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:fcd8bd5cb69c9183a40a9e173490ba967063220641c597b630623b7e7ca191fb","observation_id":"5651fa05-28bc-498a-971a-3eba652e4da9","resolution":{"observed_at":"2026-08-14T04:16:48.988150Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.347486Z","title":"FederatedScope-LLM: A comprehensive package for fine-tuning large language models in federated learning","venue":null,"work_id":"da2a2b08-079e-4914-bbdb-b86795d4c35b","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.992664Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:9ec8b3f1aa13b4b34e6740b693b454738a346481556790ce784c5e23bbe4ef6a","observation_id":"b51067df-2a38-4bcf-8d87-6ae17488afc7","resolution":{"observed_at":"2026-08-14T04:16:50.352376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.332064Z","title":"OpenFedLLM: Training large language models on decentralized private data via federated learning","venue":null,"work_id":"904aeec1-8e37-414a-8dd9-2aab38c461f2","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.997616Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:03ab813f42fc4434cd537138ec28daf7a2149917479445ae19275ea2e657dcaf","observation_id":"91b60dd1-247f-45a7-9943-fb63ca631069","resolution":{"observed_at":"2026-08-14T04:16:50.337400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.214342Z","title":"FedLLM- Bench: Realistic benchmarks for federated learning of large language models.Advances in Neural Information Processing Systems, 37:111106–111130, 2024","venue":null,"work_id":"a81b4b93-c171-4d0a-9b10-0fb1dc0e19a7","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.003288Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:8425eb905810e06a9a430787c201a985493412bc6e4be1428f02ccc7ad92b33e","observation_id":"05d9897a-5a82-4ed0-bd8e-42e12a1fc046","resolution":{"observed_at":"2026-08-14T04:16:50.219573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.198061Z","title":"Fed- BCGD: Communication-efficient accelerated block coordinate gradient descent for federated learning","venue":null,"work_id":"30218a1d-1862-4b45-9f81-9bb0df0e36eb","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.009221Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:272d7adb548dbd14063477991d16f7a6fc51574afe98bbc510c1f4d0666da9d2","observation_id":"35b26f49-ef11-4b1b-bc01-a92d4ce935a5","resolution":{"observed_at":"2026-08-14T04:16:50.203185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.181459Z","title":"Improving generalization in federated learning with highly heterogeneous data via momentum-based stochastic controlled weight averaging","venue":null,"work_id":"42ce11de-178b-44b9-add7-1cef950838c5","year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.015368Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:f27327ee0407f1d8d1e822411f0d02816f1ac1a3ea8a7309da2f966df3778ebf","observation_id":"6f5f60c5-89b1-4427-aa63-3183f86fbf06","resolution":{"observed_at":"2026-08-14T04:16:50.187145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2510.27486","last_updated":"2026-01-27T03:01:11Z","snapshot_observed_at":"2026-07-06T22:34:33.419178Z","submitted_at":"2025-10-31T14:04:43Z","title":"FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.27486","snapshot_observed_at":"2026-08-14T04:16:49.020967Z","title":"FedAdamW: A communication-efficient optimizer with convergence and generalization guarantees for federated large models.arXiv preprint arXiv:2510.27486, 2025","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.020967Z"},"links":{"cited_paper":"/paper/2510.27486","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:ab46d18c9390fca8e63ebddfdf0d812bb936e3483be6abd8891278286e7d65b1","observation_id":"51ac086c-f01e-48d4-a183-a25a2f68d975","resolution":{"observed_at":"2026-08-14T04:16:49.020967Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.163105Z","title":"Consistency of local and global flatness for federated learning","venue":null,"work_id":"c1273595-d47d-4090-9888-97113379af61","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.026667Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:21fe76b6d0efb6bf3c196a4a445d8bea738fab3386fb35d8efe5351e5156b71c","observation_id":"facea6ef-1220-4b48-acc7-9f308b8847da","resolution":{"observed_at":"2026-08-14T04:16:50.168353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:49.031233Z","title":"FedMuon: Accelerating federated learning with matrix orthogonalization.arXiv preprint arXiv:2510.27403, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.031233Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:92ea54d1ea199754ef4291d9c80ad269030b536f4aec923d75de6b70099fd33e","observation_id":"1fdd5eb2-965f-4a17-8138-49b52f9dea1b","resolution":{"observed_at":"2026-08-14T04:16:49.031233Z","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":"2026-08-14T04:16:49.036538Z","title":"DP-FedPGN: Finding global flat minima for differentially private federated learning via penalizing gradient norm.arXiv preprint arXiv:2510.27504, 2025","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.036538Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:54ee0efaa2bc695d11403a2a14a27c1b4f83da77df00710e45d0a4dac80af10d","observation_id":"77edb4e7-00b4-40a3-b1d5-7656508e0796","resolution":{"observed_at":"2026-08-14T04:16:49.036538Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.145852Z","title":"Federated residual low-rank adaptation of large language models","venue":null,"work_id":"52995e25-a3fc-4f97-9225-595cd9bce7f1","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.041847Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:91d3a6a868547b72154c2e8c7978f4434af569a1a41525734fa853c7217ab3aa","observation_id":"2d24ccd7-af1b-4783-8165-6bd0bbff9e3c","resolution":{"observed_at":"2026-08-14T04:16:50.151071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.129674Z","title":"Differentially private federated low rank adaptation beyond fixed-matrix","venue":null,"work_id":"40fcf15e-f6d9-4b8b-9f85-cb68db815438","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.046493Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:accd791f8e169bc39e96fe7f5953a01c74a8bd0f1542f85bb2855afbb1f3ae21","observation_id":"ea5c0333-3609-4496-a0ab-456c7dab09cc","resolution":{"observed_at":"2026-08-14T04:16:50.135444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.114358Z","title":"Towards robust parameter-efficient fine-tuning for federated learning.Advances in Neural Information Processing Systems, 38:141777–141800, 2026","venue":null,"work_id":"83c62e63-45c1-428c-a202-107c9870f55d","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.051135Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:03f85462062224191080a0b3c4de756d32c903ffb46079a74c724a2d7ca4c525","observation_id":"a51a564f-6bbd-499a-b73b-2ee0b358340b","resolution":{"observed_at":"2026-08-14T04:16:50.119232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.097818Z","title":"Personalized federated fine- tuning for LLMs via data-driven heterogeneous model architectures","venue":null,"work_id":"cbca7cb1-cf4c-438b-9fe8-175c62add1ae","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.055950Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:1869327a3c09aa1fedf1931a4013c80fcb8bb1a6563f1e280d66a48f3e92fc1c","observation_id":"00f38cca-191a-4184-934b-29625f9da03d","resolution":{"observed_at":"2026-08-14T04:16:50.103714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07925","last_updated":"2026-07-06T13:54:37Z","snapshot_observed_at":"2026-08-12T23:44:53.660547Z","submitted_at":"2024-06-12T06:44:59Z","title":"FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07925","snapshot_observed_at":"2026-08-14T04:16:49.061472Z","title":"FDLoRA: Personalized federated learning of large language model via dual lora tuning.arXiv preprint arXiv:2406.07925, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.061472Z"},"links":{"cited_paper":"/paper/2406.07925","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:dd8cf9f539997f9b42a60f8736b11c80e52cb5db634316ea81191211d88ecf44","observation_id":"f2410eb0-6481-4b62-999d-124bb5c942df","resolution":{"observed_at":"2026-08-14T04:16:49.061472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09432","last_updated":"2025-06-30T07:53:38Z","snapshot_observed_at":"2026-08-12T22:24:53.457399Z","submitted_at":"2024-10-12T08:22:44Z","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09432","snapshot_observed_at":"2026-08-14T04:16:49.066405Z","title":"FedEx-LoRA: Exact aggregation for federated and efficient fine-tuning of foundation models.arXiv preprint arXiv:2410.09432, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.066405Z"},"links":{"cited_paper":"/paper/2410.09432","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:246973e20f9f610dfae9c4ca243b89b1d7e783ae032844e75dfdff61fa416609","observation_id":"e4348d85-7a35-498d-8489-5bf5b2cb5934","resolution":{"observed_at":"2026-08-14T04:16:49.066405Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.080924Z","title":"Fedsvd: Adaptive orthogonalization for private federated learning with lora.Advances in Neural Information Processing Systems, 38:119733–119757, 2026","venue":null,"work_id":"0a5500ff-b01e-4987-8ae6-25fa603da9f5","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.072020Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:142680c67d8bb926ce4211d8bf243cc14e9f98bbaf1a1fb260b3ffc8ccb89918","observation_id":"8a97a8a0-9973-4f8c-9632-18a62878574d","resolution":{"observed_at":"2026-08-14T04:16:50.087111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:49.076811Z","title":"Towards robust and efficient federated low-rank adaptation with heterogeneous clients","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.076811Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:35173e7effb4c12519f3ac0d2f5f931acc927b883b07157159bf9b711c9bb29d","observation_id":"b04c7f65-3a38-43f9-aca5-1c39f5848a2f","resolution":{"observed_at":"2026-08-14T04:16:49.076811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.23638","last_updated":"2026-05-12T01:32:19Z","snapshot_observed_at":"2026-08-10T04:38:20.210388Z","submitted_at":"2026-02-27T03:18:32Z","title":"FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.23638","snapshot_observed_at":"2026-08-14T04:16:49.081884Z","title":"FedRot-LoRA: Mitigating rotational misalignment in federated lora.arXiv preprint arXiv:2602.23638, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.081884Z"},"links":{"cited_paper":"/paper/2602.23638","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:0a53c5ef483399c3402229fa65cc55555b98924010cf4526929c8320936f0c5b","observation_id":"4497f6ea-d78f-4987-98c9-560dec9ed558","resolution":{"observed_at":"2026-08-14T04:16:49.081884Z","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":"2026-08-14T04:16:49.087666Z","title":"LoRA-FAIR: Federated LoRA fine-tuning with aggregation and initialization refinement.arXiv preprint arXiv:2411.14961, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.087666Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:db7027c4ecde0c7c9d26d49e1e9aef0184bc9fa00cebec28a0219b30bd081bce","observation_id":"fde271f9-a8d5-424d-9b15-4c6bef37e81f","resolution":{"observed_at":"2026-08-14T04:16:49.087666Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:50.055604Z","title":"SLoRA: Federated parameter efficient fine-tuning of language models","venue":null,"work_id":"2de8e08c-7bf8-4190-be8f-c91ce1693103","year":2023},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.092285Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:bf7156833de512f63b14af366a0c11ea8098f00a3cd340c7d0053c03bb8bae98","observation_id":"85c710e9-b60e-449b-ab8b-1570631e26e7","resolution":{"observed_at":"2026-08-14T04:16:50.060731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2603.08014","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:49.386935Z","title":"FedMomentum: Preserving lora training momentum in federated fine-tuning.arXiv preprint arXiv:2603.08014, 2026","venue":null,"work_id":"a96e181b-d1ba-495a-b99a-a47ce3665585","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.096597Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:6e4e0d39cb792e6e7975f53c3b81f18f17da7475ebcca9584c91af4c89d6ef4e","observation_id":"a9c3a082-61f5-4283-908a-603ef7b8e6fc","resolution":{"observed_at":"2026-08-14T04:16:49.395973Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.24773","last_updated":"2025-08-20T08:08:03Z","snapshot_observed_at":"2026-08-09T09:03:37.562748Z","submitted_at":"2025-05-30T16:35:32Z","title":"AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption","version":2},"cited_work":{"arxiv_id":"2505.24773","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.24773","snapshot_observed_at":"2026-08-14T04:16:49.268424Z","title":"AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption","venue":"cs.LG","work_id":"57ed3025-d121-45dc-bbf7-10e9e996fddc","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.100684Z"},"links":{"cited_paper":"/paper/2505.24773","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:fcb2e217a8121a449ee7eab56d14f8360311019d013ee19a051940d75e21733b","observation_id":"09b69a96-c22e-498c-8717-ab4a22911d29","resolution":{"observed_at":"2026-08-14T04:16:49.274400Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.13486","last_updated":"2026-05-09T19:00:33Z","snapshot_observed_at":"2026-08-11T03:39:13.195066Z","submitted_at":"2026-02-13T21:42:06Z","title":"Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity","version":2},"cited_work":{"arxiv_id":"2602.13486","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.13486","snapshot_observed_at":"2026-08-14T04:16:49.246166Z","title":"Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity","venue":"cs.LG","work_id":"79019c01-9d15-48cc-9220-9a2bf31c8e97","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.104972Z"},"links":{"cited_paper":"/paper/2602.13486","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:9e8cd7d4ab565ee4656ce7c5464377b973d3211c33822eee8a7a01348d4cb930","observation_id":"816182de-5424-4f4f-97a4-45b97e30a6ac","resolution":{"observed_at":"2026-08-14T04:16:49.251760Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18494","last_updated":"2025-05-24T04:12:12Z","snapshot_observed_at":"2026-08-09T13:16:27.056248Z","submitted_at":"2025-05-24T04:12:12Z","title":"FedHL: Federated Learning for Heterogeneous Low-Rank Adaptation via Unbiased Aggregation","version":1},"cited_work":{"arxiv_id":"2505.18494","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.18494","snapshot_observed_at":"2026-08-14T04:16:49.220173Z","title":"FedHL: Federated Learning for Heterogeneous Low-Rank Adaptation via Unbiased Aggregation","venue":"cs.LG","work_id":"7faa25dd-b2da-4102-8f11-af87386a3011","year":2025},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.110346Z"},"links":{"cited_paper":"/paper/2505.18494","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:16dc0405bcee16a9a7545465b41d53b0dc6c9b7b419ae59752ebddbb91d0f30c","observation_id":"7845cf69-d643-4bb9-86bc-9faa59b845b1","resolution":{"observed_at":"2026-08-14T04:16:49.227782Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T04:16:50.040389Z","title":"Florg: Federated fine-tuning with low-rank gram matrices and procrustes alignment","venue":null,"work_id":"f2844960-fa8c-4238-9d1e-27685aefa64b","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.116140Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:97e602909c2865a144dcf6eefbcd858354d09d8f471d52f75921d35d95042728","observation_id":"718b39d3-cfac-43e5-bbc9-f62b760cce35","resolution":{"observed_at":"2026-08-14T04:16:50.044986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2606.22724","last_updated":"2026-06-21T23:49:22Z","snapshot_observed_at":"2026-07-06T23:57:32.788548Z","submitted_at":"2026-06-21T23:49:22Z","title":"Subspace-Constrained Federated Learning with Low-Rank Adaptation","version":1},"cited_work":{"arxiv_id":"2606.22724","doi":null,"metadata_source":"pith","pith_arxiv_id":"2606.22724","snapshot_observed_at":"2026-08-14T04:16:49.194877Z","title":"Subspace-Constrained Federated Learning with Low-Rank Adaptation","venue":"cs.LG","work_id":"62aa1160-daaf-4af6-a530-05be18aa8c19","year":2026},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:49.120859Z"},"links":{"cited_paper":"/paper/2606.22724","citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:4ee25e4ab51b07e97b026f79e20c9f4fce2d338a1d3e7b8a8f8c72f30e60909c","observation_id":"251abe8d-81b4-47f2-a720-61dacbd3fc99","resolution":{"observed_at":"2026-08-14T04:16:49.202154Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T04:16:48.758696Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-14T04:16:48.758696Z"},"links":{"citing_paper":"/paper/2608.10144"},"observation_digest":"sha256:f7a461fc6698a419ebf81ab39c904acca805e7d848956b5e0ac03d00404bad89","observation_id":"e7cecfcb-aeec-4bc3-a889-badf25a96526","resolution":{"observed_at":"2026-08-14T04:16:48.758696Z","resolver_source":null,"status":"parse_uncertain"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.10144","last_updated":"2026-08-10T18:59:25Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T03:54:47.905903Z","submitted_at":"2026-08-10T18:59:25Z","title":"SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks"},"reference_resolution":{"displayed":91,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":1,"unresolved":40,"verified_exact":6,"verified_fuzzy":43},"total_outbound_references":91},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 91 of 91 outbound references and 0 inbound Pith citation observations for arXiv:2608.10144."}